├── .gitattributes
├── CV2019.md
├── Data-Competition.md
├── Data-Competition2020.md
├── NLP2020.md
├── Other_Awesome.md
├── Others.md
├── README.md
├── Recommendation.md
└── Way.md


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/CV2019.md:
--------------------------------------------------------------------------------
  1 | # AI-News 2019
  2 | - [x] [Semantation(new)](#Semantic-Segmentation)
  3 | - [x] [Re-Identification](#Re-Identification)
  4 | - [x] [Classification](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)  
  5 | - [x] [Graph Neural Networks](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)    
  6 | - [x] [Super-Resolution](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)    
  7 | - [x] [Registration](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)  
  8 | - [x] [Normalization](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)   
  9 | - [x] [Survey](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)   
 10 | - [x] [Dataset](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md)  
 11 | - [x] [Conference and Journal ](https://github.com/xiaoketongxue/CV-News/blob/master/Others.md) 
 12 | 
 13 | # Segmentation
 14 | - [x] [Semantic Segmentation](#Semantic-Segmentation)
 15 | - [x] [2D Medical Segmentation](#2D-Medical-Segmentation)
 16 | - [x] [3D Medical Segmentation](#3D-Medical-Segmentation)
 17 | - [x] [Instance Segmentation](#Instance-Segmentation)
 18 | - [x] [Panoptic Segmentation](#Panoptic-Segmentation)
 19 | - [x] [Video Segmentation](#Video-Segmentation)
 20 | 
 21 | ## Semantic Segmentation
 22 | ### 2020
 23 |   - AAAI
 24 |     + [Segmenting Medical MRI via Recurrent Decoding Cell](https://arxiv.org/abs/1911.09401)[[Code]](https://github.com/beijixiong3510/OWM)
 25 |     + [F3Net: Fusion, Feedback and Focus for Salient Object Detection](https://arxiv.org/abs/1911.11445)[[Code]](https://github.com/weijun88/F3Net)
 26 |     + [An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation](https://arxiv.org/abs/1912.08954)
 27 |     + [JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds](https://arxiv.org/abs/1912.09654)[Code](https://github.com/dlinzhao/JSNet)
 28 |   - ICLR
 29 |     + [FasterSeg: Searching for Faster Real-time Semantic Segmentation ](https://openreview.net/pdf?id=BJgqQ6NYvB)[[Code]](https://github.com/TAMU-VITA/FasterSeg)
 30 | 
 31 | 
 32 | ### 2019
 33 |   - Nature Machine Intelligence
 34 |     + [Clinically applicable deep learning framework for organs at risk delineation in CT images](https://www_nature.xilesou.top/articles/s42256-019-0099-z)[[Code]](https://github.com/uci-cbcl/UaNet)
 35 |     + [An integrated iterative annotation technique for easing neural network training in medical image analysis](https://www.nature.com/articles/s42256-019-0018-3)[[Code]](https://github.com/SarderLab/H-AI-L)
 36 |     + [Continual learning of context-dependent processing in neural networks](https://www_nature.xilesou.top/articles/s42256-019-0080-x)
 37 |     + [Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks](https://www.nature.com/articles/s42256-019-0101-9)[[Code]](https://codeocean.com/capsule/9068249/tree/v1)
 38 |     + [Deep learning and alternative learning strategies for retrospective real-world clinical data](https://www.nature.com/articles/s41746-019-0122-0)[[Code]](https://github.com/davidchenatmayo/ForPubDM)
 39 |   - NEW
 40 |     + [PointRend: Image Segmentation as Rendering](https://arxiv.org/abs/1912.08193)[Kaiming He]
 41 |     + [Momentum Contrast for Unsupervised Visual Representation Learning](https://arxiv.org/abs/1911.05722)[Kaiming He]
 42 |     + [Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research](https://arxiv.org/abs/1911.05063)[[Code]](https://github.com/NVIDIAGameWorks/kaolin/)
 43 |     + [Reinventing 2D Convolutions for 3D Medical Images](https://arxiv.org/abs/1911.10477)[[Code]](https://github.com/m3dv/ACSConv)
 44 |     + [A Multigrid Method for Efficiently Training Video Models](https://arxiv.org/abs/1912.00998)[Kaiming He]
 45 |   - ICCV2019
 46 |     + [ShelfNet for Fast Semantic Segmentation](https://arxiv.org/abs/1811.11254v6)[[Code]](https://arxiv.org/abs/1811.11254v6)
 47 |     + [Recurrent U-Net for Resource-Constrained Segmentation](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Recurrent_U-Net_for_Resource-Constrained_Segmentation_ICCV_2019_paper.pdf)
 48 |     + [Eye Semantic Segmentation with a Lightweight Model](https://arxiv.org/abs/1911.01049)[Code](https://github.com/th2l/Eye_VR_Segmentation)[Workshop]
 49 |     + [On the Efficacy of Knowledge Distillation](https://arxiv.org/abs/1910.01348)
 50 |     + [DeepGCNs: Making GCNs Go as Deep as CNNs](https://arxiv.org/abs/1910.06849)
 51 |     + [SegSort: Segmentation by Discriminative Sorting of Segments](https://arxiv.org/abs/1910.06962)[[Code]](https://jyhjinghwang.github.io/projects/segsort.html)
 52 |     + [Domain Adaptation for Semantic Segmentation with Maximum Squares Loss](https://arxiv.org/abs/1909.13589)
 53 |     + [ACFNet: Attentional Class Feature Network for Semantic Segmentation](https://arxiv.org/abs/1909.09408)
 54 |     + [Asymmetric Non-local Neural Networks for Semantic Segmentation](https://arxiv.org/abs/1908.07678)[[Code]](https://github.com/MendelXu/ANN)
 55 |     + [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://arxiv.org/abs/1907.05740)[[Project]](https://nv-tlabs.github.io/GSCNN/)
 56 |     + [CCNet: Criss-Cross Attention for Semantic Segmentation](https://arxiv.org/abs/1811.11721)[[Pytorch]](https://github.com/speedinghzl/CCNet)
 57 |     + [SPGNet: Semantic Prediction Guidance for Scene Parsing](https://arxiv.org/abs/1908.09798)
 58 |     + [Expectation-Maximization Attention Networks for Semantic Segmentation(31 Jul)](https://arxiv.org/abs/1907.13426)[[Code]](https://github.com/XiaLiPKU/EMANet) 
 59 |     + [Boundary-Aware Feature Propagation for Scene Segmentation](https://arxiv.org/abs/1909.00179)
 60 |     + [Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation](https://arxiv.org/abs/1909.10469)
 61 |     + [Explicit Shape Encoding for Real-Time Instance Segmentation](https://arxiv.org/abs/1908.04067)[[Code]](https://github.com/WenqiangX/ese_seg)
 62 |     + [Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation](https://arxiv.org/abs/1909.04161)
 63 |     + [Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation](https://arxiv.org/abs/1909.00589)
 64 |     + [Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation](https://arxiv.org/abs/1908.07669)
 65 |     + [Incremental Class Discovery for Semantic Segmentation with RGBD Sensing](https://arxiv.org/abs/1907.10008)
 66 |     + [Similarity-Preserving Knowledge Distillation](https://arxiv.org/abs/1907.09682)
 67 |     + [Orientation-aware Semantic Segmentation on Icosahedron Spheres](https://arxiv.org/abs/1907.12849)
 68 |     + [Incremental Learning Techniques for Semantic Segmentation](https://arxiv.org/abs/1907.13372)
 69 |     + [Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion](https://arxiv.org/abs/1908.00382)
 70 |     + [Learning Lightweight Lane Detection CNNs by Self Attention Distillation](https://arxiv.org/abs/1908.00821)[[tensorflow]](https://github.com/cardwing/Codes-for-Lane-Detection)
 71 |     + [SqueezeNAS: Fast neural architecture search for faster semantic segmentation](https://arxiv.org/abs/1908.01748)[[ICCVW]]
 72 |     + [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://arxiv.org/abs/1908.03245)
 73 |     + [Interpolated Convolutional Networks for 3D Point Cloud Understanding](https://arxiv.org/abs/1908.04512)
 74 |     + [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://arxiv.org/abs/1908.06391)
 75 |     + [Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization](https://arxiv.org/abs/1908.06387)
 76 |     + [Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition](https://arxiv.org/abs/1908.07325)[[Code]](https://github.com/HCPLab-SYSU/SSGRL)
 77 |     + [Attention on Attention for Image Captioning](https://arxiv.org/abs/1908.06954)[[Code]](https://github.com/husthuaan/AoANet)
 78 |     + [A Fast and Accurate One-Stage Approach to Visual Grounding](https://arxiv.org/abs/1908.06354)
 79 |     + [Context-Aware Emotion Recognition Networks](https://arxiv.org/abs/1908.05913)[[Code]](https://arxiv.org/abs/1908.05913)
 80 |     + [Learning Filter Basis for Convolutional Neural Network Compression](https://arxiv.org/pdf/1908.08932.pdf)[[Pytorch]](https://github.com/ofsoundof/learning_filter_basis)
 81 |     + [Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels](https://arxiv.org/abs/1908.09597)
 82 |     + [Deep Camera: A Fully Convolutional Neural Network for Image Signal Processing](https://arxiv.org/abs/1908.09191)[[workshop]]
 83 |     + [Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment](https://arxiv.org/abs/1908.11821)[Code](https://github.com/LeiJiangJNU/DAMDNet)[[workshop]]
 84 |     + [Adversarial Learning with Margin-based Triplet Embedding Regularization](https://arxiv.org/abs/1909.09481)[Code](https://github.com/zhongyy/Adversarial_MTER)
 85 |     + [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://arxiv.org/abs/1909.12828)[Code](https://www.seas.upenn.edu/~nkolot/projects/spin/)
 86 |     + [RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking](https://arxiv.org/abs/1910.00694)[[Code]](https://bitbucket.org/eye-ush/ritnet/)[workshop]
 87 |     + [Mask-Guided Attention Network for Occluded Pedestrian Detection](https://arxiv.org/abs/1910.06160)[[Code]](https://github.com/Leotju/MGAN)
 88 |     + [Guided Image-to-Image Translation with Bi-Directional Feature Transformation](https://arxiv.org/list/cs.CV/recent)[[Code]](https://github.com/vt-vl-lab/Guided-pix2pix)
 89 |     + [Seeing What a GAN Cannot Generate](https://arxiv.org/abs/1910.11626)[[Code]](https://arxiv.org/abs/1910.11626)
 90 |   - NIPS 2019
 91 |     + [Object landmark discovery through unsupervised adaptation](https://arxiv.org/abs/1910.09469)[[Code]](https://arxiv.org/abs/1910.09469)
 92 |     + [Implicit Semantic Data Augmentation for Deep Networks](https://arxiv.org/abs/1909.12220)[[Pytorch]](https://github.com/blackfeather-wang/ISDA-for-Deep-Networks)
 93 |     + [Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations](https://arxiv.org/pdf/1911.05277.pdf)[[code]](https://github.com/fly519/ELGS)
 94 |     + [FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video](https://arxiv.org/abs/1910.06407)[Workshop]
 95 |   - BMVC2019
 96 |     + [MixNet: Mixed Depthwise Convolutional Kernels](https://arxiv.org/abs/1907.09595)[Code](https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet)
 97 |     + [DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation](https://arxiv.org/abs/1907.11357)[[Pytorch]](https://github.com/Reagan1311/DABNet)
 98 |     + [Dual Graph Convolutional Network for Semantic Segmentation](https://arxiv.org/abs/1909.06121)
 99 |     + [Global Aggregation then Local Distribution in Fully Convolutional Networks](https://arxiv.org/abs/1909.07229)[Code](https://github.com/lxtGH/GALD-Net)
100 |     + [Feature Pyramid Encoding Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1909.08599)
101 |     + [Accurate and Compact Convolutional Neural Networks with Trained Binarization](https://arxiv.org/abs/1909.11366)[[oral]]
102 |     + [Referring Expression Object Segmentation with Caption-Aware Consistency](https://arxiv.org/abs/1910.04748)[[Pytorch]](https://github.com/wenz116/lang2seg)
103 |   - CVPR2019   
104 |     + [Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search](https://arxiv.org/abs/1903.03777)[[Code]](https://github.com/lixincn2015/Partial-Order-Pruning)
105 |     + [Searching for A Robust Neural Architecture in Four GPU Hours](https://arxiv.org/abs/1910.04465)[[Code]](https://github.com/D-X-Y/NAS-Projects)[camera-ready version]
106 |     + [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://arxiv.org/abs/1901.02985)[[Tensorflow]](https://github.com/tensorflow/models/tree/master/research/deeplab)[[Pytorch]](https://github.com/MenghaoGuo/AutoDeeplab)
107 |     + [ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network](https://arxiv.org/search/?query=ESPNetv2&searchtype=all&source=header)[[Code]](https://github.com/sacmehta/ESPNetv2)
108 |     + [DFANet：Deep Feature Aggregation for Real-Time Semantic Segmentation](https://arxiv.org/abs/1904.02216)[[Pytoch]](https://github.com/huaifeng1993/DFANet)
109 |     + [In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images(Mar 2019))](https://arxiv.org/abs/1903.08469)[[Pytroch]](https://github.com/orsic/swiftnet)
110 |     + [Knowledge Adaptation for Efficient Semantic Segmentation(Mar 2019)](https://arxiv.org/abs/1903.04688)
111 |     + [Dual Attention Network for Scene Segmentation(Sep 2018)](https://arxiv.org/abs/1809.02983)[[Pytorch]](https://github.com/junfu1115/DANet) 
112 |     + [Adaptive Pyramid Context Network for Semantic Segmentation](http://openaccess.thecvf.com/content_CVPR_2019/papers/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.pdf)
113 |     + [Co-Occurrent Features in Semantic Segmentation](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.pdf)
114 |     + [Structured Knowledge Distillation for Semantic Segmentation(Mar 2019)](https://arxiv.org/abs/1903.04197)
115 |     + [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://arxiv.org/abs/1903.02351)
116 |     + [Semantic Correlation Promoted Shape-Variant Context for Segmentation](https://arxiv.org/abs/1909.02651)
117 |     + [Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images](https://arxiv.org/abs/1905.06368)[oral]
118 |     + [Bidirectional Learning for Domain Adaptation of Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.10620)[[Pytoch]](https://github.com/liyunsheng13/BDL)
119 |     + [Seamless Scene Segmentation](https://arxiv.org/abs/1905.01220)
120 |     + [Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation](https://arxiv.org/abs/1904.11693)   
121 |     + [Cross-Modal Self-Attention Network for Referring Image Segmentation(Apr 2019)](https://arxiv.org/abs/1904.04745)
122 |     + [Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation](https://arxiv.org/abs/1903.02120)[[Pytorch]](https://github.com/xiaoketongxue/DUpsampling)
123 |     + [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://arxiv.org/abs/1902.10421)
124 |     + [A Cross-Season Correspondence Dataset for Robust Semantic Segmentation](https://arxiv.org/abs/1903.06916)
125 |     + [Large-scale interactive object segmentation with human annotators](https://arxiv.org/abs/1903.10830)
126 |     + [Deep Modular Co-Attention Networks for Visual Question Answering](https://arxiv.org/abs/1906.10770)
127 |     + [Enhancing Salient Object Segmentation Through Attention](https://arxiv.org/abs/1905.11522)[CVPRW】
128 |     + [The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation](https://arxiv.org/abs/1907.01342)
129 |     + [Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhuang_Structured_Binary_Neural_Networks_for_Accurate_Image_Classification_and_Semantic_CVPR_2019_paper.pdf)
130 |   - AAAI 2019
131 |     + [Learning Fully Dense Neural Networks for Image Semantic Segmentation(May 2019)](https://arxiv.org/abs/1905.08929)
132 |   - ICIP2019
133 |     + [Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation](https://arxiv.org/abs/1809.09077)[[Code]](https://github.com/shangweihung/LDFNet)
134 |     + [Implicit Background Estimation for Semantic Segmentation](https://arxiv.org/abs/1905.13306)
135 |     + [LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation](https://arxiv.org/pdf/1905.02423.pdf)
136 |     + [What's There in The Dark](https://ieeexplore.ieee.org/abstract/document/8803299/authors#authors)[[Keras]](https://github.com/sauradip/night_image_semantic_segmentation)
137 |     + [Diversity in Fashion Recommendation using Semantic Parsing](https://arxiv.org/abs/1910.08292)[[pytorch]](https://github.com/sagarverma/FashionRecommendationST-LSTM)
138 |   - SPL
139 |     + [RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation(29 Jun)](https://arxiv.org/abs/1907.00135)
140 |   -  SCI  
141 |     + [Self-Supervised Model Adaptation for Multimodal Semantic Segmentation](https://arxiv.org/abs/1808.03833)[[Code]](https://github.com/DeepSceneSeg)[IJCV]   
142 |     + [Fine-grained Action Segmentation using the Semi-Supervised Action GAN](https://arxiv.org/abs/1909.09269)[ Pattern Recognition]  
143 |   - WACV
144 |     + [CNN-based Semantic Segmentation using Level Set Loss](https://arxiv.org/abs/1910.00950)
145 |     + [Shape Constrained Network for Eye Segmentation in the Wild](https://arxiv.org/abs/1910.05283)[[Code]](https://arxiv.org/abs/1910.05283)
146 |   - ICCD
147 |     + [VNet: A Versatile Network for Efficient Real-Time Semantic Segmentation](http://www.iccd-conf.com/Program_2019_.html)
148 |   - other
149 |     + [SCAttNet: Semantic Segmentation Network with Spatial and Channel Attention Mechanism for High-Resolution Remote Sensing Images](https://arxiv.org/abs/1912.09121)[[Code]](https://github.com/lehaifeng/SCAttNet)
150 |     + [PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing](https://arxiv.org/abs/1912.07190)[[Code]](https://github.com/rfuruta/pixelRL)
151 |     + [Semantic Segmentation for Compound figures](https://arxiv.org/abs/1912.07142)
152 |     + [LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation](https://arxiv.org/abs/1912.06683)
153 |     + [Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation](https://arxiv.org/abs/1912.03183)
154 |     + [RGPNet: A Real-Time General Purpose Semantic Segmentation](https://arxiv.org/abs/1912.01394)
155 |     + [Deep Object Co-segmentation via Spatial-Semantic Network Modulation](https://arxiv.org/abs/1911.12950)
156 |     + [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://arxiv.org/abs/1911.11236)[[Code]](https://github.com/QingyongHu/RandLA-Net)
157 |     + [Stagewise Knowledge Distillation](https://arxiv.org/abs/1911.06786)
158 |     + [Location-aware Upsampling for Semantic Segmentation](https://arxiv.org/abs/1911.05250)[Code](https://arxiv.org/abs/1911.05250)
159 |     + [Improving Semantic Segmentation via Dilated Affinity](https://arxiv.org/abs/1907.07011)
160 |     + [LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution](https://arxiv.org/abs/1910.11853)
161 |     + [Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images](https://arxiv.org/abs/1910.08313)[[Pytorch]](https://github.com/z-bingo/Attention-Mechanism-Enhanced-KPN)
162 |     + [Background Segmentation for Vehicle Re-Identification](https://arxiv.org/abs/1910.06613)
163 |     + [Saliency Guided Self-attention Network for Weakly-supervised Semantic Segmentation](https://arxiv.org/abs/1910.05475)
164 |     + [Unrestricted Adversarial Attacks for Semantic Segmentation](https://arxiv.org/abs/1910.02354)
165 |     + [Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation](https://arxiv.org/abs/1910.01269)
166 |     + [3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation](https://arxiv.org/abs/1910.01460)
167 |     + [End-to-End Deep Convolutional Active Contours for Image Segmentation](https://arxiv.org/abs/1909.13359)
168 |     + [IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers](https://arxiv.org/list/cs.CV/pastweek?skip=0&show=25)
169 |     + [Point Attention Network for Semantic Segmentation of 3D Point Clouds](https://arxiv.org/abs/1909.12663)
170 |     + [Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/abs/1909.11065)[[Code]](https://arxiv.org/list/cs.CV/recent)
171 |     + [A New Few-shot Segmentation Network Based on Class Representation](https://arxiv.org/abs/1909.08754)
172 |     + [Object Segmentation using Pixel-wise Adversarial Loss](https://arxiv.org/abs/1909.10341)
173 |     + [Graph-guided Architecture Search for Real-time Semantic Segmentation](https://arxiv.org/abs/1909.06793)
174 |     + [Boosting Real-Time Driving Scene Parsing with Shared Semantics](https://arxiv.org/abs/1909.07038)
175 |     + [Squeeze-and-Attention Networks for Semantic Segmentation](https://arxiv.org/abs/1909.03402)
176 |     + [Semantic Segmentation of Panoramic Images Using a Synthetic Dataset](https://arxiv.org/abs/1909.00532)
177 |     + [Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation](https://arxiv.org/abs/1908.11525)
178 |     + [Revisiting CycleGAN for semi-supervised segmentation](https://arxiv.org/abs/1908.11569)
179 |     + [LU-Net: An Efficient Network for 3D LiDAR Point Cloud Semantic Segmentation Based on End-to-End-Learned 3D Features and U-Net](https://arxiv.org/abs/1908.11656)
180 |     + [Where Is My Mirror?](https://arxiv.org/abs/1908.09101)
181 |     + [Don't ignore Dropout in Fully Convolutional Networks](https://arxiv.org/abs/1908.09162)
182 |     + [See More Than Once -- Kernel-Sharing Atrous Convolution for Semantic Segmentation](https://arxiv.org/abs/1908.09443)
183 |     + [Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach](https://arxiv.org/abs/1908.09547)
184 |     + [Consensus Feature Network for Scene Parsing](https://arxiv.org/abs/1907.12411)
185 |     + [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://arxiv.org/abs/1908.05724)
186 |     + [See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion](https://arxiv.org/abs/1908.05868)
187 |     + [Adaptative Inference Cost With Convolutional Neural Mixture Models](https://arxiv.org/abs/1908.06694)
188 |     + [Dynamic Graph Message Passing Networks](https://arxiv.org/abs/1908.06955)
189 |     + [PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation](https://arxiv.org/abs/1908.05425)
190 |     + [MoGA: Searching Beyond MobileNetV3](https://arxiv.org/pdf/1908.01314.pdf)
191 |     + [I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentation](https://arxiv.org/abs/1908.02711)
192 |     + [EdgeNet: Semantic Scene Completion from RGB-D images](https://arxiv.org/abs/1908.02893)
193 |     + [ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules](https://arxiv.org/abs/1908.03093)
194 |     + [Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes](https://arxiv.org/abs/1908.00448)
195 |     + [DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation](https://arxiv.org/abs/1907.12022)
196 |     + [Dilated Point Convolutions: On the Receptive Field of Point Convolutions](https://arxiv.org/abs/1907.12046)
197 |     + [ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks](https://arxiv.org/abs/1907.12859)
198 |     + [Grid Saliency for Context Explanations of Semantic Segmentation](https://arxiv.org/abs/1907.13054)
199 |     + [A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network](https://arxiv.org/abs/1907.11394)
200 |     + [Semantic Deep Intermodal Feature Transfer: Transferring Feature Descriptors Between Imaging Modalities](https://arxiv.org/list/cs.CV/recent)
201 |     + [Context-Integrated and Feature-Refined Network for Lightweight Urban Scene Parsing](https://arxiv.org/pdf/1907.11474.pdf)
202 |     + [Single Level Feature-to-Feature Forecasting with Deformable Convolutions](https://arxiv.org/abs/1907.11475)
203 |     + [SDNet: Semantically Guided Depth Estimation Network](https://arxiv.org/abs/1907.10659)
204 |     + [Self-supervised Domain Adaptation for Computer Vision Tasks](https://arxiv.org/abs/1907.10915)[Pytorch](https://github.com/Jiaolong/self-supervised-da)
205 |     + [Make Skeleton-based Action Recognition Model Smaller, Faster and Better](https://arxiv.org/abs/1907.09658)
206 |     + [LYTNet: A Convolutional Neural Network for Real-Time Pedestrian Traffic Lights and Zebra Crossing Recognition for the Visually Impaired](https://arxiv.org/abs/1907.09706)
207 |     + [RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation](https://arxiv.org/abs/1907.09707)
208 |     + [Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks](https://arxiv.org/abs/1907.09438)
209 |     + [Adaptive Context Encoding Module for Semantic Segmentation](https://arxiv.org/abs/1907.06082)
210 |     + [Mango Tree Net -- A fully convolutional network for semantic segmentation and individual crown detection of mango trees](https://arxiv.org/abs/1907.06915)
211 |     + [Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision](https://arxiv.org/abs/1907.07023)
212 |     + [Efficient Segmentation: Learning Downsampling Near Semantic Boundaries](https://arxiv.org/abs/1907.07156)
213 |     + [VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing](https://arxiv.org/abs/1907.05653)
214 |     + [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation(12 Jul)](https://arxiv.org/abs/1907.05740)[Code](https://nv-tlabs.github.io/GSCNN/)
215 |     + [SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images](https://arxiv.org/abs/1907.03089)
216 |     + [Slim-CNN: A Light-Weight CNN for Face Attribute Prediction](https://arxiv.org/abs/1907.02157)
217 |     + [ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation](https://arxiv.org/abs/1906.11428)
218 |     + [Hard Pixels Mining: Learning Using Privileged Information for Semantic Segmentation](https://arxiv.org/abs/1906.11437)
219 |     + [ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1906.09826)[[Pytorch]](https://github.com/xiaoyufenfei/ESNet)
220 |     + [Recurrent U-Net for Resource-Constrained Segmentation](https://arxiv.org/abs/1906.04913)
221 |     + [Topology-Preserving Deep Image Segmentation](https://arxiv.org/abs/1906.05404)
222 |     + [Show, Match and Segment: Joint Learning of Semantic Matching and Object Co-segmentation](https://arxiv.org/pdf/1906.05857.pdf)
223 |     + [DiCENet: Dimension-wise Convolutions for Efficient Networks](https://arxiv.org/abs/1906.03516)
224 |     + [Cross-view Semantic Segmentation for Sensing Surroundings](https://arxiv.org/abs/1906.03560)
225 |     + [NAS-FCOS: Fast Neural Architecture Search for Object Detection](https://arxiv.org/abs/1906.04423)
226 |     + [Gated CRF Loss for Weakly Supervised Semantic Image Segmentation](https://arxiv.org/abs/1906.04651)
227 |     + [Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions](https://arxiv.org/abs/1906.02885)
228 |     + [Zero-Shot Semantic Segmentation](https://arxiv.org/abs/1906.00817)
229 |     + [Consistency regularization and CutMix for semi-supervised semantic segmentation](https://arxiv.org/abs/1906.01916)
230 |     + [RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving](https://arxiv.org/abs/1906.00208)
231 |     + [Zero-Shot Semantic Segmentation](https://arxiv.org/abs/1906.00817)
232 |     + [Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation](https://arxiv.org/abs/1905.12190)
233 |     + [Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation](https://arxiv.org/abs/1905.12190)
234 |     + [Incorporating Human Domain Knowledge in 3D LiDAR-based Semantic Segmentation](https://arxiv.org/abs/1905.09533)
235 |     + [U-Net Based Multi-instance Video Object Segmentation(May 2019)](https://arxiv.org/abs/1905.07826)
236 |     + [Boundary Loss for Remote Sensing Imagery Semantic Segmentation(May 2019)](https://arxiv.org/abs/1905.07852)
237 |     + [Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images(May 2019)](https://arxiv.org/abs/1905.05661)
238 |     + [Simultaneous Object Detection and Semantic Segmentation](https://arxiv.org/abs/1905.02285)
239 |     + [Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images](https://arxiv.org/abs/1905.03198)
240 |     + [EdgeSegNet: A Compact Network for Semantic Segmentation(May 2019)](https://arxiv.org/abs/1905.04222)
241 |     + [SEMEDA: Enhancing Segmentation Precision with Semantic Edge Aware Loss](https://arxiv.org/abs/1905.01892)
242 |     + [Segmenting the Future(Apr 2019)](https://arxiv.org/abs/1904.10666)[[Code]](https://github.com/eddyhkchiu/segmenting_the_future/)
243 |     + [CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing(Apr 2019)](https://arxiv.org/abs/1904.08170)
244 |     + [ACE: Adapting to Changing Environments for Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.06268)
245 |     + [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation(Mar 2019)](https://arxiv.org/abs/1903.11816)[[Pytorch]](https://github.com/wuhuikai/FastFCN)
246 |     + [Architecture Search of Dynamic Cells for Semantic Video Segmentation(Apr 2019)](https://arxiv.org/abs/1904.02371)
247 |     + [Template-Based Automatic Search of Compact Semantic Segmentation Architectures(Apr 2019)](https://arxiv.org/abs/1904.02365)
248 |     + [DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.02216)
249 |     + [DADA: Depth-aware Domain Adaptation in Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.01886)
250 |     + [GFF: Gated Fully Fusion for Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.01803)
251 |     + [MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks(Apr 2019)](https://arxiv.org/abs/1904.01795)
252 |     + [Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.00876)
253 |     + [The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation(Apr 2019)](https://arxiv.org/abs/1904.03215)
254 |     + [Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes(Apr 2019)](https://arxiv.org/abs/1904.09092)
255 |     + [The iterative convolution-thresholding method (ICTM) for image segmentation(Apr 2019)](https://arxiv.org/abs/1904.10917)
256 |     + [Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields( Apr 2019)](https://arxiv.org/abs/1904.11487)
257 | ### 2018
258 |   - CVPR 2018
259 |     + [Context Encoding for Semantic Segmentation(Mar 2018)](https://hangzhang.org/PyTorch-Encoding/experiments/segmentation.html)
260 |     + [DenseASPP for Semantic Segmentation in StreetScenes](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_DenseASPP_for_Semantic_CVPR_2018_paper.pdf)[[Pytorch]](https://github.com/DeepMotionAIResearch/DenseASPP/tree/master/models)
261 |     + [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing(May 2018)](https://arxiv.org/abs/1805.04409)
262 |     + [Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.pdf)
263 |     + [DFN:Learning a Discriminative Feature Network for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_Learning_a_Discriminative_CVPR_2018_paper.pdf)
264 |     + [Guided Proofreading of Automatic Segmentations for Connectomics](http://openaccess.thecvf.com/content_cvpr_2018/papers/Haehn_Guided_Proofreading_of_CVPR_2018_paper.pdf)
265 |     + [Recurrent Scene Parsing with Perspective Understanding in the Loop](http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/0534.pdf)
266 |     + [Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ding_Context_Contrasted_Feature_CVPR_2018_paper.pdf)
267 |     + [icient interactive annotation of segmentation datasets with polygon rnn++](http://openaccess.thecvf.com/content_cvpr_2018/papers/Acuna_Efficient_Interactive_Annotation_CVPR_2018_paper.pdf)
268 |     + [Compassionately Conservative Balanced Cuts for Image Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cahill_Compassionately_Conservative_Balanced_CVPR_2018_paper.pdf)
269 |     + [Dynamic-structured Semantic Propagation Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liang_Dynamic-Structured_Semantic_Propagation_CVPR_2018_paper.pdf)
270 |     + [In-Place Activated BatchNorm for Memory-Optimized Training of DNNs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bulo_In-Place_Activated_BatchNorm_CVPR_2018_paper.pdf)
271 |     + [Error Correction for Dense Semantic Image Labeling](http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w14/Huang_Error_Correction_for_CVPR_2018_paper.pdf)
272 |     + [Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Revisiting_Dilated_Convolution_CVPR_2018_paper.pdf)
273 |     + [On the Importance of Label Quality for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zlateski_On_the_Importance_CVPR_2018_paper.pdf)
274 |     + [Referring Image Segmentation via Recurrent Refinement Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Referring_Image_Segmentation_CVPR_2018_paper.pdf)[[Code]](https://github.com/liruiyu/referseg_rrn)  
275 |     + [Learning Superpixels with Segmentation-Aware Affinity Loss](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tu_Learning_Superpixels_With_CVPR_2018_paper.pdf)
276 |     + [Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer](http://openaccess.thecvf.com/content_cvpr_2018/papers/Fang_Weakly_and_Semi_CVPR_2018_paper.pdf)
277 |     + [Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning](https://github.com/wutianyiRosun/Segmentation.X)
278 |     + [Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ahn_Learning_Pixel-Level_Semantic_CVPR_2018_paper.pdf)
279 |     + [Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf)
280 |     + [Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Revisiting_Dilated_Convolution_CVPR_2018_paper.pdf)
281 |     + [Bootstrapping the Performance of Webly Supervised Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Bootstrapping_the_Performance_CVPR_2018_paper.pdf)
282 |     + [Normalized Cut Loss for Weakly-Supervised CNN Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tang_Normalized_Cut_Loss_CVPR_2018_paper.pdf)
283 |     + [Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf)
284 |     + [Weakly Supervised Instance Segmentation Using Class Peak Response](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Weakly_Supervised_Instance_CVPR_2018_paper.pdf)
285 | 
286 |   - ECCV 2018
287 |     + [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation(Aug 2018)](https://www.baidu.com/link?url=jC2iP9t_S6_XTmwSijQ9qCKLn6n51z71MV-Tki8qdlIgHCUgXgeIntJCx1PVmzZE&wd=&eqid=af75bc8c00018f26000000035cc7a700)
288 |     + [ICNet for Real-Time Semantic Segmentation on High-Resolution Images(Apr 2017)](https://arxiv.org/abs/1704.08545)[[Pytorch]](https://github.com/hszhao/ICNet)
289 |     + [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation(Mar 2018 )](https://arxiv.org/abs/1803.06815)[[Pytorch]](https://github.com/sacmehta/ESPNet)
290 |     + [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation(Feb 2018)](https://arxiv.org/abs/1802.02611v1)[Deeplab V3+]
291 |     + [Pyramid Attention Network for Semantic Segmentation](https://www.baidu.com/link?url=dZPzXSz0sfHZylg1XlEb608N5xbz2bWdZWR0vJCVEqct4jh21DANQeE1NNqK1gwU&wd=&eqid=f4fbbf6400068658000000025ddf6a2e)
292 |     + [Adaptive Affinity Fields for Semantic Segmentation(Mar 2018)](https://arxiv.org/abs/1803.10335)
293 |     + [ExFuse: Enhancing Feature Fusion for Semantic Segmentation(Apr 2018)](https://arxiv.org/abs/1804.03821)
294 |     + [Unified Perceptual Parsing for Scene Understanding(Jul 2018)](https://arxiv.org/abs/1807.10221)
295 |     + [Multi-Scale Context Intertwining for Semantic Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/papers/Di_Lin_Multi-Scale_Context_Intertwining_ECCV_2018_paper.pdf)
296 |     + [PSANet: Point-wise Spatial Attention Network for Scene Parsing](https://hszhao.github.io/papers/eccv18_psanet.pdf)
297 |   - NeurIPS 2018
298 |     + [Searching for Efficient Multi-Scale Architectures for Dense Image Prediction(Sep 2018)](https://arxiv.org/abs/1809.04184)[[Tensorflow]](https://github.com/tensorflow/models/tree/master/research/deeplab)
299 |     + [A Probabilistic U-Net for Segmentation of Ambiguous Images(Jun 2018)](https://arxiv.org/abs/1806.05034)
300 |     + [DifNet: Semantic Segmentation by DiffusionNetworks(May 2018)](https://arxiv.org/abs/1805.08015v1)
301 |   - AAAI 2018
302 |     + [Spatial As Deep: Spatial CNN for Traffic Scene Understanding(Dec 2017)](https://arxiv.org/abs/1712.06080)
303 |     + [Mix-and-Match Tuning for Self-Supervised Semantic Segmentation(Dec 2017)](https://arxiv.org/abs/1712.00661)
304 |     + [Searching for Efficient Multi-Scale Architectures for Dense Image Prediction](https://papers.nips.cc/paper/8087-searching-for-efficient-multi-scale-architectures-for-dense-image-prediction.pdf)
305 |     + [A^2-Nets: Double Attention Networks](https://papers.nips.cc/paper/7318-a2-nets-double-attention-networks.pdf)
306 |     + [Symbolic Graph Reasoning Meets Convolutions](https://papers.nips.cc/paper/7456-symbolic-graph-reasoning-meets-convolutions)
307 |     + [Beyond Grids: Learning Graph Representations for Visual Recognition](https://github.com/wutianyiRosun/Segmentation.X)
308 |   - IJCAI 2018
309 |     + [High Resolution Feature Recovering for Accelerating Urban Scene Parsing](https://www.ijcai.org/proceedings/2018/0161.pdf)
310 |   - Othes
311 |     + [SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving](https://arxiv.org/abs/1909.08291)[Code](https://arxiv.org/abs/1909.08291)
312 |     + [Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation](https://arxiv.org/pdf/1907.10303.pdf)
313 |     + [RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation][ICPR]
314 |     + [CCNet: Criss-Cross Attention for Semantic Segmentation(Nov 2018)](https://arxiv.org/abs/1811.11721)[[Pytorch]](https://github.com/speedinghzl/CCNet)
315 |     + [OCNet: Object Context Network for Scene Parsing(Sep 2018)](https://arxiv.org/abs/1809.00916)[[Pytorch]](https://github.com/PkuRainBow/OCNet.pytorch)
316 |     + [CGNet: A Light-weight Context Guided Network for Semantic Segmentation(Nov 2018)](https://arxiv.org/abs/1811.08201)[[Pytorch]](https://github.com/wutianyiRosun/CGNet)
317 |     + [ShelfNet for Real-time Semantic Segmentation, Multi-path segmentation network(Nov 2018)](https://arxiv.org/abs/1811.11254v2)[[Pytorch]](https://github.com/juntang-zhuang/ShelfNet)
318 |     + [Evaluating Bayesian Deep Learning Methods for Semantic Segmentation(Nov 2018)](https://arxiv.org/abs/1811.12709)
319 |     + [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://arxiv.org/abs/1812.01593)[Code](https://nv-adlr.github.io/publication/2018-Segmentation)
320 |     + [Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation(Mar 2018)](https://arxiv.org/abs/1803.02563)
321 |     + [Locally Adaptive Learning Loss for Semantic Image Segmentation(Feb 2018)](https://arxiv.org/abs/1802.08290)
322 |     + [RTSeg: Real-time Semantic Segmentation Comparative Study( Mar 2018)](https://arxiv.org/abs/1803.02758)
323 | ### 2017
324 |   - CVPR 2017
325 |     + [Pyramid Scene Parsing Network(Dec 2016)](https://arxiv.org/abs/1612.01105)
326 |     + [Dilated Residual Networks(Jun 2016)](https://arxiv.org/abs/1705.09914)
327 |     + [Convolutional RandomWalk Networks for Semantic Image Segmentation(May 2016)](https://arxiv.org/abs/1605.07681)
328 |     + [Loss Max-Pooling for Semantic Image Segmentation(Apr 2017)](https://arxiv.org/abs/1704.02966)
329 |     + [Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes(Nov 2016)](https://arxiv.org/abs/1611.08323)
330 |     + [Gated Feedback Refinement Network for Dense Image Labeling](http://openaccess.thecvf.com/content_cvpr_2017/papers/Islam_Gated_Feedback_Refinement_CVPR_2017_paper.pdf)
331 |     + [Refinenet: Multi-path refinement networks for high-resolution semantic segmentation](http://openaccess.thecvf.com/content_cvpr_2017/papers/Lin_RefineNet_Multi-Path_Refinement_CVPR_2017_paper.pdf)
332 |     + [Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF](http://openaccess.thecvf.com/content_cvpr_2017/papers/Shen_Semantic_Segmentation_via_CVPR_2017_paper.pdf)
333 |     + [Learning Adaptive Receptive Fields for Deep Image Parsing Network](http://openaccess.thecvf.com/content_cvpr_2017/papers/Wei_Learning_Adaptive_Receptive_CVPR_2017_paper.pdf)
334 |     + [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://arxiv.org/abs/1611.09326)[Workshop]
335 | 
336 |   - ICCV 2017
337 |     + [Segmentation-Aware Convolutional Networks Using Local Attention Mask(Mar 2017)](https://arxiv.org/abs/1703.07684)  
338 |     + [Predicting Deeper into the Future of Semantic Segmentation(Mar 2017)](https://arxiv.org/abs/1703.07684)  
339 |     + [FoveaNet: Perspective-aware Urban Scene Parsing(Aug 2017))](https://arxiv.org/abs/1708.02421)  
340 |     + [Dense and Low-Rank Gaussian CRFs Using Deep Embeddings Siddhartha](http://openaccess.thecvf.com/content_ICCV_2017/papers/Chandra_Dense_and_Low-Rank_ICCV_2017_paper.pdf)
341 |     + [Scale-adaptive Convolutions for Scene Parsing](http://openaccess.thecvf.com/content_ICCV_2017/papers/Zhang_Scale-Adaptive_Convolutions_for_ICCV_2017_paper.pdf)
342 |     + [Deep Dual Learning for Semantic Image Segmentation](http://openaccess.thecvf.com/content_ICCV_2017/papers/Luo_Deep_Dual_Learning_ICCV_2017_paper.pdf)
343 |     + [Semi Supervised Semantic Segmentation Using Generative Adversarial Network](http://openaccess.thecvf.com/content_ICCV_2017/papers/Souly__Semi_Supervised_ICCV_2017_paper.pdf)
344 |   - NIPS 2017
345 |     + [Learning Affinity via Spatial Propagation Networks](https://papers.nips.cc/paper/6750-learning-affinity-via-spatial-propagation-networks.pdf)
346 |     + [Dual Path Networks](https://papers.nips.cc/paper/7033-dual-path-networks.pdf)
347 |   - Others
348 |     + [Understanding Convolution for Semantic Segmentation](http://cseweb.ucsd.edu/~gary/pubs/panqu-wacv-2018.pdf)[WACV
349 | ]
350 |     + [Semantic Segmentation with Reverse Attention(Jul 2017)](https://arxiv.org/abs/1707.06426)[BMVC]
351 |     + [Rethinking Atrous Convolution for Semantic Image Segmentation(Jun 2017)](https://arxiv.org/abs/1706.05587)
352 |     + [Pixel Deconvolutional Networks(May 2017)](https://arxiv.org/abs/1705.06820)
353 | 
354 | ### 2016
355 |   - CVPR 2016
356 |     + [Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform(Nov 2015)](https://arxiv.org/abs/1511.03328?context=cs.CV)
357 |     + [ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation(Nov 2015)](https://arxiv.org/abs/1511.07053)[Workshop][[Pytorch]](https://github.com/Wizaron/reseg-pytorch)
358 |   - ECCV 2016
359 |     + [Attention to Scale: Scale-aware Semantic Image Segmentation(Nov 2015)](https://arxiv.org/abs/1511.03339v1)
360 |     + [Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2016/papers/Lin_Efficient_Piecewise_Training_CVPR_2016_paper.pdf)  
361 |     + [Semantic Object Parsing with Graph LSTM(Mar 2016)](https://arxiv.org/abs/1603.07063)  
362 |   - ICLR 2016   
363 |     + [Multi-scale context aggregation by dilated convolutions(Nov 2015) ](https://arxiv.org/abs/1511.07122v2)[[Pytorch]](https://github.com/fyu/drn#semantic-image-segmentataion)  
364 |     + [Learning Dense Convolutional Embeddings for Semantic Segmentation(Nov 2015)](https://arxiv.org/abs/1511.04377)  
365 |   - NIPS Workshop   
366 |     + [Semantic Segmentation using Adversarial Networks(Nov 2016)](https://arxiv.org/abs/1611.08408)  
367 |   - others   
368 |     + [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation(Jun 2016)](https://arxiv.org/abs/1606.02147) 
369 |     + [High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks(Apr 2016)](https://arxiv.org/abs/1604.04339)
370 |     + [PixelNet: Towards a General Pixel-level Architecture(Sep 2016))](https://arxiv.org/abs/1609.06694)  
371 |     + [MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving(Dec 2016)](https://arxiv.org/abs/1612.07695)  
372 | ### 2015
373 |   - CVPR 2015
374 |     + [Fully Convolutional Networks for Semantic Segmentation(Nov 2014)](https://arxiv.org/abs/1411.4038)
375 |     + [Feedforward semantic segmentation with zoom-out features(Dec 2014)](https://arxiv.org/abs/1412.0774v1)
376 |     + [Learning to Propose Objects](http://openaccess.thecvf.com/content_cvpr_2015/papers/Krahenbuhl_Learning_to_Propose_2015_CVPR_paper.pdf)[[Project]](http://vladlen.info/publications/learning-to-propose-objects/)[[Pytorch]](https://github.com/philkr/lpo)
377 |     + [Hypercolumns for Object Segmentation and Fine-grained Localization](http://openaccess.thecvf.com/content_cvpr_2015/papers/Hariharan_Hypercolumns_for_Object_2015_CVPR_paper.pdf)
378 |     + [Scene Labeling with LSTM Recurrent Neural Networks](http://openaccess.thecvf.com/content_cvpr_2015/papers/Byeon_Scene_Labeling_With_2015_CVPR_paper.pdf)
379 |     + [Weakly supervised semantic segmentation for social images](http://openaccess.thecvf.com/content_cvpr_2015/papers/Zhang_Weakly_Supervised_Semantic_2015_CVPR_paper.pdf)
380 |   - ICCV 2015
381 |     + [Learning deconvolution network for semantic segmentation(May 2015)](https://arxiv.org/abs/1505.04366)
382 |     + [Semantic Image Segmentation via Deep Parsing Network(Sep 2015)](https://arxiv.org/abs/1509.02634v1)
383 |   - Other 
384 |     + [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs(Dec 2014](https://arxiv.org/abs/1412.7062)[ICLR][DeepLabv1]  
385 |     + [U-Net: Convolutional Networks for Biomedical Image Segmentation(May 2015)](https://arxiv.org/abs/1505.04597)[MICCAI]  
386 |     + [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation(Nov 2015)](https://arxiv.org/abs/1511.00561)   
387 |     + [Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation](https://papers.nips.cc/paper/5858-decoupled-deep-neural-network-for-semi-supervised-semantic-segmentation)[NIPS]
388 | ### Before 2015
389 |   - paper
390 |     + [Simultaneous Detection and Segmentation(Jul 2014)](https://arxiv.org/abs/1407.1808)[ECCV 2014]
391 |     + [Dense Segmentation-aware Descriptors](https://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Trulls_Dense_Segmentation-Aware_Descriptors_2013_CVPR_paper.pdf)[CVPR 2013]
392 |     + [Semantic Segmentation with Second-Order Pooling](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.423.3707&rep=rep1&type=pdf)[ECCV2012]
393 |     + [Nonparametric Scene Parsing via Label Transfer](http://people.csail.mit.edu/celiu/pdfs/LabelTransferTPAMI.pdf)[TPAMI2011][[Project]](http://people.csail.mit.edu/celiu/LabelTransfer/code.html)
394 | ## 2D Medical Segmentation
395 | ### 2019
396 |   - ICCV 2019
397 |     + [Eyenet: Attention based Convolutional Encoder-Decoder Network for Eye Region Segmentation](https://arxiv.org/abs/1910.03274)
398 |     + [Deep Plug-and-Play Prior for Parallel MRI Reconstruction](https://arxiv.org/abs/1909.00089)
399 |     + [CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation](https://arxiv.org/abs/1908.10555)
400 |     + [Multi-Stage Pathological Image Classification using Semantic Segmentation](https://arxiv.org/abs/1910.04473)
401 |   - NIPS 2019
402 |     + [Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands](https://arxiv.org/abs/1910.10470)[[Code]](https://arxiv.org/abs/1910.10470)
403 |   - MICCAI 2019
404 |     + [Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation](https://arxiv.org/abs/1911.10360)
405 |     + [PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation](https://arxiv.org/abs/1911.01062)[MMMI2019 Best Student Paper Award]
406 |     + [Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations](https://arxiv.org/abs/1911.01218)
407 |     + [Automatic Segmentation of Muscle Tissue and Inter-muscular Fat in Thigh and Calf MRI Images](https://arxiv.org/abs/1910.04866)
408 |     + [Integrating cross-modality hallucinated MRI with CT to aid mediastinal lung tumor segmentation](https://arxiv.org/abs/1909.04542)
409 |     + [IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation](https://arxiv.org/abs/1908.06623?context=cs)
410 |     + [Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge](https://arxiv.org/abs/1909.00735)[Challenge]
411 |     + [Hyper-Pairing Network for Multi-Phase Pancreatic Ductal Adenocarcinoma Segmentation](https://arxiv.org/abs/1909.00906)
412 |     + [U-Net Fixed-Point Quantization for Medical Image Segmentation](https://arxiv.org/abs/1908.01073)[Code](https://github.com/hossein1387/U-Net-Fixed-Point-Quantization-for-Medical-Image-Segmentation)[Workshop]
413 |     + [Automated Lesion Detection by Regressing Intensity-Based Distance with a Neural Network](https://arxiv.org/abs/1907.12452)
414 |     + [Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation](https://arxiv.org/abs/1907.13124)[[Code]](https://github.com/utkuozbulak/adaptive-segmentation-mask-attack)
415 |     + [Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation](https://arxiv.org/abs/1907.11292)
416 |     + [NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation](https://arxiv.org/abs/1907.11320)
417 |     + [Multi-task Localization and Segmentation for X-ray Guided Planning in Knee Surgery](https://arxiv.org/abs/1907.10465)
418 |     + [Mixed-Supervised Dual-Network for Medical Image Segmentation](https://arxiv.org/abs/1907.10209)
419 |     + [Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation](https://arxiv.org/abs/1907.03338)[[Code]](https://github.com/alainjungo/reliability-challenges-uncertainty)
420 |     + [INN: Inflated Neural Networks for IPMN Diagnosis(30 Jun)](https://arxiv.org/abs/1907.00437)[[Code]](https://github.com/lalonderodney/INN-Inflated-Neural-Nets)
421 |     + [Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders](https://arxiv.org/abs/1906.02343)    
422 |     + [Supervised Uncertainty Quantification for Segmentation with Multiple Annotations](https://arxiv.org/abs/1907.01949)
423 |     + [Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography](https://arxiv.org/abs/1908.05343)[Workshop]
424 |     + [U-Net Training with Instance-Layer Normalization](https://arxiv.org/abs/1908.08466)[[Workshop]]
425 |     + [Estimation of preterm birth markers with U-Net segmentation network](https://arxiv.org/abs/1908.09148)[[Workshop]]
426 |     + [A Weakly Supervised Method for Instance Segmentation of Biological Cells](https://arxiv.org/abs/1908.09891)[[Workshop]][Weakly Supervised]
427 |     + [Weakly supervised segmentation from extreme points](https://arxiv.org/abs/1910.01236)[Workshop][Weakly supervised]
428 |     + [A hybrid deep learning framework for integrated segmentation and registration: evaluation on longitudinal white matter tract changes](https://arxiv.org/abs/1908.10221)[[oral]]
429 |     + [CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning](https://arxiv.org/abs/1909.07097)[Weakly Supervised]
430 |     + [Cardiac Segmentation of LGE MRI with Noisy Labels](https://arxiv.org/abs/1910.01242)[Workshop]
431 |     + [Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting](https://arxiv.org/abs/1908.08841)
432 |     + [Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation](https://arxiv.org/abs/1906.11143)[[Pytorch]](https://github.com/EmmaW8/BEAL)[[Dataset]](https://refuge.grand-challenge.org/)
433 |     + [Dual Adaptive Pyramid Network for Cross-Stain Histopathology Image Segmentation](https://arxiv.org/abs/1909.11524)
434 |     + [Attention Guided Network for Retinal Image Segmentation](https://arxiv.org/abs/1907.12930)[[Pytorch]](https://github.com/HzFu/AGNet)
435 |     + [ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation](https://arxiv.org/abs/1907.10936)[Code](https://github.com/ZzzJzzZ/ETNet)
436 |     + [FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images](https://arxiv.org/abs/1907.12056)[SenseTime]
437 |     + [Adversarial Learning with Multiscale Features and Kernel Factorization for Retinal Blood Vessel Segmentation(5 Jul)](https://arxiv.org/abs/1907.02742)
438 |   - CVPR 2019
439 |     + [Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology(Apr 2019)](https://arxiv.org/abs/1904.06040)
440 |     + [Exploiting Computation Power of Blockchain for Biomedical Image Segmentation(Apr 2019)](https://arxiv.org/abs/1904.07349)
441 |   - AAAI 2019
442 |     + [Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks(Apr 2019)](https://arxiv.org/abs/1904.12181)
443 |   - ISBI2019
444 |     + [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation(Oct 2018)](https://arxiv.org/abs/1810.07842)[[Keras]](https://github.com/nabsabraham/focal-tversky-unet)
445 |     + [Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks(Apr 2019)](https://arxiv.org/abs/1904.09106)
446 |     + [Automatic Pulmonary Lobe Segmentation Using Deep Learning(Mar 2019)](https://arxiv.org/abs/1903.09879)
447 |     + [Deep Learning with Anatomical Priors: Imitating Enhanced Autoencoders in Latent Space for Improved Pelvic Bone Segmentation in MRI(March 2019)](https://arxiv.org/search/?query=ISBI&searchtype=all&abstracts=show&order=-announced_date_first&size=50)
448 |     + [US-net for robust and efficient nuclei instance segmentation(Jan 2019)](https://arxiv.org/abs/1902.00125)
449 |     + [Deep Convolutional Encoder-Decoders with Aggregated Multi-Resolution Skip Connections for Skin Lesion Segmentation](https://arxiv.org/abs/1901.09197)
450 |     + [Mask-RCNN and U-net Ensembled for Nuclei Segmentation(Jan 2019)](https://arxiv.org/abs/1901.10170)
451 |     + [Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation](https://arxiv.org/abs/1901.08379)
452 |     + [U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans](https://arxiv.org/abs/1901.07929)
453 |     + [SUMNet: Fully Convolutional Model for Fast Segmentation of Anatomical Structures in Ultrasound Volumes](https://arxiv.org/abs/1901.06920)
454 |     + [Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images](https://arxiv.org/abs/1901.06047)
455 |     + [Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation](https://arxiv.org/abs/1901.04949)
456 |     + [Residual Pyramid FCN for Robust Follicle Segmentation](https://arxiv.org/abs/1901.03760)
457 |     + [Classification and Detection in Mammograms with Weak Supervision via Dual Branch Deep Neural(Net Apr 2019)](https://arxiv.org/abs/1904.12319)[oral]
458 |   - EMBC 2019
459 |     + [Ultrasound segmentation using U-Net: learning from simulated data and testing on real data](https://arxiv.org/abs/1904.11031)[]
460 |     + [RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network(May 2019)](https://arxiv.org/abs/1905.08663)
461 |   - MIDL 2019
462 |     + [Distance Map Loss Penalty Term for Semantic Segmentation](https://arxiv.org/abs/1908.03679)   
463 |     + [XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation(Apr 2019))](https://arxiv.org/abs/1904.09229)[[Pytorch]](https://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor)
464 |     + [Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets](https://arxiv.org/abs/1907.03327)
465 |   - MLMI
466 |     + [Privacy-preserving Federated Brain Tumour Segmentation](https://arxiv.org/abs/1910.00962)
467 |     + [Deep Active Lesion Segmentation](https://arxiv.org/abs/1908.06933)
468 |     + [Weakly Supervised Segmentation by A Deep Geodesic Prior](https://arxiv.org/abs/1908.06498)
469 |     + [Boundary Aware Networks for Medical Image Segmentation](https://arxiv.org/abs/1908.08071)
470 |     + [Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks](https://arxiv.org/abs/1908.08746)
471 |     + [Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset](https://arxiv.org/abs/1908.10219)
472 |     + [Biomedical Image Segmentation by Retina-like Sequential Attention Mechanism Using Only A Few Training Images](https://arxiv.org/abs/1909.12612)
473 |   - SCI
474 |     + [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://arxiv.org/abs/1912.05074)[[Keras]](https://github.com/MrGiovanni/UNetPlusPlus)[IEEE Transactions on Medical Imaging]
475 |     + [CA-RefineNet:A Dual Input WSI Image Segmentation Algorithm Based on Attention](https://arxiv.org/abs/1907.06358)
476 |     + [Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net(Apr 2019))](https://arxiv.org/abs/1904.09120)[IEEE Transactions on Medical Imaging,TMI]
477 |     + [CE-Net: Context Encoder Network for 2D Medical Image Segmentation(Mar 2019)](https://arxiv.org/abs/1903.02740)[[Pytorch]](https://github.com/Guzaiwang/CE-Net)[[Pytorch2]](https://github.com/xiaoketongxue/CE-Net)[IEEE Transactions on Medical Imaging,TMI] 
478 |     + [The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning](https://arxiv.org/abs/1904.12654)[IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE]
479 |     + [Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation](https://arxiv.org/abs/1902.07519)[IEEE Transactions on Medical Imaging,TMI]
480 |     + [Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation(May 2019)](https://arxiv.org/abs/1905.08720)[IEEE Transactions on Medical Imaging,TMI]
481 |     + [NAS-Unet: Neural Architecture Search for Medical Image Segmentation(Apr 2019)](https://ieeexplore.ieee.org/iel7/6287639/8600701/08681706.pdf)[IEEE Access]
482 |     + [3-D Surface Segmentation Meets Conditional Random Fields](https://arxiv.org/abs/1906.04714)
483 |     + [Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications](https://arxiv.org/abs/1911.02521)
484 | 
485 |   - other
486 |     + [Robust Automated Thalamic Nuclei Segmentation using a Multi-planar Cascaded Convolutional Neural Network](https://arxiv.org/abs/1912.07209)
487 |     + [Divided We Stand: A Novel Residual Group Attention Mechanism for Medical Image Segmentation](https://arxiv.org/abs/1912.02079)
488 |     + [Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning](https://arxiv.org/abs/1911.10334)
489 |     + [HybridNetSeg: A Compact Hybrid Network for Retinal Vessel Segmentation](https://arxiv.org/abs/1911.09982)[[Pytorch]](https://github.com/JACKYLUO1991/HybridNetSeg)
490 |     + [Retinal Vessel Segmentation based on Fully Convolutional Networks](https://arxiv.org/abs/1911.09915)
491 |     + [Gland Segmentation in Histopathological Images by Deep Neural Network](https://arxiv.org/abs/1911.00909)
492 |     + [Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database](https://arxiv.org/abs/1911.00282)
493 |     + [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://arxiv.org/pdf/1902.04049v1.pdf)[[Keras]](https://github.com/nibtehaz/MultiResUNet)
494 |     + [Unified Multi-scale Feature Abstraction for Medical Image Segmentation](https://arxiv.org/abs/1910.11456)
495 |     + [Semantic Segmentation of Skin Lesions using a Small Data Set](https://arxiv.org/abs/1910.10534)
496 |     + [Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments](https://arxiv.org/abs/1910.11109)
497 |     + [Lung nodule segmentation via level set machine learning](https://arxiv.org/abs/1910.03191)
498 |     + [A Symmetric Equilibrium Generative Adversarial Network with Attention Refine Block for Retinal Vessel Segmentation](https://arxiv.org/abs/1909.11936)
499 |     + [Intelligent image synthesis to attack a segmentation CNN using adversarial learning](https://arxiv.org/abs/1909.11167)
500 |     + [Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning](https://arxiv.org/abs/1909.09931)
501 |     + [RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments](https://arxiv.org/abs/1909.10360)
502 |     + [Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints](https://arxiv.org/abs/1909.06645)
503 |     + [Local block-wise self attention for normal organ segmentation](https://arxiv.org/abs/1909.05054)
504 |     + [ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths](https://arxiv.org/abs/1909.04148)
505 |     + [On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Funduscopy](https://arxiv.org/abs/1909.03856)
506 |     + [Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions](https://arxiv.org/list/cs.CV/pastweek?skip=75&show=25)
507 |     + [Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI](https://arxiv.org/abs/1909.01182)
508 |     + [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://arxiv.org/abs/1908.10454)
509 |     + [Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation](https://arxiv.org/abs/1908.10489)
510 |     + [O-MedAL: Online Active Deep Learning for Medical Image Analysis](https://arxiv.org/abs/1908.10508)
511 |     + [IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation](https://arxiv.org/abs/1908.06623)
512 |     + [A unified representation network for segmentation with missing modalities](https://arxiv.org/abs/1908.06683)
513 |     + [Lung segmentation on chest x-ray images in patients with severe abnormal findings using deep learning](https://arxiv.org/abs/1908.07704)
514 |     + [Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems](https://arxiv.org/abs/1908.05480)
515 |     + [Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation](https://arxiv.org/abs/1908.05311)
516 |     + [Automatic segmentation of kidney and liver tumors in CT images](https://arxiv.org/abs/1908.01279)
517 |     + [Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network](https://arxiv.org/abs/1908.01373)
518 |     + [Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation](https://arxiv.org/abs/1908.01997)
519 |     + [Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation](https://arxiv.org/abs/1907.12282)
520 |     + [A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation](https://arxiv.org/abs/1907.12296)
521 |     + [Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation](https://arxiv.org/abs/1907.12303)
522 |     + [Lung image segmentation by generative adversarial networks](https://arxiv.org/abs/1907.13033)
523 |     + [Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation](https://arxiv.org/abs/1907.13590)
524 |     + [Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images](https://arxiv.org/abs/1907.11483)
525 |     + [Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation](https://arxiv.org/abs/1907.11587)
526 |     + [Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalization of a Musculoskeletal Model](https://arxiv.org/abs/1907.08915)
527 |     + [ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning](https://arxiv.org/abs/1907.03241)
528 |     + [DSNet: Automatic Dermoscopic Skin Lesion Segmentation](https://arxiv.org/abs/1907.04305)[[Code]](https://github.com/kamruleee51/Skin-Lesion-Segmentation-Using-Proposed-DSNet)
529 |     + [A multi-task U-net for segmentation with lazy labels(20 Jun)](https://arxiv.org/abs/1906.12177)
530 |     + [An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial LearningJul 2019)](https://arxiv.org/abs/1907.00887)
531 |     + [CaDSS: Cataract Dataset for Semantic Segmentation](https://arxiv.org/abs/1906.11586)
532 |     + [Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures](https://arxiv.org/abs/1906.09540)
533 |     + [Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography](https://arxiv.org/abs/1906.07679)
534 |     + [Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Network](https://arxiv.org/abs/1906.05251)
535 |     + [V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation](https://arxiv.org/abs/1906.02817)
536 |     + [Multi-scale guided attention for medical image segmentation](https://arxiv.org/abs/1906.02849)[[Pytorch]](https://github.com/sinAshish/Multi-Scale-Attention)
537 |     + [Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images](https://arxiv.org/abs/1906.02901)
538 |     + [A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities](https://arxiv.org/abs/1905.13077)
539 |     + [Deep Dilated Convolutional Nets for the Automatic Segmentation of Retinal Vessels](https://arxiv.org/abs/1905.12120)
540 |     + [Segmentation of blood vessels in retinal fundus images](https://arxiv.org/abs/1905.12596)
541 |     + [A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images(May 2019)](https://arxiv.org/abs/1905.10835)
542 |     + [A 2D dilated residual U-Net for multi-organ segmentation in thoracic CT(May 2019)](https://arxiv.org/abs/1905.07710)
543 |     + [Dual-branch residual network for lung nodule segmentation(May 2019)](https://arxiv.org/abs/1905.08413)
544 |     + [A novel algorithm for segmentation of leukocytes in peripheral blood(May 2019)](https://arxiv.org/abs/1905.08416)
545 |     + [Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset(May 2019)](https://arxiv.org/abs/1905.07203)
546 |     + [iRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading(May 2019)](https://arxiv.org/abs/1905.06312)
547 |     + [Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function(May 2019)](https://arxiv.org/pdf/1905.03639.pdf)
548 |     + [T-Net: Encoder-Decoder in Encoder-Decoder architecture for the main vessel segmentation in coronary angiography](https://arxiv.org/abs/1905.04197)
549 |     + [Breast Tumor Classification and Segmentation using Convolutional Neural Networks(May 2019)](https://arxiv.org/abs/1905.04247)
550 |     + [nnU-Net: Breaking the Spell on Successful Medical Image Segmentation(Apr 2019)](https://arxiv.org/abs/1904.08128)[[Code]](https://github.com/MIC-DKFZ/nnunet)
551 |     + [Feature Fusion Encoder Decoder Network For Automatic Liver Lesion Segmentation(Mar 2019)](https://arxiv.org/abs/1903.11834)  
552 |     + [MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation(Dec 2018)](https://arxiv.org/abs/1812.00352)
553 |     + [Segmentation of the Prostatic Gland and the Intraprostatic Lesions on Multiparametic MRI Using Mask-RCNN(Apr 2019)](https://arxiv.org/abs/1904.02575)
554 |     + [FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI( Apr 2019)](https://arxiv.org/abs/1904.02082)
555 |     + [FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation(https://arxiv.org/abs/1902.03091)](https://arxiv.org/abs/1902.03091)
556 |     + [Skin Cancer Segmentation and Classification with NABLA-N and Inception Recurrent Residual Convolutional Networks](https://arxiv.org/abs/1904.11126)
557 | ### 2018
558 |   - MICCAI
559 |     + [UNet++: A Nested U-Net Architecture for Medical Image Segmentation(Jul 2018)](https://arxiv.org/abs/1807.10165)[[Keras]](https://github.com/MrGiovanni/UNetPlusPlus)[[Pytorch]](https://github.com/ShawnBIT/UNet-family/blob/master/networks/UNet_Nested.py)
560 |   - IPMI 2018
561 |     + [CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation](https://arxiv.org/abs/1903.05358)
562 |   - other
563 |     + [Attention U-Net: Learning Where to Look for the Pancreas(Apr 2018)](https://arxiv.org/abs/1804.03999)[[Pytorch]](https://github.com/ozan-oktay/Attention-Gated-Networks/tree/master/models)
564 |     + [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images(Aug 2018)](https://arxiv.org/abs/1808.08114)[[Pytorch]](https://github.com/ozan-oktay/Attention-Gated-Networks/tree/master/models)
565 |     + [MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation](https://arxiv.org/pdf/1812.00352.pdf)
566 |     + [DUNet: A deformable network for retinal vessel segmentation](https://arxiv.org/pdf/1811.01206.pdf)
567 |     + [LADDERNET: Multi-Path Networks Based on U-Net for Medical Image Segmentation](https://arxiv.org/pdf/1810.07810.pdf)[[Pytorch]](https://github.com/juntang-zhuang/LadderNet)
568 |     + [A Probabilistic U-Net for Segmentation of Ambiguous Images (NIPS)](https://arxiv.org/pdf/1806.05034.pdf)[[tensorflow]](https://github.com/SimonKohl/probabilistic_unet)
569 |     + [3D RoI-aware U-Net for Accurate and Efficient Colorectal Cancer Segmentation ](https://arxiv.org/pdf/1806.10342.pdf)[[Pytorch]](https://github.com/huangyjhust/3D-RU-Net)
570 |     
571 | ### Before 2018
572 |   - 2017
573 |     + [H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes ](https://arxiv.org/pdf/1709.07330.pdf)[[Keras]](https://github.com/xmengli999/H-DenseUNet)[IEEE Transactions on Medical Imaging,TIM]
574 |   - 2016
575 |     + [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](http://campar.in.tum.de/pub/milletari2016Vnet/milletari2016Vnet.pdf)[[Pytorch]](https://github.com/mattmacy/vnet.pytorch)[[Cafee]](https://github.com/faustomilletari/VNet)
576 |     + [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://arxiv.org/pdf/1606.06650.pdf)[[Pytorch]](https://github.com/wolny/pytorch-3dunet)
577 |   - MICCAI 2015   
578 |     + [U-Net: Convolutional Networks for Biomedical Image Segmentation(May 2015)](https://arxiv.org/abs/1505.04597)[[Keras]](https://github.com/zhixuhao/unet)[[Pytorch]](https://github.com/ShawnBIT/UNet-family/blob/master/networks/UNet.py)
579 | ## 3D Medical Segmentation
580 | ### 2019
581 |   - [MICCAI 2019](https://www.miccai2019.org/) [Workshop](https://www.miccai2019.org/programme/workshops-challenges-tutorials/)
582 |     + [Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation](https://arxiv.org/abs/1911.02014)
583 |     + [TuNet: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networks](https://arxiv.org/abs/1910.05338)[MICCAI BrainLes 2019]
584 |     + [Semi-Supervised Variational Autoencoder for Survival Prediction](https://arxiv.org/abs/1910.04488)
585 |     + [Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube](https://arxiv.org/list/cs.CV/pastweek?skip=25&show=25)
586 |     + [Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data](https://arxiv.org/abs/1909.09716)[Code](https://github.com/horsepurve/StyleSegor)
587 |     + [MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation](https://arxiv.org/abs/1909.06726)
588 |     + [SegNAS3D: Network Architecture Search with Derivative-Free Global Optimization for 3D Image Segmentation](https://arxiv.org/abs/1909.05962)
589 |     + [Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation](https://arxiv.org/abs/1909.00548)
590 |     + [3D U2-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation](https://arxiv.org/abs/1909.06012)[[Pytorch]](https://github.com/huangmozhilv/u2net_torch/)[S. Kevin Zhou]
591 |     + [Generative adversarial network for segmentation of motion affected neonatal brain MRI](https://arxiv.org/abs/1906.04704)
592 |     + [Learning Shape Representation on Sparse Point Clouds for Volumetric Image Segmentation](https://arxiv.org/abs/1906.02281)[[Code]](https://github.com/fabianbalsiger/point-cloud-segmentation-miccai2019)
593 |     + [Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders](https://arxiv.org/abs/1906.02343)
594 |     + [Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images](https://arxiv.org/abs/1906.02901)
595 |     + [PseudoEdgeNet: Nuclei Segmentation only with Point Annotations](https://arxiv.org/abs/1906.02924)[weakly supervised ]
596 |     + [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://arxiv.org/abs/1906.04045)[[Code]](https://github.com/baumgach/PHiSeg-code)
597 |     + [Cardiac MRI Segmentation with Strong Anatomical Guarantees(5 Jul)](https://arxiv.org/abs/1907.02865)
598 |     + [Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation(5 Jul)](https://arxiv.org/abs/1907.02766)[Unsupervised]
599 |     + [Automated Multi-sequence Cardiac MRI Segmentation Using Supervised Domain Adaptation](https://arxiv.org/abs/1908.07726)[Stacom 2019]
600 |     + [Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation](https://arxiv.org/abs/1908.07344)[Stacom 2019]
601 |     + [Endotracheal Tube Detection and Segmentation in Chest Radiographs using Synthetic Data](https://arxiv.org/abs/1908.07170)
602 |     + [Multi-step Cascaded Networks for Brain Tumor Segmentation](https://arxiv.org/abs/1908.05887)[[Code]](https://github.com/JohnleeHIT/Brats2019)[BraTS 2019]
603 |     + [Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR](https://arxiv.org/abs/1908.08870)[[MICCAI PIPPI]]
604 |     + [Permutohedral Attention Module for Efficient Non-Local Neural Networks(Jul 2019)](https://arxiv.org/abs/1907.00641)[[Pytorch]](https://github.com/xiaoketongxue/Permutohedral_attention_module)[[Dataset]](http://spineweb.digitalimaginggroup.ca/)
605 |     + [A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation](https://arxiv.org/abs/1906.06148)[[Pytorch]](https://github.com/RobinBruegger)[[Pytorch2]](https://github.com/RobinBruegger/PartiallyReversibleUnet)
606 |     + [X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies](https://arxiv.org/abs/1907.07000)[[Keras]](https://github.com/Andrewsher/X-Net)
607 |     + [CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke](https://arxiv.org/abs/1907.07008)[Keras](https://github.com/YH0517/CLCI_Net)[[Keras]](https://github.com/YH0517/CLCI_Net)
608 |     + [3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI(Apr 2019)](https://arxiv.org/abs/1904.03355)[[Pytorch]](https://github.com/China-LiuXiaopeng/BraTS-DMFNet)[online-evaluation]    
609 |     + [Project & Excite Modules for Segmentation of Volumetric Medical Scans](https://arxiv.org/abs/1906.04649)[[Pytorch]](https://github.com/ai-med/squeeze_and_excitation) 
610 |     + [Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention](https://arxiv.org/abs/1907.04052)
611 |   - IPMI2019
612 |     + [Brain Tumor Segmentation on MRI with Missing Modalities(Apr 2019)](https://arxiv.org/abs/1904.07290)
613 |     + [Accurate Nuclear Segmentation with \\Center Vector Encoding](https://arxiv.org/abs/1907.03951)
614 |     + [Learning-based Optimization of the Under-sampling Pattern in MRI](https://arxiv.org/abs/1901.01960)[Code](https://github.com/cagladbahadir/LOUPE)
615 |     + [Random 2.5D U-net for Fully 3D Segmentation](https://arxiv.org/abs/1910.10398)[[Workshop]]
616 |   - ISBI2019
617 |     + [Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure](https://arxiv.org/abs/1903.02500)
618 |     + [Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCN](https://arxiv.org/abs/1902.05582)
619 |   - SCI
620 |     + [Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning](https://arxiv.org/abs/1909.00273)
621 |     + [3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles(Mar 2019)](https://arxiv.org/ftp/arxiv/papers/1903/1903.12152.pdf)[[Pytorch]](https://github.com/MASILab/SLANTbrainSeg)[NeuroImage]
622 |   - arxiv
623 |     + [Transfer Learning with Edge Attention for Prostate MRI Segmentation](https://arxiv.org/abs/1912.09847)
624 |     + [C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation](https://arxiv.org/abs/1912.09628)
625 |     + [Adversarial normalization for multi domain image segmentation](https://arxiv.org/pdf/1912.00993.pdf)[Adversarial ]
626 |     + [EM-NET: Centerline-Aware Mitochondria Segmentation in EM Images via Hierarchical View-Ensemble Convolutional Network](https://arxiv.org/abs/1912.00201)
627 |     + [DARTS: DenseUnet-based Automatic Rapid Tool for brain Segmentation](https://arxiv.org/abs/1911.05567)[Code](https://github.com/NYUMedML/DARTS)
628 |     + [Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates](https://arxiv.org/abs/1910.09773)[[Keras]](https://arxiv.org/abs/1910.09773)
629 |     + [Memory efficient brain tumor segmentation using an autoencoder-regularized U-Net](https://arxiv.org/abs/1910.02058)
630 |     + [Brain Tumor Segmentation and Survival Prediction](https://arxiv.org/abs/1909.09399)
631 |     + [3D Deep Affine-Invariant Shape Learning for Brain MR Image Segmentation](https://arxiv.org/abs/1909.06629)
632 |     + [3D Kidneys and Kidney Tumor Semantic Segmentation using Boundary-Aware Networks](https://arxiv.org/abs/1909.06684)
633 |     + [Automated Multiclass Cardiac Volume Segmentation and Model Generation](https://arxiv.org/abs/1909.06685)
634 |     + [MRI Brain Tumor Segmentation using Random Forests and Fully Convolutional Networks](https://arxiv.org/abs/1909.06337)
635 |     + [An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image](https://arxiv.org/abs/1909.05488)[[Keras]](https://github.com/Suiiyu/MS-CMR2019/tree/master/code)
636 |     + [Hybrid Cascaded Neural Network for Liver Lesion Segmentation](https://arxiv.org/abs/1909.04797)
637 |     + [CEREBRuM: a Convolutional Encoder-decodeR for Fully Volumetric Fast sEgmentation of BRain MRI](https://arxiv.org/abs/1909.05085)
638 |     + [High Resolution Medical Image Analysis with Spatial Partitioning](https://arxiv.org/abs/1909.03108)
639 |     + [Deep Learning for Brain Tumor Segmentation in Radiosurgery: Prospective Clinical Evaluation](https://arxiv.org/abs/1909.02799)
640 |     + [Intensity augmentation for domain transfer of whole breast segmentation in MRI](https://arxiv.org/abs/1909.02642)
641 |     + [Gland Segmentation in Histopathology Images Using Deep Networks and Handcrafted Features](https://www.baidu.com/link?url=qztifxKRTSMnCsBVaGx4FaZtQbsY5ZaVnfwgUWqQ9rFjJ80Ee8_0TeFJsfw2-FRilGZUmHMFdxw-_xXsqQpzlq&wd=&eqid=93f976b600088d2e000000035d788836)
642 |     + [Transfer Learning from Partial Annotations for Whole Brain Segmentation](https://arxiv.org/abs/1908.10851)
643 |     + [Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation](https://arxiv.org/abs/1908.10281)
644 |     + [Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-Sequence Cardiac MR Images Segmentation](https://arxiv.org/abs/1908.09298)
645 |     + [A joint 3D UNet-Graph Neural Network-based method for Airway Segmentation from chest CTs](https://arxiv.org/abs/1908.08588)
646 |     + [Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation](https://arxiv.org/abs/1908.08251)
647 |     + [Discretely-constrained deep network for weakly supervised segmentation](https://arxiv.org/abs/1908.05770)
648 |     + [Pixel-wise Segmentation of Right Ventricle of Heart](https://arxiv.org/abs/1908.08004)
649 |     + [Boosting Liver and Lesion Segmentation from CT Scans By Mask Mining](https://arxiv.org/abs/1908.05062)
650 |     + [Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN](https://arxiv.org/abs/1908.05094)
651 |     + [D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation](https://arxiv.org/abs/1908.05104)
652 |     + [Automatic acute ischemic stroke lesion segmentation using semi-supervised learning](https://arxiv.org/abs/1908.03735)
653 |     + [Automated Brain Tumour Segmentation Using Deep Fully Convolutional Residual Networks](https://arxiv.org/abs/1908.04250)
654 |     + [Generalizing Deep Whole Brain Segmentation for Pediatric and Post-Contrast MRI with Augmented Transfer Learning](https://arxiv.org/abs/1908.04702)
655 |     + [An attempt at beating the 3D U-Net](https://arxiv.org/abs/1908.02182)
656 |     + [Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation](https://arxiv.org/abs/1908.03204)
657 |     + [A Unified Point-Based Framework for 3D Segmentation](https://arxiv.org/abs/1908.00478)
658 |     + [2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy](https://arxiv.org/abs/1907.12868)
659 |     + [Convolutional neural network stacking for medical image segmentation in CT scans](https://arxiv.org/abs/1907.10132)
660 |     + [Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders](https://arxiv.org/abs/1907.08870)
661 |     + [FD-FCN: 3D Fully Dense and Fully Convolutional Network for Semantic Segmentation of Brain Anatomy](https://arxiv.org/abs/1907.09194)
662 |     + [AirwayNet: A Voxel-Connectivity Aware Approach for Accurate Airway Segmentation Using Convolutional Neural Networks](https://arxiv.org/abs/1907.06852)
663 |     + [CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation](https://arxiv.org/abs/1907.07677)
664 |     + [A fully 3D multi-path convolutional neural network with feature fusion and feature weighting for automatic lesion identification in brain MRI images](https://arxiv.org/abs/1907.07807)
665 |     + [Brain Tissues Segmentation on MR Perfusion Images Using CUSUM Filter for Boundary Pixels](https://arxiv.org/abs/1907.03865)
666 |     + [Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior(29 Jun )](https://arxiv.org/abs/1907.00281)
667 |     + [Improving the generalizability of convolutional neural network-based segmentation on CMR images](https://arxiv.org/abs/1907.01268)
668 |     + [CSSegNet: Fine-Grained Cardiac Structures Segmentation Using Dilated Pyramid Pooling in U-net](https://arxiv.org/abs/1907.01390)
669 |     + [Anatomically Consistent Segmentation of Organs at Risk in MRI with Convolutional Neural Networks](https://arxiv.org/abs/1907.02003)
670 |     + [https://arxiv.org/ftp/arxiv/papers/1906/1906.10486.pdf](https://arxiv.org/abs/1906.10486)
671 |     + [Scalable Neural Architecture Search for 3D Medical Image Segmentation](https://arxiv.org/abs/1906.05956)
672 |     + [Enforcing temporal consistency in Deep Learning segmentation of brain MR images](https://arxiv.org/abs/1906.07160)
673 |     + [4D CNN for semantic segmentation of cardiac volumetric sequences](https://arxiv.org/abs/1906.07295)
674 |     + [Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors](https://arxiv.org/abs/1906.07347)
675 |     + [A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation](https://arxiv.org/abs/1906.07367)
676 |     + [OctopusNet: A Deep Learning Segmentation Network for Multi-modal Medical Images](https://arxiv.org/abs/1906.02031)
677 |     + [AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation](https://arxiv.org/abs/1906.01862)
678 |     + [Fully Automated Pancreas Segmentation with Two-stage 3D Convolutional Neural Networks(Jun 2019)](https://arxiv.org/abs/1906.01795)[ cross-validation]
679 |     + [Generative Model-Based Ischemic Stroke Lesion Segmentation(Jun 2019)](https://arxiv.org/abs/1906.02392)
680 |     + [Automated Segmentation for Hyperdense Middle Cerebral Artery Sign of Acute Ischemic Stroke on Non-Contrast CT Images(May 2019)](https://arxiv.org/abs/1905.09049)
681 |     + [3D Dense Separated Convolution Module for Volumetric Image Analysis(May 2019)](https://arxiv.org/abs/1905.08608)[[cross validation]]
682 |     + [RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud（May 2019)](https://arxiv.org/abs/1905.08748) 
683 |     + [Thickened 2D Networks for 3D Medical Image Segmentation(Apr 2019)](https://arxiv.org/abs/1904.01150)
684 |     + [Spherical U-Net on Cortical Surfaces: Methods and Applications(Apr 2019)](https://arxiv.org/abs/1904.00906)[cross-validation] 
685 |     + [Fully Automatic Segmentation of 3D Brain Ultrasound: Learning from Coarse Annotations(Apr 2019)](https://arxiv.org/abs/1904.08655)[cross-validation]  
686 | ### 2018
687 |   - MICCAI 2018
688 |     + [Multi-Task Learning for Left Atrial Segmentation on GE-MRI(Oct 2018)](https://arxiv.org/abs/1810.13205)[[Pytorch]](https://github.com/cherise215/atria_segmentation_2018/)  
689 | ### Before 2018
690 |   - MICCAI
691 |     + [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation(Jun 2016)](https://arxiv.org/abs/1606.06650)   
692 | ### Brain Tissue Segmentation
693 |   - Paper
694 |     + [DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images](https://arxiv.org/abs/1907.02110)
695 |     + [Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization](https://arxiv.org/abs/1906.10400)
696 |     + [3D Patchwise U-Net with Transition Layers for MR Brain Segmentation(Rank 1)](https://www.springerprofessional.de/en/3d-patchwise-u-net-with-transition-layers-for-mr-brain-segmentat/16457542)[[TensorFlow]](https://github.com/xiaoketongxue/mrbrains18-1)  
697 |     + [MixNet: Multi-modality Mix Network for Brain Segmentation(Rank3)](https://link.springer.com/chapter/10.1007%2F978-3-030-11723-8_37)[[tensorflow]](https://github.com/xiaoketongxue/MRBrainS-Brain-Segmentation)
698 |     + [Robust 3D Convolutional Neural Network with Boundary Correction for Accurate Brain Tissue Segmentation(Rank3)](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8543143)[[Keras]]()
699 |     + [Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net(Rank9)](https://arxiv.org/abs/1811.04312)
700 |     + [On direct distribution matching for adapting segmentation networks(Apr 2019)](https://arxiv.org/abs/1904.02657)[[Code]](https://github.com/anonymauthor/DDMSegNet)
701 | ### MS lesion segmentation
702 |   - Paper
703 |     + [Soft labeling by Distilling Anatomical knowledge for Improved MS Lesion Segmentation(Jan 2019)](https://arxiv.org/abs/1901.09263)[ISBI2019]
704 |     + [Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NET(Jan 2019)](https://arxiv.org/abs/1901.05733)
705 |     + [Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions(Dec 2018)](https://arxiv.org/abs/1901.00055)
706 |     + [A Self-Adaptive Network For Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Protocols(Nov 2018)](https://arxiv.org/abs/1811.07491)
707 |     + [Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation(Nov 2018)](https://arxiv.org/abs/1811.02942)[NeuroImage]
708 |     + [Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation((Aug 2018)](https://arxiv.org/abs/1811.07491)[MICCAI 2018]
709 | 
710 | ## Instance Segmentation
711 | ### 2019
712 |   - ICCV 2019
713 |     + [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://arxiv.org/abs/1908.07801)
714 |   - CVPR 2019   
715 |     + [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://arxiv.org/abs/1908.03195)
716 |     + [Hybrid Task Cascade for Instance Segmentation(Jan 2019)](https://arxiv.org/abs/1901.07518)[[Pytorch]](https://github.com/open-mmlab/mmdetection)
717 |     + [Pose2Seg: Detection Free Human Instance Segmentation(Mar 2018)](https://arxiv.org/abs/1803.10683)[[Code]](https://github.com/liruilong940607/OCHumanApi)  
718 |     + [Budget-aware Semi-Supervised Semantic and Instance Segmentation](https://arxiv.org/abs/1905.05880)[[Workshop]]
719 |   - other
720 |     + [A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation](https://arxiv.org/abs/1906.11713)
721 |     + [Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth](https://arxiv.org/abs/1906.11109)[[Code]](https://github.com/davyneven/SpatialEmbeddings)
722 |     + [DARNet: Deep Active Ray Network for Building Segmentation](https://arxiv.org/abs/1905.05889)
723 |     + [YOLACT: Real-time Instance Segmentation(Apr 2019)](https://arxiv.org/abs/1904.02689)
724 |     + [Concatenated Feature Pyramid Network for Instance Segmentation(Mar 2019)](https://arxiv.org/abs/1904.00768)
725 |     + [Single Pixel Reconstruction for One-stage Instance Segmentation(Apr 2019 ](https://arxiv.org/abs/1904.07426)
726 |     + [Learning Instance Occlusion for Panoptic Segmentation](https://arxiv.org/abs/1906.05896)
727 | ## Panoptic Segmentation
728 | ### 2019
729 |   - CVPR2019
730 |     + [Attention-guided Unified Network for Panoptic Segmentation](https://arxiv.org/abs/1812.03904)
731 |     + [UPSNet: A Unified Panoptic Segmentation Network(Apr 2019)](https://arxiv.org/abs/1901.03784)[[Pytorch]](https://github.com/uber-research/UPSNet)  
732 |     + [Panoptic Feature Pyramid Networks(Jan 2019](https://arxiv.org/search/?query=Panoptic+Segmentation&searchtype=all)[Kaiming He]
733 |     + [Interactive Full Image Segmentation by Considering All Regions Jointly](https://arxiv.org/abs/1812.01888)
734 |     + [Panoptic Segmentation](https://arxiv.org/abs/1801.00868)
735 |   - other
736 |     + [Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation](https://arxiv.org/list/cs.CV/recent)
737 |     + [Panoptic-DeepLab](https://arxiv.org/abs/1910.04751)
738 |     + [Fast Panoptic Segmentation Network](https://arxiv.org/abs/1910.03892
739 |     + [Generator evaluator-selector net: a modular approach for panoptic segmentation](https://arxiv.org/abs/1908.09108)
740 |     + [Straight to Shapes++: Real-time Instance Segmentation Made More Accurate(May 2019)](https://arxiv.org/abs/1905.11358)
741 |     + [DeeperLab: Single-Shot Image Parser(Feb 2019)](https://arxiv.org/abs/1902.05093)[[Code]]
742 |     + [An End-to-End Network for Panoptic Segmentation(Mar 2019](https://arxiv.org/abs/1903.05027)
743 |     + [Single Network Panoptic Segmentation for Street Scene Understanding](https://arxiv.org/abs/1902.02678)
744 |     + [Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network(Feb 2019)](https://arxiv.org/abs/1809.02110)
745 |     + [Detecting Reflections by Combining Semantic and Instance Segmentation(Apr 2019)](https://arxiv.org/abs/1904.13273)
746 |     + [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things(March 2019)](https://arxiv.org/search/?query=Panoptic+Segmentation&searchtype=all)
747 |     + [Class-independent sequential full image segmentation, using a convolutional net that finds a segment within an attention region, given a pointer pixel within this segment(February 2019](https://arxiv.org/search/?query=Panoptic+Segmentation&searchtype=all)
748 |  ### 2018
749 |   - ECCV2018
750 |     + [Weakly- and Semi-Supervised Panoptic Segmentation(Aug 2018)](https://arxiv.org/abs/1808.03575)
751 |   other 
752 |     + [Learning to Fuse Things and Stuff(Dec 2018)](https://arxiv.org/abs/1812.01192)
753 |  ## Video-Segmentation
754 |  ### 2019
755 |   - NIPS 
756 |     + [MetaPix: Few-Shot Video Retargeting](https://arxiv.org/abs/1910.04742)[[Code]](https://imjal.github.io/MetaPix/)[Workshop]
757 |     + [LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition](https://arxiv.org/abs/1912.01601)
758 |   - ICCV 2019
759 |     + [Anchor Diffusion for Unsupervised Video Object Segmentation](https://arxiv.org/abs/1910.10895)  
760 |     + [CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing](https://arxiv.org/abs/1910.00132)[[Code]](https://github.com/KevinDuarte/CapsuleVOS)
761 |     + [DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation](https://arxiv.org/abs/1909.12471)[Pytorch](https://github.com/ZENGXH/DMM_Net)
762 |     + [RANet: Ranking Attention Network for Fast Video Object Segmentation](https://arxiv.org/abs/1908.06647)[[Cpde]](https://github.com/Storife/RANet)
763 |     + [Exploiting Temporality for Semi-Supervised Video Segmentation](https://arxiv.org/abs/1908.11309)
764 |   - CVPR 2019
765 |     + [Spatiotemporal CNN for Video Object Segmentation(Apr 2019)](https://arxiv.org/abs/1904.02363)[[Code]](https://github.com/longyin880815/STCNN)
766 |     + [MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation](http://openaccess.thecvf.com/content_CVPR_2019/papers/Xu_MHP-VOS_Multiple_Hypotheses_Propagation_for_Video_Object_Segmentation_CVPR_2019_paper.pdf)[[Code]](https://github.com/shuangjiexu/MHP-VOS)
767 |   - other
768 |     + [RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation](https://arxiv.org/abs/1909.13247)
769 |     + [Towards Good Practices for Video Object Segmentation](https://arxiv.org/abs/1909.13583)
770 |     + [Towards Good Practices for Video Object Segmentation](https://arxiv.org/abs/1909.13583)
771 |     + [Fast Video Object Segmentation via Mask Transfer Network](https://arxiv.org/abs/1908.10717)
772 |     + [Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation(Jul 2019)](https://arxiv.org/abs/1907.01203)
773 |     + [Video Instance Segmentation](https://arxiv.org/abs/1905.04804)
774 |     + [MAIN: Multi-Attention Instance Network for Video Segmentation](https://arxiv.org/abs/1904.05847)
775 |   # Re-Identification
776 |   ## 2019
777 |    - ICCV  
778 |      + [ABD-Net: Attentive but Diverse Person Re-Identification](https://arxiv.org/abs/1908.01114)[Code](https://github.com/TAMU-VITA/ABD-Net)   
779 |      + [Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Discriminative_Feature_Learning_With_Consistent_Attention_Regularization_for_Person_Re-Identification_ICCV_2019_paper.pdf)
780 |      + [self-Critical Attention Learning for Person Re-Identification](http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Self-Critical_Attention_Learning_for_Person_Re-Identification_ICCV_2019_paper.pdf)  
781 |      + [Attention Bridging Network for Knowledge Transfer](http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Attention_Bridging_Network_for_Knowledge_Transfer_ICCV_2019_paper.pdf)   
782 |      + [Attentional Feature-Pair Relation Networks for Accurate Face Recognition](https://arxiv.org/abs/1908.06255)   
783 |      + [Towards Interpretable Face Recognition](https://arxiv.org/abs/1805.00611)      
784 |      + [Mixed High-Order Attention Network for Person Re-Identification](https://arxiv.org/abs/1908.05819)[[Code]](http://www.bhchen.cn/)     
785 |      + [Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification](https://arxiv.org/abs/1811.10144)[Code](https://github.com/OasisYang/SSG)[Oral]    
786 |    - Awesome   
787 |     + [Awesome Person Re-identification (Person ReID)](https://github.com/bismex/Awesome-person-re-identification)  
788 |   ## 2018
789 |    + [A2-Nets: Double Attention Networks](https://www.baidu.com/link?url=-dsREYMGs4zZNPIm9M3qq2rdRUcAam6_uPqqBDUqCymQ4TNPpp-D7qWCxZpeyt-bO1-UfVG4njpqXoMA__lQVa&wd=&eqid=bd04129c0000989c000000025df8c83b)[NIPS]     
790 |    + [CBAM: Convolutional Block Attention Module](https://arxiv.org/abs/1807.06521)[ECCV]    
791 |   ## 2017
792 |    + [SVDNet for Pedestrian Retrieval](https://arxiv.org/abs/1703.05693)   
793 |      
794 |      
795 | 


--------------------------------------------------------------------------------
/Data-Competition.md:
--------------------------------------------------------------------------------
  1 | # Data-Competition
  2 | - [x] [结构化数据/时间序列](#结构化数据/时间序列)
  3 | - [x] [NLP](#NLP)
  4 | - [x] [CV](#CV)
  5 | - [x] [其它资源列表](#其它资源列表)
  6 | - [x] [大佬的 Git](#大佬的-Git)
  7 | 
  8 | ## 结构化数据/时间序列
  9 | 
 10 | 1.  2019 腾讯广告算法大赛
 11 | 
 12 |     Rank1: https://github.com/guoday/Tencent2019_Preliminary_Rank1st
 13 | 
 14 | 1.  2019 CCF 乘用车细分市场销量预测
 15 | 
 16 |     EDA: http://lambda-xmu.club/2018/08/27/2019CCF-Car-Sales-EDA/
 17 |     
 18 |     Baseline 0.488: https://zhuanlan.zhihu.com/p/79940352
 19 |     
 20 |     Baseline 0.511: https://blog.csdn.net/weixin_43593330/article/details/100175414
 21 |     
 22 | 1.  2019 CCF 离散制造过程中典型工件的质量符合率预测
 23 | 
 24 |     EDA1: http://lambda-xmu.club/2018/08/25/2019CCF-Work-Piece-EDA/
 25 |     
 26 |     EDA2: http://lambda-xmu.club/2018/09/04/2019CCF-Work-Piece-EDA-Part2/
 27 | 
 28 |     Baseline 0.678: https://github.com/destiny19960207/CCF_BDCI2019_discrete-manufacturing
 29 |     
 30 |     Baseline 0.644: [CCF2019-discrete-manufacturing/644baseline.py](src/CCF2019-discrete-manufacturing/644baseline.py)
 31 | 
 32 | 1.  2018 科大讯飞 AI 营销算法大赛
 33 | 
 34 |     Rank1: https://zhuanlan.zhihu.com/p/47807544
 35 |     
 36 |     Rank2: https://github.com/infturing/kdxf
 37 |     
 38 |     Rank21: https://github.com/Michaelhuazhang/-AI21-
 39 | 
 40 | 2.  2018 IJCAI 阿里妈妈搜索广告转化预测
 41 | 
 42 |     Rank1: https://github.com/plantsgo/ijcai-2018 
 43 | 
 44 |     Rank2: 
 45 |     
 46 |     +   https://github.com/YouChouNoBB/ijcai-18-top2-single-mole-solution 
 47 | 
 48 |     +   https://blog.csdn.net/Bryan__/article/details/80600189 
 49 | 
 50 |     Rank3: https://github.com/luoda888/2018-IJCAI-top3 
 51 | 
 52 |     Rank8: https://github.com/fanfanda/ijcai_2018 
 53 | 
 54 |     Rank8: https://github.com/Gene20/IJCAI-18 
 55 | 
 56 |     Rank9（第一赛季）https://github.com/yuxiaowww/IJCAI-18-TIANCHI 
 57 | 
 58 |     Rank29: https://github.com/bettenW/IJCAI18_Tianchi_Rank29 
 59 | 
 60 |     Rank41: https://github.com/cmlaughing/IJCAI-18 
 61 | 
 62 |     Rank48: https://github.com/YunaQiu/IJCAI-18alimama 
 63 | 
 64 |     Rank53: https://github.com/altmanWang/IJCAI-18-CVR 
 65 | 
 66 |     Rank60: https://github.com/Chenyaorui/ijcai_2018 
 67 | 
 68 |     Rank81: https://github.com/wzp123456/IJCAI_18 
 69 | 
 70 |     Rank94: https://github.com/Yangtze121/-IJCAI-18- 
 71 | 
 72 | 3.  2018 腾讯广告算法大赛
 73 | 
 74 |     Rank3: https://github.com/DiligentPanda/Tencent_Ads_Algo_2018 
 75 | 
 76 |     rank6: https://github.com/nzc/tencent-contest 
 77 | 
 78 |     Rank7: https://github.com/guoday/Tencent2018_Lookalike_Rank7th 
 79 | 
 80 |     Rank9: https://github.com/ouwenjie03/tencent-ad-game 
 81 | 
 82 |     Rank10: https://github.com/keyunluo/Tencent2018_Lookalike_Rank10th 
 83 | 
 84 |     rank10（初赛）: https://github.com/ShawnyXiao/2018-Tencent-Lookalike 
 85 | 
 86 |     Rank11: 
 87 |     
 88 |     +   https://github.com/liupengsay/2018-Tencent-social-advertising-algorithm-contest 
 89 | 
 90 |     +   https://my.oschina.net/xtzggbmkk/blog/1865680 
 91 | 
 92 |     Rank26: https://github.com/zsyandjyhouse/TencentAD_contest 
 93 | 
 94 |     Rank33: https://github.com/John-Yao/Tencent_Social_Ads2018 
 95 | 
 96 |     Rank69: https://github.com/BladeCoda/Tencent2018_Final_Phrase_Presto 
 97 |     
 98 | 3.  2017 腾讯广告算法大赛
 99 | 
100 |     Rank14: https://github.com/freelzy/Tencent_Social_Ads
101 |     
102 |     Rank20: https://github.com/shenweichen/Tencent_Social_Ads2017_Mobile_App_pCVR
103 | 
104 | 4.  2018 高校大数据挑战赛-快手活跃用户预测
105 | 
106 |     Rank1: 
107 |     
108 |     +   https://github.com/drop-out/RNN-Active-User-Forecast
109 |     
110 |     +   https://zhuanlan.zhihu.com/p/42622063
111 |     
112 |     Rank4: https://github.com/chantcalf/2018-Rank4-
113 |     
114 |     Rank13 (初赛 a 榜 rank2 b 榜 rank5):
115 |     
116 |     +   https://github.com/luoda888/2018-KUAISHOU-TSINGHUA-Top13-Solutions
117 |     
118 |     +   https://github.com/totoruo/KuaiShou2018-RANK13-RNN
119 |     
120 |     Rank15: https://github.com/sunwantong/Kuaishou-Active-User
121 |     
122 |     Rank20: https://github.com/bigzhao/Kuaishou_2018_rank20th
123 |     
124 |     Rank28 (初赛 a 榜 rank1 b 榜 rank2): 
125 |     
126 |     +   https://github.com/YangKing0834131/2018-KUAISHOU-TSINGHUA-Top28-Solutions-
127 |     
128 |     +   https://github.com/FNo0/2018-KUAISHOU-Top28
129 |     
130 |     Rank35: https://github.com/chizhu/kuaishou2018
131 |     
132 | 4.  2018JDATA 用户购买时间预测
133 | 
134 |     Rank9: https://zhuanlan.zhihu.com/p/45141799 
135 |     
136 | 5.  2018 DF 风机叶片开裂预警
137 | 
138 |     Rank2: https://github.com/SY575/DF-Early-warning-of-the-wind-power-system 
139 |     
140 | 6.  2018 DF 光伏发电量预测
141 | 
142 |     Rank1: 
143 |     
144 |     +   https://zhuanlan.zhihu.com/p/44755488?utm_source=qq&utm_medium=social&utm_oi=623925402599559168 
145 | 
146 |     +   https://mp.weixin.qq.com/s/Yix0xVp2SiqaAcuS6Q049g 
147 |            
148 | 7.  AI 全球挑战者大赛-违约用户风险预测
149 | 
150 |     Rank1: https://github.com/chenkkkk/User-loan-risk-prediction 
151 |     
152 | 8.  2016 融 360-用户贷款风险预测
153 | 
154 |     Rank7: https://github.com/hczheng/Rong360 
155 |     
156 | 8.  2018 CCF-面向电信行业存量用户的智能套餐个性化匹配模型
157 | 
158 |     Rank1: https://github.com/PPshrimpGo/BDCI2018-ChinauUicom-1st-solution
159 | 
160 |     
161 |     Rank2: https://github.com/PandasCute/2018-CCF-BDCI-China-Unicom-Research-Institute-top2
162 | 
163 |     
164 |     Rank4: https://github.com/jinchenyu/2018_CCF_BDCI_ChinaUicom_rank4_solution
165 | 
166 |     
167 |     Rank6: https://github.com/ZengHaihong/2018_CCF_BDCI_ChinaUnicom_Package_Match_Rank6
168 | 
169 | 8.  2018 CCF-汽车行业用户观点主题及情感识别 ASC 挑战赛
170 | 
171 |     Rank1: https://github.com/yilirin/BDCI_Car_2018
172 |     
173 |     Rank7: https://github.com/nlpjoe/CCF-BDCI-Automotive-Field-ASC-2018
174 |     
175 | 8.  2017 CCF-商场中精确定位用户所在店铺
176 | 
177 |     Rank1: https://github.com/drop-out/Tianchi-Wifi-Positioning
178 |     
179 | 9.  2016 CCF-020 优惠券使用预测
180 | 
181 |     Rank1: https://github.com/wepe/O2O-Coupon-Usage-Forecast 
182 |     
183 | 0.  2016 ccf-农产品价格预测
184 | 
185 |     Rank2: https://github.com/xing89qs/CCF_Product 
186 | 
187 |     Rank35: https://github.com/wqlin/ccf-price-prediction 
188 |  
189 | 1.  2016 ccf-客户用电异常
190 | 
191 |     Rank4: https://github.com/AbnerYang/2016CCF-StateGrid 
192 |     
193 | 2.  2016 ccf-搜狗的用户画像比赛
194 | 
195 |     Rank1: https://github.com/hengchao0248/ccf2016_sougou 
196 | 
197 |     Rank3: https://github.com/AbnerYang/2016CCF-SouGou 
198 | 
199 |     Rank5: 
200 |     
201 |     +   https://github.com/dhdsjy/2016_CCFsougou 
202 | 
203 |     +   https://github.com/dhdsjy/2016_CCFsougou2 
204 | 
205 |     +   https://github.com/prozhuchen/2016CCF-sougou 
206 | 
207 |     +   https://github.com/coderSkyChen/2016CCF_BDCI_Sougou 
208 |            
209 | 3.  2016 ccf-联通的用户轨迹
210 | 
211 |     RankX: https://github.com/xuguanggen/2016CCF-unicom 
212 |     
213 | 4.  2016 ccf-Human or Robots
214 | 
215 |     Rank6: https://github.com/pickou/ccf_human_or_robot 
216 |     
217 | 5.  菜鸟-需求预测与分仓规划
218 | 
219 |     Rank6:  https://github.com/wepe/CaiNiao-DemandForecast-StoragePlaning 
220 | 
221 |     Rank10: https://github.com/xing89qs/TianChi_CaiNiao_Season2 
222 |     
223 | 6.  Kaggle 2018 Data Science Bow
224 | 
225 |     Rank1: https://www.kaggle.com/c/data-science-bowl-2018/discussion/54741
226 | 
227 |     Rank4: 
228 |     
229 |     +   https://www.kaggle.com/c/data-science-bowl-2018/discussion/55118
230 |     
231 |     +   https://github.com/pdima/kaggle_2018_data_science_bowl_solution
232 |     
233 | 7.  2018 对抗挑战优胜经验分享
234 | 
235 |     +   http://t.cn/RBMaq4y
236 |     
237 |     +   http://t.cn/RBMlfBH
238 |     
239 | 8.  Galaxy Zoo challenge
240 | 
241 |     http://benanne.github.io/2014/04/05/galaxy-zoo.html
242 |     
243 | 9.  Kaggle Home Credit 违约风险预测
244 | 
245 |     Rank1: http://t.cn/RFsoHgv
246 |     
247 | 0.  Kaggle 2017 Santa competition
248 | 
249 |     Rank54: https://github.com/bigzhao/MPI-Hungarian-method
250 |     
251 | 1.  Kaggle 2017 Porto Seguro’s Safe Driver Prediction
252 | 
253 |     Rank131: https://bigzhao.github.io/2017/12/18/kaggle-silver/
254 |     
255 | 1.  第三届阿里云安全算法挑战赛
256 | 
257 |     Rank1: https://github.com/poteman/Alibaba-3rd-Security-Algorithm-Challenge
258 |     
259 | 1.  2018dc-新网银行杯
260 | 
261 |     Rank3: https://github.com/Smilexuhc/Xingwangbankcup-top3
262 | 
263 |     
264 |     Rank4: https://github.com/TingNie/CreditForecast
265 |     
266 | 1.  2018 AI Challenger 全球 AI 挑战赛 - 细粒度用户评论情感分析
267 | 
268 |     Rank1: https://github.com/chenghuige/wenzheng
269 |     
270 |     Rank16: https://github.com/xueyouluo/fsauor2018
271 |     
272 |     Rank17: https://github.com/BigHeartC/Al_challenger_2018_sentiment_analysis
273 |     
274 | 1.  第二届 “智慧中国杯” 数据科学大赛，首发皇包车（HI GUIDES）精品旅行服务成单预测竞赛
275 | 
276 |     Rank4: https://github.com/SunnyMarkLiu/Datacastle_Travel_Services_Predict
277 | 
278 |     Rank?: https://github.com/zlxy9892/DC_hbc
279 |     
280 | 1.  2018 ATEC 蚂蚁金服 NLP 智能客服比赛
281 | 
282 |     Rank16: https://github.com/zle1992/atec
283 |     
284 | 1.  2018 ATEC 蚂蚁金服 NLP 蚂蚁金服金融大脑赛题
285 | 
286 |     Rank18: https://github.com/ziweipolaris/atec2018-nlp
287 |     
288 | 1.  DataCastle-城市治理大数据应用创意方案赛
289 | 
290 |     Rank1: https://github.com/poteman/DataCastle-Urban-governance-competition
291 |     
292 | 1.  Kaggle - Crowdflower Search Results Relevance
293 | 
294 |     Rank1: https://github.com/ChenglongChen/Kaggle_CrowdFlower
295 |     
296 | 1.  第三届融 360 天机智能金融算法挑战赛 - 特征挖掘
297 | 
298 |     Rank1: https://github.com/xSupervisedLearning/Rong360_feature_mining_1st_solution
299 |     
300 | 1.  2017 摩拜杯算法挑战赛
301 | 
302 |     Rank3: https://github.com/Magic-Bubble/Mobike
303 |     
304 | 1.  DataFountain - 招商银行信用卡中心 消费金融场景下的用户购买预测
305 | 
306 |     Rank1: https://github.com/sunwantong/China-Merchants-Bank-credit-card-Cente-User-purchase-forecast
307 | 
308 | 1.  天池糖尿病血糖预测比赛 精准医疗
309 | 
310 |     Rank24: https://github.com/xingyuezhiji/Diabetes
311 |     
312 | 1.  第一届西安交通大学人工智能实践大赛（2018AI 实践大赛--图片文字识别）
313 | 
314 |     Rank1: https://github.com/yinchangchang/ocr_densenet
315 |     
316 | 1.  2019 KaggleDays Paris offline competition（Kaggle 产品销售额预测比赛优胜方案）
317 | 
318 |     Rank1: https://github.com/mxbi/kaggledays-paris
319 |     
320 | 1.  2019 Kaggle Freesound Audio Tagging
321 | 
322 |     Rank1: https://github.com/qrfaction/1st-Freesound-Audio-Tagging-2019
323 |     
324 | 1.  Kaggle iMaterialist (Fashion) 2019 at FGVC6
325 | 
326 |     Rank1: https://github.com/amirassov/kaggle-imaterialist
327 |     
328 | ## NLP
329 | 
330 | 1.  2019 CCF 互联网新闻情感分析
331 | 
332 |     Baseline 0.801: https://github.com/finlay-liu/kaggle_public
333 |     
334 |     Baseline 0.803: https://github.com/guoday/CCF-BDCI-Sentiment-Analysis-Baseline
335 | 
336 | 1.  2019 CCF 互联网金融新实体发现
337 | 
338 |     Baseline 0.2049: https://github.com/finlay-liu/kaggle_public/
339 | 
340 | 1.  2018 DC 达观-文本智能处理挑战 
341 | 
342 |     Rank1: https://github.com/ShawnyXiao/2018-DC-DataGrand-TextIntelProcess
343 | 
344 |     Rank2: https://github.com/CortexFoundation/-
345 | 
346 |     Rank4: https://github.com/hecongqing/2018-daguan-competition
347 | 
348 |     Rank8: https://github.com/Rowchen/Text-classifier
349 | 
350 |     Rank10: https://github.com/moneyDboat/data_grand 
351 |     
352 |     Rank11: https://github.com/TianyuZhuuu/DaGuan_TextClassification_Rank11
353 | 
354 |     Rank18: https://github.com/nlpjoe/daguan-classify-2018
355 | 
356 |     RankX: https://github.com/yanqiangmiffy/daguan
357 |     
358 | 1.  智能客服问题相似度算法设计——第三届魔镜杯大赛
359 | 
360 |     rank6 https://github.com/qrfaction/paipaidai
361 |     
362 |     rank12 
363 |     
364 |     +   https://www.jianshu.com/p/827dd447daf9
365 |            
366 |     +   https://github.com/LittletreeZou/Question-Pairs-Matching
367 |     
368 |     Rank16: https://github.com/guoday/PaiPaiDai2018_rank16
369 | 
370 |     Rank29: https://github.com/wangjiaxin24/daguan_NLP
371 | 
372 | 1.  2018JD Dialog Challenge 任务导向型对话系统挑战赛
373 | 
374 |     Rank2: https://github.com/Dikea/Dialog-System-with-Task-Retrieval-and-Seq2seq
375 | 
376 |     Rank3: https://github.com/zengbin93/jddc_solution_4th
377 | 
378 | 1.  2018CIKM AnalytiCup – 阿里小蜜机器人跨语言短文本匹配算法竞赛
379 | 
380 |     Rank2: https://github.com/zake7749/Closer
381 | 
382 |     Rank12: https://github.com/Leputa/CIKM-AnalytiCup-2018
383 | 
384 |     Rank18: https://github.com/VincentChen525/Tianchi/tree/master/CIKM%20AnalytiCup%202018
385 | 
386 | 1.  路透社新闻数据集“深度”探索性分析(词向量/情感分析)
387 | 
388 |     https://www.kaggle.com/hoonkeng/deep-eda-word-embeddings-sentiment-analysis/notebook
389 | 
390 | 1.  “神策杯”2018 高校算法大师赛(关键词提取)
391 | 
392 |     Rank1: http://www.dcjingsai.com/common/bbs/topicDetails.html?tid=2382
393 | 
394 |     Rank2: https://github.com/bigzhao/Keyword_Extraction
395 | 
396 |     Rank5: https://github.com/Dikea/ShenceCup.extract_keywords
397 | 
398 | 1.  知乎看山杯
399 | 
400 |     Rank1: https://github.com/chenyuntc/PyTorchText
401 | 
402 |     Rank2: https://github.com/Magic-Bubble/Zhihu
403 | 
404 |     Rank6: https://github.com/yongyehuang/zhihu-text-classification 
405 |     
406 |     Rank9: https://github.com/coderSkyChen/zhihu_kanshan_cup_2017
407 | 
408 |     Rank21: https://github.com/zhaoyu87/zhihu
409 | 
410 | 1.  2018 CCL 客服领域用户意图分类评测
411 | 
412 |     Rank1: https://github.com/nlpjoe/2018-CCL-UIIMCS
413 |     
414 | 1.  第二届搜狐内容识别大赛
415 | 
416 |     Rank1: https://github.com/zhanzecheng/SOHU_competition
417 |     
418 | 1.  科赛 - 百度 PaddlePaddle AI 大赛——智能问答
419 |     
420 |     Rank3: https://github.com/312shan/rc_tf
421 |     
422 | 1.  2018 kaggle quora insincere questions classification 
423 | 
424 |     Rank1: https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/80568 
425 |     
426 |     Rank13: https://mp.weixin.qq.com/s/DD-BOtPbGCXvxfFxL-qOgg 
427 |     
428 |     Rank153: https://github.com/jetou/kaggle-qiqc
429 | 
430 | ## CV
431 | 
432 | 
433 | 1.  2019 CCF 视频版权检测
434 | 
435 |     Baseline 0.0001: https://github.com/finlay-liu/kaggle_public
436 | 
437 | 1.  Kaggle-TGS
438 | 
439 |     Rank1: http://t.cn/EzkDlOC   
440 |     
441 |     Rank4: 
442 |     
443 |     +   http://t.cn/EzuvemA
444 | 
445 |     +   http://t.cn/EzuPvfp
446 |     
447 |     Rank9: http://t.cn/EznzvYv  
448 |     
449 |     Rank11: https://github.com/iasawseen/Kaggle-TGS-salt-solution
450 |     
451 |     Rank14: https://github.com/lRomul/argus-tgs-salt
452 |     
453 |     Rank15: https://github.com/adam9500370/Kaggle-TGS
454 |     
455 |     Rank22: http://t.cn/EzYkR6i  
456 |     
457 |     Rank56: https://github.com/Gary-Deeplearning/TGS-Salt
458 | 
459 | 2.  Kaggle Google 地标检索 
460 | 
461 |     Rank1: http://t.cn/R1i7Xiy  
462 |     
463 |     Rank14:  http://t.cn/R1nQriY
464 | 
465 | 3.  Lyft 感知挑战赛   
466 | 
467 |     赛题:  http://t.cn/RBtrJcE  
468 |     
469 |     Rank4:
470 |         
471 |     +   http://t.cn/RBtrMdw  
472 |     
473 |     +   http://t.cn/RBJnlug
474 | 
475 | 4.  Kaggle CVPR 2018 WAD 视频分割  
476 | 
477 |     Rank2: http://t.cn/Ehp4Ggm
478 | 
479 | 5.  Kaggle Google AI Open Images  
480 | 
481 |     Rank15: http://t.cn/RF1jnis
482 | 
483 | 6.  Quick, Draw! Kaggle Competition Starter Pack    
484 |    
485 |     http://t.cn/EZAoZDM
486 | 
487 | 7.  Kaggle 植物幼苗图像分类挑战赛   
488 | 
489 |     Rank1: http://t.cn/RBssjf6
490 | 
491 | 8.  Kaggle Airbus Ship Detection Challenge (Kaggle 卫星图像船舶检测比赛)   
492 | 
493 |     Rank8: https://github.com/SeuTao/Kaggle_Airbus2018_8th_code
494 |     
495 |     Rank21: https://github.com/pascal1129/kaggle_airbus_ship_detection
496 | 
497 | 
498 | 9.  kaggle RSNA Pneumonia Detection
499 | 
500 |     Rank1: https://github.com/i-pan/kaggle-rsna18
501 |     
502 |     Rank2: https://github.com/SeuTao/Kaggle_TGS2018_4th_solution
503 |     
504 |     Rank3: https://github.com/pmcheng/rsna-pneumonia
505 |     
506 |     Rank6: https://github.com/pfnet-research/pfneumonia
507 |     
508 |     Rank10: https://github.com/alessonscap/rsna-challenge-2018
509 |    
510 | 0.  Kaggle PLAsTiCC Astronomical Classification Competition（PLAsTiCC 天文分类比赛）
511 | 
512 |     Rank1: https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75033
513 | 
514 |     Rank2: https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75059
515 | 
516 |     Rank3: 
517 |     
518 |     +   https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75116
519 |     
520 |     +   https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75131
521 |     
522 |     +   https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75222
523 | 
524 |     Rank4: https://github.com/aerdem4/kaggle-plasticc
525 | 
526 |     Rank5: https://www.kaggle.com/c/PLAsTiCC-2018/discussion/75040
527 |    
528 | 1.  Kaggle Human Protein Atlas Image Classification Challenge（Kaggle 人类蛋白质图谱图像分类比赛）
529 | 
530 |     Rank3: https://github.com/pudae/kaggle-hpa
531 |    
532 | 1.  SpaceNet Challenge Round 4: Off-Nadir Buildings（SpaceNet 挑战卫星图片建筑物识别）
533 | 
534 |     RankX: https://github.com/SpaceNetChallenge/SpaceNet_Off_Nadir_Solutions
535 |    
536 | 1.  Kaggle Humpback Whale Identification Challenge（Kaggle 座头鲸识别比赛）
537 | 
538 |     Rank1: https://github.com/earhian/Humpback-Whale-Identification-1st-
539 | 
540 |     Rank7: https://medium.com/@ducha.aiki/thanks-radek-7th-place-solution-to-hwi-2019-competition-738624e4c885
541 | 
542 | 0.  kaggle Carvana Image Masking Challenge
543 | 
544 |     Rank1:https://github.com/asanakoy/kaggle_carvana_segmentation
545 |     
546 |     Rank3:https://github.com/lyakaap/Kaggle-Carvana-3rd-place-solution
547 |     
548 | 1.  kaggle Statoil/C-CORE Iceberg Classifier Challenge
549 | 
550 |     Rank4: https://github.com/asydorchuk/kaggle/blob/master/statoil/README.md
551 |     
552 | 2.  kaggle 2018 Data Science Bowl
553 |     
554 |     Rank1: https://github.com/selimsef/dsb2018_topcoders
555 |     
556 |     Rank2: https://github.com/jacobkie/2018DSB
557 |     
558 |     Rank3: https://github.com/Lopezurrutia/DSB_2018
559 |     
560 |     Rank4: https://github.com/pdima/kaggle_2018_data_science_bowl_solution
561 |     
562 |     Rank5: https://github.com/mirzaevinom/data_science_bowl_2018
563 |     
564 | 
565 | ## 其它资源列表
566 | 
567 | 1.  [DataSciComp 数据比赛资讯](https://github.com/iphysresearch/DataSciComp)
568 | 
569 | 1.  [ApacheCN 的 kaggle 资料链接](https://github.com/apachecn/kaggle)
570 | 
571 | 2.  [Kaggle top 方案整理](https://github.com/EliotAndres/kaggle-past-solutions)
572 | 
573 | 3.  [Data competition Top Solution 数据竞赛 Top 解决方案开源整理](https://github.com/Smilexuhc/Data-Competition-TopSolution)
574 | 
575 | 1.  [介绍 featexp 一个帮助理解特征的工具包](http://www.sohu.com/a/273552971_129720)
576 | 
577 | 1.  [Ask Me Anything session with a Kaggle Grandmaster Vladimir I. Iglovikov](http://t.cn/Eww4nnu) [PDF](https://pan.baidu.com/s/1XkFwko_YrI5TfjjIai7ONQ)
578 | 
579 | 1.  [Owen Zhang 访谈: Kaggle 制胜的秘密](http://t.cn/RBzPcyg)
580 | 
581 | 1.  [How to Compete for Zillow Prize at Kaggle](https://www.datasciencecentral.com/profiles/blogs/how-to-compete-for-zillow-prize-at-kaggle)
582 | 
583 | 1.  [Profiling Top Kagglers: Martin Henze](http://blog.kaggle.com/2018/06/19/tales-from-my-first-year-inside-the-head-of-a-recent-kaggle-addict/)
584 | 
585 | 1.  [Kaggle 数据科学词汇表](http://t.cn/Rdx72Cn)
586 | 
587 | 1.  [Kaggle 比赛优胜方案汇总](http://t.cn/Rdkj3Co)
588 | 
589 | 1.  [Kaggle 比赛实战教程(Pandas, Matplotlib, XGBoost/Colab)](http://t.cn/ReIJOX0)
590 | 
591 | 1.  [llSourcell/kaggle_challenge](http://t.cn/ReIJOXK)
592 | 
593 | 1.  [Kaggle 看照片猜相机比赛心得分享](http://t.cn/Rkz5Q9y) [PDF](http://t.cn/Rkz5Q9L)
594 | 
595 | 1.  [Kaggle 在线分类广告需求预测比赛优胜方案分享](http://t.cn/RFpQg9O)
596 | 
597 | 1.  [Kaggle | Winner Interview ](http://blog.kaggle.com/2018/09/14/pei-lien-chou/)
598 | 
599 | 1.  [2018 NIPS 视觉对抗挑战总结](http://t.cn/EAMqw0P)
600 | 
601 |     
602 | ## 大佬的 Git
603 | 
604 | 1.  植物: https://github.com/plantsgo 
605 | 2.  wepon: https://github.com/wepe 
606 | 3.  Snake: https://github.com/luoda888 
607 | 4.  Drop-out: https://github.com/drop-out 
608 | 5.  金老师的知乎: https://zhuanlan.zhihu.com/jlbookworm 
609 | 6.  渣大: https://github.com/nzc 
610 | 7.  郭大: https://github.com/guoday 
611 | 8.  Cortex Lab: https://github.com/CortexFoundation
612 | 


--------------------------------------------------------------------------------
/Data-Competition2020.md:
--------------------------------------------------------------------------------
 1 | # Data-Competition2020
 2 | - [x] [Data-competition2019](https://github.com/xiaoketongxue/AI-News/blob/master/Data-Competition.md)
 3 | - [x] [结构化数据/时间序列](#结构化数据/时间序列)
 4 | - [x] [NLP](#NLP)
 5 | - [x] [CV](#CV)
 6 | - [x] [其它资源列表](#其它资源列表)
 7 | - [x] [大佬的 Git](#大佬的-Git)
 8 | 
 9 | ## 结构化数据/时间序列
10 |   - 阿里天池-安泰杯跨境电商智能算法大赛
11 |     + [Top1法国南部](https://github.com/RainFung/Tianchi-AntaiCup-International-E-commerce-Artificial-Intelligence-Challenge)
12 | ## NLP
13 |   - [智源&计算所-互联网虚假新闻检测挑战赛](https://www.biendata.com/competition/falsenews/)
14 |     + [Top1](https://www.biendata.com/models/category/3529/L_notebook/)
15 | 


--------------------------------------------------------------------------------
/NLP2020.md:
--------------------------------------------------------------------------------
 1 | # NLP2020
 2 | - [x] [Classification](#Classification)
 3 | - [x] [named entity recognition](#named-entity-recognition)
 4 | 
 5 | ## Classification
 6 |   - arxiv
 7 |     + [Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference](https://arxiv.org/abs/2002.04815)
 8 |   - ICAART 
 9 |     + [Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification](https://arxiv.org/abs/2001.11857)[[Keras]](https://github.com/mtrusca/HTCNN)
10 |   - ICONIP 2019
11 |     + [A Deep Neural Framework for Contextual Affect Detection](https://arxiv.org/abs/2001.10169)
12 |   - BERT
13 |     + [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.xilesou.top/abs/1909.11942)[[Code]](https://github.com/google-research/ALBERT)
14 |     + [RobBERT: a Dutch RoBERTa-based Language Model](https://arxiv.org/abs/2001.06286)
15 |     + [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692)
16 |     + [PoWER-BERT: Accelerating BERT inference for Classification Tasks](https://arxiv.org/abs/2001.08950)
17 |     + [TinyBERT: Distilling BERT for Natural Language Understanding](https://arxiv.org/abs/1909.10351)
18 |   - NIPS2019
19 |     + [XLNet: Generalized Autoregressive Pretraining for Language Understanding](http://papers.nips.cc/paper/8812-xlnet-generalized-autoregressive-pretraining-for-language-understanding)
20 |   - 2018
21 |     + [BERT: Pre-training of Deep Bidirectional Transformers for
22 | Language Understanding](https://arxiv.xilesou.top/abs/1810.04805)
23 |   
24 | ## named entity recognition
25 |   - 2020
26 |     + [A multimodal deep learning approach for named entity recognition from social media](https://arxiv.org/abs/2001.06888)
27 |   - arxiv
28 |     + [Self-attention-based BiGRU and capsule network for named entity recognition](https://arxiv.org/abs/2002.00735)
29 |     + [Joint Embedding in Named Entity Linking on Sentence Level](https://arxiv.org/abs/2002.04936)
30 |     + [Zero-Resource Cross-Domain Named Entity Recognition](https://arxiv.org/abs/2002.05923)
31 | 


--------------------------------------------------------------------------------
/Other_Awesome.md:
--------------------------------------------------------------------------------
  1 | ## Other_Awesome
  2 | - [Awesome](#awesome-paper-list)
  3 |   - [Tabel of Contents](#tabel-of-contents)
  4 |   - [Contributing](#contributing)
  5 |   - [Natural Language Processing](#natural-language-processing)
  6 |   - [Computer Vision](#computer-vision)
  7 |   - [Graphs](#graphs)
  8 |   - [Knowledge Graph](#knowledge-graph)
  9 |   - [MultiModality](#multimodality)
 10 |   - [Others](#others)
 11 |   - [Commensense](#commensense)
 12 |   - [Time Series](#time-series)
 13 |   - [Speech](#speech)
 14 |   - [Causality](#causality)
 15 |   - [Anomaly Detection](#anomaly-detection)
 16 | 
 17 | ## Natural Language Processing
 18 | 
 19 | * [Machine Translation](https://github.com/maidis/awesome-machine-translation) <br> ![](https://img.shields.io/badge/author-maidis-be8abf) ![](https://img.shields.io/github/stars/maidis/awesome-machine-translation)
 20 | * [Text Classification](https://github.com/fendouai/Awesome-Text-Classification) <br> ![](https://img.shields.io/badge/author-fendouai-be8abf) ![](https://img.shields.io/github/stars/fendouai/Awesome-Text-Classification)
 21 | * [Sentiment Analysis](https://github.com/xiamx/awesome-sentiment-analysis) <br> ![](https://img.shields.io/badge/author-xiamx-be8abf) ![](https://img.shields.io/github/stars/xiamx/awesome-sentiment-analysis)
 22 | * [Sentiment Analysis](https://github.com/laugustyniak/awesome-sentiment-analysis) <br> ![](https://img.shields.io/badge/author-laugustyniak-be8abf) ![](https://img.shields.io/github/stars/laugustyniak/awesome-sentiment-analysis)
 23 | * [Sentiment Analysis](https://github.com/haiker2011/awesome-nlp-sentiment-analysis) <br> ![](https://img.shields.io/badge/author-haiker2011-be8abf) ![](https://img.shields.io/github/stars/haiker2011/awesome-nlp-sentiment-analysis)
 24 | * [Aspect-Based Sentiment Analysis](https://github.com/ZhengZixiang/ABSAPapers) <br> ![](https://img.shields.io/badge/author-ZhengZixiang-be8abf) ![](https://img.shields.io/github/stars/ZhengZixiang/ABSAPapers)
 25 | * [Aspect-Based Sentiment Analysis](https://github.com/jiangqn/Aspect-Based-Sentiment-Analysis) <br> ![](https://img.shields.io/badge/author-jiangqn-be8abf) ![](https://img.shields.io/github/stars/jiangqn/Aspect-Based-Sentiment-Analysis)
 26 | * [Machine Reading Comprehension](https://github.com/thunlp/RCPapers) <br> ![](https://img.shields.io/badge/author-thunlp-be8abf) ![](https://img.shields.io/github/stars/thunlp/RCPapers)
 27 | * [Machine Reading Comprehension](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers) <br> ![](https://img.shields.io/badge/author-xanhho-be8abf) ![](https://img.shields.io/github/stars/xanhho/Reading-Comprehension-Question-Answering-Papers)
 28 | * [Relation Extraction](https://github.com/thunlp/NREPapers) <br> ![](https://img.shields.io/badge/author-thunlp-be8abf) ![](https://img.shields.io/github/stars/thunlp/NREPapers)
 29 | * [Relation Extraction](https://github.com/roomylee/awesome-relation-extraction) <br> ![](https://img.shields.io/badge/author-roomylee-be8abf) ![](https://img.shields.io/github/stars/roomylee/awesome-relation-extraction)
 30 | * [BERT-based Research](https://github.com/cedrickchee/awesome-bert-nlp) <br> ![](https://img.shields.io/badge/author-cedrickchee-be8abf) ![](https://img.shields.io/github/stars/cedrickchee/awesome-bert-nlp)
 31 | * [Pre-trained Language Model](https://github.com/thunlp/PLMpapers) <br> ![](https://img.shields.io/badge/author-thunlp-be8abf) ![](https://img.shields.io/github/stars/thunlp/PLMpapers)
 32 | * [Sememe Computation](https://github.com/thunlp/SCPapers) <br> ![](https://img.shields.io/badge/author-thunlp-be8abf) ![](https://img.shields.io/github/stars/thunlp/SCPapers)
 33 | * [Text Generation](https://github.com/THUNLP-MT/TG-Reading-List)<br> ![](https://img.shields.io/badge/author-THUNLP_MT-be8abf) ![](https://img.shields.io/github/stars/THUNLP-MT/TG-Reading-List)
 34 | * [Text Generation](https://github.com/ChenChengKuan/awesome-text-generation) <br> ![](https://img.shields.io/badge/author-ChenChengKuan-be8abf) ![](https://img.shields.io/github/stars/ChenChengKuan/awesome-text-generation)
 35 | * [Textual Adversarial Attack and Defense](https://github.com/thunlp/TAADpapers) <br> ![](https://img.shields.io/badge/author-thunlp-be8abf) ![](https://img.shields.io/github/stars/thunlp/TAADpapers)
 36 | * [Dialogue System](https://github.com/jaromirsalamon/Awesome-Dialogue-System-Papers) <br> ![](https://img.shields.io/badge/author-jaromirsalamon-be8abf) ![](https://img.shields.io/github/stars/jaromirsalamon/Awesome-Dialogue-System-Papers)
 37 | * [Dialogue System](https://github.com/ZhengZixiang/DSPapers) <br> ![](https://img.shields.io/badge/author-ZhengZixiang-be8abf) ![](https://img.shields.io/github/stars/ZhengZixiang/DSPapers)
 38 | * [Dialogue Generation](https://github.com/tsenghungchen/dialog-generation-paper) <br> ![](https://img.shields.io/badge/author-tsenghungchen-be8abf) ![](https://img.shields.io/github/stars/tsenghungchen/dialog-generation-paper)
 39 | * [Dialogue System](https://github.com/yajingsunno/dialogue-system-reading-paper-list) <br> ![](https://img.shields.io/badge/author-yajingsunno-be8abf) ![](https://img.shields.io/github/stars/yajingsunno/dialogue-system-reading-paper-list)
 40 | * [Dialogue State Tracking](https://github.com/google-research-datasets/dstc8-schema-guided-dialogue) <br> ![](https://img.shields.io/badge/author-google-be8abf) ![](https://img.shields.io/github/stars/google-research-datasets/dstc8-schema-guided-dialogue)
 41 | * [Task-Oriented Dialogue](https://github.com/AtmaHou/Task-Oriented-Dialogue-Dataset-Survey) <br> ![](https://img.shields.io/badge/author-AtmaHou-be8abf) ![](https://img.shields.io/github/stars/AtmaHou/Task-Oriented-Dialogue-Dataset-Survey)
 42 | * [Conversational AI](https://github.com/jianguoz/Conversational-AI) <br> ![](https://img.shields.io/badge/author-jianguoz-be8abf) ![](https://img.shields.io/github/stars/jianguoz/Conversational-AI)
 43 | * [Sentence Embeddings](https://github.com/Separius/awesome-sentence-embedding) <br> ![](https://img.shields.io/badge/author-Separius-be8abf) ![](https://img.shields.io/github/stars/Separius/awesome-sentence-embedding)
 44 | * [Question Answering](https://github.com/dapurv5/awesome-question-answering) <br> ![](https://img.shields.io/badge/author-dapurv5-be8abf) ![](https://img.shields.io/github/stars/dapurv5/awesome-question-answering)
 45 | * [Knowledge Base Question Answering](https://github.com/BshoterJ/awesome-knowledge-graph-question-answering) <br> ![](https://img.shields.io/badge/author-Bshoter-be8abf) ![](https://img.shields.io/github/stars/BshoterJ/awesome-knowledge-graph-question-answering)
 46 | * [Text Style Transfer](https://github.com/fuzhenxin/Style-Transfer-in-Text) <br> ![](https://img.shields.io/badge/author-fuzhenxin-be8abf) ![](https://img.shields.io/github/stars/fuzhenxin/Style-Transfer-in-Text)
 47 | * [Text Style Transfer](https://github.com/yd1996/awesome-text-style-transfer) <br> ![](https://img.shields.io/badge/author-yd1996-be8abf) ![](https://img.shields.io/github/stars/yd1996/awesome-text-style-transfer)
 48 | * [Text Matching](https://github.com/NTMC-Community/awesome-neural-models-for-semantic-match) <br> ![](https://img.shields.io/badge/author-NTMC_Community-be8abf) ![](https://img.shields.io/github/stars/NTMC-Community/awesome-neural-models-for-semantic-match)
 49 | * [Text Summarization](https://github.com/luopeixiang/awesome-text-summarization) <br> ![](https://img.shields.io/badge/author-NTMC_Community-be8abf) ![](https://img.shields.io/github/stars/NTMC-Community/awesome-neural-models-for-semantic-match)
 50 | * [Personal Emotional Stylized Dialog](https://github.com/fuzhenxin/Personal-Emotional-Stylized-Dialog) <br> ![](https://img.shields.io/badge/author-fuzhenxin-be8abf) ![](https://img.shields.io/github/stars/fuzhenxin/Personal-Emotional-Stylized-Dialog)
 51 | * [Named Entity Recognition](https://github.com/pfliu-nlp/Named-Entity-Recognition-NER-Papers) <br> ![](https://img.shields.io/badge/author-pfliu-be8abf) ![](https://img.shields.io/github/stars/pfliu-nlp/Named-Entity-Recognition-NER-Papers)
 52 | * [Biomedical NER](https://github.com/lingluodlut/BioNER-Progress) <br> ![](https://img.shields.io/badge/author-lingluodlut-be8abf) ![](https://img.shields.io/github/stars/lingluodlut/BioNER-Progress)
 53 | * [Named Entity Recognition](https://github.com/ZhengZixiang/NERPapers) <br> ![](https://img.shields.io/badge/author-ZhengZixiang-be8abf) ![](https://img.shields.io/github/stars/ZhengZixiang/NERPapers)
 54 | * [Cross-lingual Information Retrieval](https://github.com/ryanzhumich/awesome-clir) <br> ![](https://img.shields.io/badge/author-ryanzhumich-be8abf) ![](https://img.shields.io/github/stars/ryanzhumich/awesome-clir)
 55 | * [Information Retrieval](https://github.com/harpribot/awesome-information-retrieval) <br> ![](https://img.shields.io/badge/author-harpribot-be8abf) ![](https://img.shields.io/github/stars/harpribot/awesome-information-retrieval)
 56 | * [Biomedical Entity Linking](https://github.com/umbrellabeach/awesome-Biomedical-EntityLinking-papers) <br> 
 57 | ![](https://img.shields.io/badge/author-umbrellabeach-be8abf)
 58 | ![](https://img.shields.io/github/stars/umbrellabeach/awesome-Biomedical-EntityLinking-papers)
 59 | * [Open Information Extraction](https://github.com/NPCai/Open-IE-Papers) <br>
 60 | ![](https://img.shields.io/badge/author-NPCai-be8abf)
 61 | ![](https://img.shields.io/github/stars/NPCai/Open-IE-Papers)
 62 | * [Biomedical Information Extraction](https://github.com/caufieldjh/awesome-bioie) <br>
 63 | ![](https://img.shields.io/badge/author-caufieldjh-be8abf)
 64 | ![](https://img.shields.io/github/stars/caufieldjh/awesome-bioie)
 65 | 
 66 | 
 67 | ## Computer Vision
 68 | 
 69 | * [Semantic Segmentation](https://github.com/mrgloom/awesome-semantic-segmentation) <br>
 70 | ![](https://img.shields.io/badge/author-mrgloom-be8abf)
 71 | ![](https://img.shields.io/github/stars/mrgloom/awesome-semantic-segmentation)
 72 | * [Action Recognition](https://github.com/jinwchoi/awesome-action-recognition) <br>
 73 | ![](https://img.shields.io/badge/author-jinwchoi-be8abf)
 74 | ![](https://img.shields.io/github/stars/jinwchoi/awesome-action-recognition)
 75 | * [Image Classification](https://github.com/weiaicunzai/awesome-image-classification) <br>
 76 | ![](https://img.shields.io/badge/author-weiaicunzai-be8abf)
 77 | ![](https://img.shields.io/github/stars/weiaicunzai/awesome-image-classification)
 78 | * [Image Retrieval](https://github.com/willard-yuan/awesome-cbir-papers) <br>
 79 | ![](https://img.shields.io/badge/author-willard_yuan-be8abf)
 80 | ![](https://img.shields.io/github/stars/willard-yuan/awesome-cbir-papers)
 81 | * [Object Detection](https://github.com/amusi/awesome-object-detection) <br>
 82 | ![](https://img.shields.io/badge/author-amusi-be8abf)
 83 | ![](https://img.shields.io/github/stars/amusi/awesome-object-detection)
 84 | * [Object Detection](https://github.com/hoya012/deep_learning_object_detection) <br>
 85 | ![](https://img.shields.io/badge/author-hoya012-be8abf)
 86 | ![](https://img.shields.io/github/stars/hoya012/deep_learning_object_detection)
 87 | * [Image-to-image Translation](https://github.com/xiaweihao/awesome-image-translation) <br>
 88 | ![](https://img.shields.io/badge/author-xiaweihao-be8abf)
 89 | ![](https://img.shields.io/github/stars/xiaweihao/awesome-image-translation)
 90 | * [Domain Adaptation](https://github.com/zhaoxin94/awesome-domain-adaptation) <br>
 91 | ![](https://img.shields.io/badge/author-zhaoxin94-be8abf)
 92 | ![](https://img.shields.io/github/stars/zhaoxin94/awesome-domain-adaptation)
 93 | * [vision-based SLAM / Visual Odometry](https://github.com/tzutalin/awesome-visual-slam) <br>
 94 | ![](https://img.shields.io/badge/author-tzutalin-be8abf)
 95 | ![](https://img.shields.io/github/stars/tzutalin/awesome-visual-slam)
 96 | * [Face-related](https://github.com/ChanChiChoi/awesome-Face_Recognition) <br>
 97 | ![](https://img.shields.io/badge/author-ChanChiChoi-be8abf)
 98 | ![](https://img.shields.io/github/stars/ChanChiChoi/awesome-Face_Recognition)
 99 | * [Scene Text Recognition](https://github.com/chongyangtao/Awesome-Scene-Text-Recognition) <br>
100 | ![](https://img.shields.io/badge/author-chongyangtao-be8abf)
101 | ![](https://img.shields.io/github/stars/chongyangtao/Awesome-Scene-Text-Recognition)
102 | * [Text Detection & Recognition](https://github.com/hwalsuklee/awesome-deep-text-detection-recognition) <br>
103 | ![](https://img.shields.io/badge/author-hwalsuklee-be8abf)
104 | ![](https://img.shields.io/github/stars/hwalsuklee/awesome-deep-text-detection-recognition)
105 | 
106 | 
107 | ## Graphs
108 | 
109 | * [Graph Neural Networks](https://github.com/nnzhan/Awesome-Graph-Neural-Networks) <br>
110 | ![](https://img.shields.io/badge/author-nnzhan-be8abf)
111 | ![](https://img.shields.io/github/stars/nnzhan/Awesome-Graph-Neural-Networks)
112 | * [Graph Neural Networks](https://github.com/thunlp/GNNPapers) <br>
113 | ![](https://img.shields.io/badge/author-thunlp-be8abf)
114 | ![](https://img.shields.io/github/stars/thunlp/GNNPapers)
115 | * [Graph Convolutional Networks](https://github.com/Jiakui/awesome-gcn) <br>
116 | ![](https://img.shields.io/badge/author-Jiakui-be8abf)
117 | ![](https://img.shields.io/github/stars/Jiakui/awesome-gcn)
118 | * [Graph Classification](https://github.com/benedekrozemberczki/awesome-graph-classification) <br>
119 | ![](https://img.shields.io/badge/author-benedekrozemberczki-be8abf)
120 | ![](https://img.shields.io/github/stars/benedekrozemberczki/awesome-graph-classification)
121 | * [Graph Representation Learning](https://github.com/ky-zhang/awesome-graph-representation-learning) <br>
122 | ![](https://img.shields.io/badge/author-ky_zhang-be8abf)
123 | ![](https://img.shields.io/github/stars/ky-zhang/awesome-graph-representation-learning)
124 | * [Graph Representation Learning](https://github.com/thunlp/NRLPapers) <br>
125 | ![](https://img.shields.io/badge/author-thunlp-be8abf)
126 | ![](https://img.shields.io/github/stars/thunlp/NRLPapers)
127 | * [Network Embeddings](https://github.com/chihming/awesome-network-embedding) <br>
128 | ![](https://img.shields.io/badge/author-chihming-be8abf)
129 | ![](https://img.shields.io/github/stars/chihming/awesome-network-embedding)
130 | * [Knowledge Graph Embeddings](https://github.com/thunlp/KB2E) <br>
131 | ![](https://img.shields.io/badge/author-thun-be8abf)
132 | ![](https://img.shields.io/github/stars/thunlp/KB2E)
133 | * [Community Detection](https://github.com/benedekrozemberczki/awesome-community-detection) <br>
134 | ![](https://img.shields.io/badge/author-benedekrozemberczki-be8abf)
135 | ![](https://img.shields.io/github/stars/benedekrozemberczki/awesome-community-detection)
136 | * [Topological Data Analysis](https://github.com/FatemehTarashi/awesome-TDA) <br>
137 | ![](https://img.shields.io/badge/author-FatemehTarashi-be8abf)
138 | ![](https://img.shields.io/github/stars/FatemehTarashi/awesome-TDA)
139 | * [Graph Adversarial Learning](https://github.com/YingtongDou/graph-adversarial-learning-literature) <br>
140 | ![](https://img.shields.io/badge/author-YingtongDou-be8abf)
141 | ![](https://img.shields.io/github/stars/YingtongDou/graph-adversarial-learning-literature)
142 | * [Graph Computing](https://github.com/jbmusso/awesome-graph) <br>
143 | ![](https://img.shields.io/badge/author-jbmusso-be8abf)
144 | ![](https://img.shields.io/github/stars/jbmusso/awesome-graph)
145 | 
146 | ## Knowledge Graph
147 | 
148 | * [Knowledge Graph Construction](https://github.com/songjiang0909/awesome-knowledge-graph-construction) <br>
149 | ![](https://img.shields.io/badge/author-songjiang0909-be8abf)
150 | ![](https://img.shields.io/github/stars/songjiang0909/awesome-knowledge-graph-construction)
151 | * [Knowledge Embeddings](https://github.com/thunlp/KRLPapers) <br>
152 | ![](https://img.shields.io/badge/author-thunlp-be8abf)
153 | ![](https://img.shields.io/github/stars/thunlp/KRLPapers)
154 | * [Knowledge Graph](https://github.com/husthuke/awesome-knowledge-graph) <br>
155 | ![](https://img.shields.io/badge/author-husthuke-be8abf)
156 | ![](https://img.shields.io/github/stars/husthuke/awesome-knowledge-graph)
157 | * [Knowledge Graph](https://github.com/shaoxiongji/awesome-knowledge-graph) <br>
158 | ![](https://img.shields.io/badge/author-shaoxiongji-be8abf)
159 | ![](https://img.shields.io/github/stars/shaoxiongji/awesome-knowledge-graph)
160 | * [Knowledge Graph](https://github.com/BrambleXu/knowledge-graph-learning) <br>
161 | ![](https://img.shields.io/badge/author-BrambleXu-be8abf)
162 | ![](https://img.shields.io/github/stars/BrambleXu/knowledge-graph-learning)
163 | * [Knowledge Graph](https://github.com/totogo/awesome-knowledge-graph) <br>
164 | ![](https://img.shields.io/badge/author-totogo-be8abf)
165 | ![](https://img.shields.io/github/stars/totogo/awesome-knowledge-graph)
166 | 
167 | 
168 | ## MultiModality
169 | 
170 | * [Image Captioning](https://github.com/zhjohnchan/awesome-image-captioning)  <br>
171 | ![](https://img.shields.io/badge/author-zhjohnchan-be8abf)
172 | ![](https://img.shields.io/github/stars/zhjohnchan/awesome-image-captioning)
173 | * [Image Captioning](https://github.com/forence/Awesome-Visual-Captioning)  <br>
174 | ![](https://img.shields.io/badge/author-forence-be8abf)
175 | ![](https://img.shields.io/github/stars/forence/Awesome-Visual-Captioning)
176 | * [Visual Question Answering](https://github.com/chingyaoc/awesome-vqa)  <br>
177 | ![](https://img.shields.io/badge/author-chingyaoc-be8abf)
178 | ![](https://img.shields.io/github/stars/chingyaoc/awesome-vqa)
179 | * [Visual Question Answering](https://github.com/jokieleung/awesome-visual-question-answering)  <br>
180 | ![](https://img.shields.io/badge/author-jokieleung-be8abf)
181 | ![](https://img.shields.io/github/stars/jokieleung/awesome-visual-question-answering)
182 | * [Visual Question Answering](https://github.com/DerekDLP/VQA-papers)  <br>
183 | ![](https://img.shields.io/badge/author-DerekDLP-be8abf)
184 | ![](https://img.shields.io/github/stars/DerekDLP/VQA-papers)
185 | * [Multimodal Machine Translation](https://github.com/ZihengZZH/awesome-multimodal-machine-translation)  <br>
186 | ![](https://img.shields.io/badge/author-ZihengZZH-be8abf)
187 | ![](https://img.shields.io/github/stars/ZihengZZH/awesome-multimodal-machine-translation)
188 | * [Visual Grounding](https://github.com/TheShadow29/awesome-grounding)  <br>
189 | ![](https://img.shields.io/badge/author-TheShadow29-be8abf)
190 | ![](https://img.shields.io/github/stars/TheShadow29/awesome-grounding)
191 | 
192 | 
193 |   
194 | ## Others
195 | 
196 | * [Awesome-VAEs](https://github.com/matthewvowels1/Awesome-VAEs) <br>
197 | ![](https://img.shields.io/badge/author-matthewvowels1-be8abf)
198 | ![](https://img.shields.io/github/stars/matthewvowels1/Awesome-VAEs)
199 | * [Unsupervised Learning](https://github.com/LongLong-Jing/awesome-unsupervised-learning) <br>
200 | ![](https://img.shields.io/badge/author-LongLong_Jing-be8abf)
201 | ![](https://img.shields.io/github/stars/LongLong-Jing/awesome-unsupervised-learning)
202 | * [Meta Learning](https://github.com/floodsung/Meta-Learning-Papers) <br>
203 | ![](https://img.shields.io/badge/author-floodsung-be8abf)
204 | ![](https://img.shields.io/github/stars/floodsung/Meta-Learning-Papers)
205 | * [Few Shot Learning](https://github.com/e-271/awesome-few-shot-learning) <br>
206 | ![](https://img.shields.io/badge/author-e_271-be8abf)
207 | ![](https://img.shields.io/github/stars/e-271/awesome-few-shot-learning)
208 | * [Few Shot Learning](https://github.com/Duan-JM/awesome-papers-fewshot) <br>
209 | ![](https://img.shields.io/badge/author-Duan_JM-be8abf)
210 | ![](https://img.shields.io/github/stars/Duan-JM/awesome-papers-fewshot)
211 | * [Capsule Networks](https://github.com/sekwiatkowski/awesome-capsule-networks) <br>
212 | ![](https://img.shields.io/badge/author-sekwiatkowski-be8abf)
213 | ![](https://img.shields.io/github/stars/sekwiatkowski/awesome-capsule-networks)
214 | * [Decision Tree](https://github.com/benedekrozemberczki/awesome-decision-tree-papers) <br>
215 | ![](https://img.shields.io/badge/author-benedekrozemberczki-be8abf)
216 | ![](https://img.shields.io/github/stars/benedekrozemberczki/awesome-decision-tree-papers)
217 | * [Cell Detection & Segmentation](https://github.com/blakeliu/awesome-cell-detection-segmentation) <br>
218 | ![](https://img.shields.io/badge/author-blakeliu-be8abf)
219 | ![](https://img.shields.io/github/stars/blakeliu/awesome-cell-detection-segmentation)
220 | * [Fraud Detection](https://github.com/benedekrozemberczki/awesome-fraud-detection-papers) <br>
221 | ![](https://img.shields.io/badge/author-benedekrozemberczki-be8abf)
222 | ![](https://img.shields.io/github/stars/benedekrozemberczki/awesome-fraud-detection-papers)
223 | * [Legal Intelligence](https://github.com/thunlp/LegalPapers) <br>
224 | ![](https://img.shields.io/badge/author-thunlp-be8abf)
225 | ![](https://img.shields.io/github/stars/thunlp/LegalPapers)
226 | * [Data Augmentation](https://github.com/CrazyVertigo/awesome-data-augmentation) <br>
227 | ![](https://img.shields.io/badge/author-CrazyVertigo-be8abf)
228 | ![](https://img.shields.io/github/stars/CrazyVertigo/awesome-data-augmentation)
229 | * [Decision Making](https://github.com/jiachenli94/Awesome-Decision-Making-Reinforcement-Learning) <br>
230 | ![](https://img.shields.io/badge/author-jiachenli94-be8abf)
231 | ![](https://img.shields.io/github/stars/jiachenli94/Awesome-Decision-Making-Reinforcement-Learning)
232 | 
233 | ## Commensense
234 | * [Commonsense Reasoning](https://github.com/yhy1117/Commonsense_Reasoning_Papers) <br>
235 | ![](https://img.shields.io/badge/author-yhy1117-be8abf)
236 | ![](https://img.shields.io/github/stars/yhy1117/Commonsense_Reasoning_Papers)
237 | * [Commonsense Modeling](https://github.com/wonderseen/Commonsense-Modeling) <br>
238 | ![](https://img.shields.io/badge/author-wonderseen-be8abf)
239 | ![](https://img.shields.io/github/stars/wonderseen/Commonsense-Modeling)
240 | 
241 | ## Time Series
242 | 
243 | * [Time Series](https://github.com/xephonhq/awesome-time-series-database) <br>
244 | ![](https://img.shields.io/badge/author-xephonhq-be8abf)
245 | ![](https://img.shields.io/github/stars/xephonhq/awesome-time-series-database)
246 | * [Time Series](https://github.com/bighuang624/Time-Series-Papers) <br>
247 | ![](https://img.shields.io/badge/author-bighuang624-be8abf)
248 | ![](https://img.shields.io/github/stars/bighuang624/Time-Series-Papers)
249 | * [Time Series in Python](https://github.com/MaxBenChrist/awesome_time_series_in_python) <br>
250 | ![](https://img.shields.io/badge/author-MaxBenChrist-be8abf)
251 | ![](https://img.shields.io/github/stars/MaxBenChrist/awesome_time_series_in_python)
252 | * [Time Series Analysis](https://github.com/youngdou/awesome-time-series-analysis) <br>
253 | ![](https://img.shields.io/badge/author-youngdou-be8abf)
254 | ![](https://img.shields.io/github/stars/youngdou/awesome-time-series-analysis)
255 | 
256 | ## Speech
257 | 
258 | * [Speech Recognition & Synthesis](https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers) <br>
259 | ![](https://img.shields.io/badge/author-zzw922cn-be8abf)
260 | ![](https://img.shields.io/github/stars/zzw922cn/awesome-speech-recognition-speech-synthesis-papers)
261 | 
262 | * [End2End Speech Recognition](https://github.com/charlesliucn/awesome-end2end-speech-recognition) <br>
263 | ![](https://img.shields.io/badge/author-charlesliucn-be8abf)
264 | ![](https://img.shields.io/github/stars/charlesliucn/awesome-end2end-speech-recognition)
265 | * [Speech Enhancement](https://github.com/cyrta/awesome-speech-enhancement) <br>
266 | ![](https://img.shields.io/badge/author-cyrta-be8abf)
267 | ![](https://img.shields.io/github/stars/cyrta/awesome-speech-enhancement)
268 | 
269 | ## Causality
270 | 
271 | * [Causal Reasoning](https://github.com/dragen1860/awesome-causal-reasoning) <br>
272 | ![](https://img.shields.io/badge/author-dragen1860-be8abf)
273 | ![](https://img.shields.io/github/stars/dragen1860/awesome-causal-reasoning)
274 | * [Causal Inference](https://github.com/imirzadeh/awesome-causal-inference) <br>
275 | ![](https://img.shields.io/badge/author-imirzadeh-be8abf)
276 | ![](https://img.shields.io/github/stars/imirzadeh/awesome-causal-inference)
277 | * [Causality Algorithms](https://github.com/rguo12/awesome-causality-algorithms) <br>
278 | ![](https://img.shields.io/badge/author-rguo12-be8abf)
279 | ![](https://img.shields.io/github/stars/rguo12/awesome-causality-algorithms)
280 | * [Causality](https://github.com/napsternxg/awesome-causality) <br>
281 | ![](https://img.shields.io/badge/author-napsternxg-be8abf)
282 | ![](https://img.shields.io/github/stars/napsternxg/awesome-causality)
283 | * [Deep Causal Learning](https://github.com/huckiyang/awesome-deep-causal-learning) <br>
284 | ![](https://img.shields.io/badge/author-huckiyang-be8abf)
285 | ![](https://img.shields.io/github/stars/huckiyang/awesome-deep-causal-learning)
286 | 
287 | ## Anomaly Detection
288 | * [Anomaly Detection](https://github.com/yzhao062/anomaly-detection-resources) <br>
289 | ![](https://img.shields.io/badge/author-yzhao062-be8abf)
290 | ![](https://img.shields.io/github/stars/yzhao062/anomaly-detection-resources)
291 | 
292 | * [Anomaly Detection](https://github.com/hoya012/awesome-anomaly-detection) <br>
293 | ![](https://img.shields.io/badge/author-hoya012-be8abf)
294 | ![](https://img.shields.io/github/stars/hoya012/awesome-anomaly-detection)
295 | * [Anomaly Detection on Time-Series Data](https://github.com/rob-med/awesome-TS-anomaly-detection) <br>
296 | ![](https://img.shields.io/badge/author-rob_med-be8abf)
297 | ![](https://img.shields.io/github/stars/rob-med/awesome-TS-anomaly-detection)
298 | 


--------------------------------------------------------------------------------
/Others.md:
--------------------------------------------------------------------------------
  1 | CV-News
  2 | ======
  3 | - [x] [Semantation(new)](https://github.com/xiaoketongxue/AI-News/blob/master/CV2019.md)
  4 | - [x] [Classification](#Classification)  
  5 | - [x] [Graph Neural Networks](#Graph-Neural-Networks)    
  6 | - [x] [Super-Resolution](#Super-Resolution )    
  7 | - [x] [Registration](#Registration)  
  8 | - [x] [Reconstruction](#Reconstruction)
  9 | - [x] [Face](#Face)
 10 | - [x] [Normalization](#Normalization)   
 11 | - [x] [Survey](#Survey)   
 12 | - [x] [Dataset](#Dataset)  
 13 | - [x] [Conference and Journal ](#Conference-and-Journal )  
 14 |     
 15 | # Classification
 16 | ## 2019
 17 |   - NIPS
 18 |     + [Traned Rank Pruning for Efficient Deep Neural Networks](https://arxiv.org/abs/1910.04576)[Code](https://github.com/yuhuixu1993/Trained-Rank-Pruning)[Worksop]
 19 |   - ICCV 2019
 20 |     + [Domain Intersection and Domain Difference](https://arxiv.org/abs/1908.11628)[Code](https://github.com/sagiebenaim/DomainIntersectionDifference)
 21 |     + [Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks](https://arxiv.org/abs/1908.05867)
 22 |     + [Embarrassingly Simple Binary Representation Learning](https://arxiv.org/abs/1908.09573)[[Workshop]]
 23 |   - TIP
 24 |     + [Learning Guided Convolutional Network for Depth Completion](https://arxiv.org/abs/1908.01238)
 25 |   - MICCAI2019
 26 |     + [Multi-Instance Multi-Scale CNN for Medical Image Classification](https://arxiv.org/abs/1907.02413)
 27 |     + [Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progression](https://arxiv.org/abs/1907.02787)
 28 |   - Exploring Randomly Wired Neural Networks
 29 |     + [Exploring Randomly Wired Neural Networks for Image Recognition（Apr 2019）](https://arxiv.org/abs/1904.01569)[[Pyroech]](https://github.com/yoheikikuta/senet-keras/tree/master/model)
 30 |     + [Network Pruning via Transformable Architecture Search(May 2019)](https://arxiv.org/abs/1905.09717)[[Code]](https://github.com/D-X-Y/TAS)
 31 |     + [AM-LFS: AutoML for Loss Function Search](https://arxiv.org/abs/1905.07375)
 32 |     + [XNAS: Neural Architecture Search with Expert Advice](https://arxiv.org/abs/1906.08031)
 33 |   - Attention Module
 34 |     + [AttentionRNN: A Structured Spatial Attention Mechanism(May 2019)](https://arxiv.org/abs/1905.09400)
 35 |   - Knowledge distillation
 36 |     + [Adversarially Robust Distillation](https://arxiv.org/abs/1905.09747)
 37 |   - CVPR 2019
 38 |     + [SKNet:Selective Kernel Networks(Mar 2019)](https://arxiv.org/abs/1903.06586?context=cs)[[Coffe]](https://github.com/implus/SKNet)[[Pytorch]](https://github.com/xiaoketongxue/SKNet-1)
 39 |     + [HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs(Mar 2019)](https://arxiv.org/abs/1903.04120)   
 40 |     + [Bag of Tricks for Image Classification with Convolutional Neural Networks(Dec 2018)](https://arxiv.org/abs/1812.01187)[[Code]](https://gluon-cv.mxnet.io/)
 41 |     + [An attention-based multi-resolution model for prostate whole slide imageclassification and localization](https://arxiv.org/abs/1905.13208)[CVPRW]
 42 |     + [On-Device Neural Net Inference with Mobile GPUs](https://arxiv.org/abs/1907.01989)[CVPRW]
 43 |   - ISBI 2019
 44 |     + [Improved ICH classification using task-dependent learning(29 Jun )](https://arxiv.org/list/cs.CV/pastweek?skip=125&show=25)
 45 |   - ICML 2019   
 46 |     + [Making Convolutional Networks Shift-Invariant Again](https://arxiv.org/abs/1904.11486)[[Code]](https://github.com/richzhang/antialiased-cnns)
 47 |     + [Self-Attention Graph Pooling](https://arxiv.org/abs/1904.08082)   
 48 |   - arXiv
 49 |     + [Pruning at a Glance: Global Neural Pruning for Model Compression](https://arxiv.org/abs/1912.00200)
 50 |     + [Blockwisely Supervised Neural Architecture Search with Knowledge Distillation](https://arxiv.org/abs/1911.13053)
 51 |     + [Training convolutional neural networks with cheap convolutions and online distillation](https://arxiv.org/abs/1909.13063)[[Pytorch]](https://github.com/EthanZhangYC/OD-cheap-convolution)
 52 |     + [FALCON: Fast and Lightweight Convolution for Compressing and Accelerating CNN](https://arxiv.org/abs/1909.11321)
 53 |     + [diffGrad: An Optimization Method for Convolutional Neural Networks](https://arxiv.org/abs/1909.11015)
 54 |     + [EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks](https://arxiv.org/abs/1909.01939)
 55 |     + [EBPC: Extended Bit-Plane Compression for Deep Neural Network Inference and Training Accelerators](https://arxiv.org/abs/1908.11645)
 56 |     + [Gated Convolutional Networks with Hybrid Connectivity for Image Classification](https://arxiv.org/abs/1908.09699)
 57 |     + [A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification](https://arxiv.org/abs/1908.09745)
 58 |     + [Multi-Path Learnable Wavelet Neural Network for Image Classification](https://arxiv.org/abs/1908.09775)
 59 |     + [Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification](https://arxiv.org/abs/1908.06673)
 60 |     + [Pay attention to the activations: a modular attention mechanism for fine-grained image recognition](https://arxiv.org/abs/1907.13075)
 61 |     + [LinearConv: Regenerating Redundancy in Convolution Filters as Linear Combinations for Parameter Reduction](https://arxiv.org/abs/1907.11432)
 62 |     + [Universal Pooling -- A New Pooling Method for Convolutional Neural Networks](https://arxiv.org/abs/1907.11440)
 63 |     + [Context-Aware Multipath Networks](https://arxiv.org/list/cs.CV/recent)
 64 |     + [Multi-level Wavelet Convolutional Neural Networks](https://arxiv.org/abs/1907.03128)[[Pytorch]](https://github.com/lpj-github-io/MWCNNv2)
 65 |     + [Point-Voxel CNN for Efficient 3D Deep Learning](https://arxiv.org/abs/1907.03739)
 66 |     + [AutoSlim: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates](https://arxiv.org/abs/1907.03141)
 67 |     + [Dissecting Pruned Neural Networks(29 Jun)](https://arxiv.org/abs/1907.00262)
 68 |     + [Difficulty-aware Meta-Learning for Rare Disease Diagnosis( 30 Jun )](https://arxiv.org/abs/1907.00354)
 69 |     + [Attention routing between capsules](https://arxiv.org/abs/1907.01750)
 70 |     + [Deep Saliency Models : The Quest For The Loss Function](https://arxiv.org/abs/1907.02336)
 71 |     + [Mapped Convolutions](https://arxiv.org/abs/1906.11096)[[Code]](https://github.com/meder411/MappedConvolutions)
 72 |     + [Zero-Shot Image Classification Using Coupled Dictionary Embedding](https://arxiv.org/abs/1906.10509)
 73 |     + [Dense Scale Network for Crowd Counting](https://arxiv.org/abs/1906.09707)
 74 |     + [Efficient N-Dimensional Convolutions via Higher-Order Factorization](https://arxiv.org/abs/1906.06196)
 75 |     + [TensorNetwork for Machine Learning](https://arxiv.org/abs/1906.06329)
 76 |     + [A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks](https://arxiv.org/abs/1906.07488)
 77 |     + [ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition](https://arxiv.org/abs/1906.07671)
 78 |     + [HGC: Hierarchical Group Convolution for Highly Efficient Neural Network](https://arxiv.org/abs/1906.03657)
 79 |     + [Visual Tree Convolutional Neural Network in Image Classification](https://arxiv.org/abs/1906.01536)
 80 |     + [DIANet: Dense-and-Implicit Attention Network](https://arxiv.org/abs/1905.10671)[[Pytorch]](https://github.com/gbup-group/DIANet)
 81 |     + [HadaNets: Flexible Quantization Strategies for Neural Networks](https://arxiv.org/abs/1905.10759)
 82 |     + [FAN: Focused Attention Networks](https://arxiv.org/abs/1905.11498)
 83 |     + [Network Deconvolution](https://arxiv.org/abs/1905.11926)[[Pytorch]](https://github.com/deconvolutionpaper/deconvolution)
 84 |     + [SpecNet: Spectral Domain Convolutional Neural Network](https://arxiv.org/abs/1905.10915)
 85 |     + [Multi-Sample Dropout for Accelerated Training and Better Generalization](https://arxiv.org/abs/1905.09788)
 86 |     + [Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks](https://arxiv.org/abs/1905.09646)
 87 |     + [TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification(May 2019)](https://arxiv.org/abs/1905.08607)
 88 |     + [Skin Cancer Recognition using Deep Residual Network(May 2019)](https://arxiv.org/abs/1905.08610)
 89 |     + [Vehicle Shape and Color Classification Using Convolutional Neural Network(May 2019)](https://arxiv.org/abs/1905.08612)
 90 |     + [TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes](https://arxiv.org/abs/1905.06509)
 91 |     + [ISBNet: Instance-aware Selective Branching Network](https://arxiv.org/abs/1905.04849)
 92 |     + [Convolutional neural networks with fractional order gradient method(May 2019)](https://arxiv.org/abs/1905.05336)
 93 |     + [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244)[[Pytorch]](https://github.com/xiaolai-sqlai/mobilenetv3)
 94 |     + [High Frequency Residual Learning for Multi-Scale Image Classification](https://arxiv.org/abs/1905.02649)
 95 |     + [Seesaw-Net: Convolution Neural Network With Uneven Group Convolution](https://arxiv.org/abs/1905.03672)
 96 |     + [TextCaps: Handwritten Character Recognition With Very Small Datasets(Apr 2019)](https://arxiv.org/abs/1904.08095)[[Keras]](https://github.com/vinojjayasundara/textcaps/blob/master/textcaps_emnist_bal.py)[WACV]
 97 |     + [Self-Attention Capsule Networks for Image Classification](https://arxiv.org/abs/1904.12483)
 98 |     + [Analytical Moment Regularizer for Gaussian Robust Networks(Apr 2019)](https://arxiv.org/abs/1904.11005)[[Pytorch]](https://github.com/ModarTensai/gaussian-regularizer)
 99 |     + [Deep Sparse Representation-based Classification(Apr 2019)](https://arxiv.org/abs/1904.11093)[[Code]](https://github.com/mahdiabavisani/DSRC)
100 |     + [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond(Apr 2019)](https://arxiv.org/abs/1904.11492)[[Pytorch]](https://github.com/xvjiarui/GCNet)
101 |     + [DenseNet Models for Tiny ImageNet Classification(Apr 2019)](https://arxiv.org/abs/1904.10429)
102 |     + [Deep Anchored Convolutional Neural Networks(Apr 2019)](https://arxiv.org/abs/1904.09764)
103 |     + [Stochastic Region Pooling: Make Attention More Expressive(Apr 2019)](https://arxiv.org/abs/1904.09853)
104 |     + [Attention Augmented Convolutional Networks(Apr 2019)](https://arxiv.org/abs/1904.09925)
105 |     + [High-Resolution Representations for Labeling Pixels and Regions(Apr 2019)](https://arxiv.org/abs/1904.04514)
106 |     + [Deep High-Resolution Representation Learning for Human Pose Estimation(Apr 2019)](https://arxiv.org/abs/1902.09212)[[Pytorch]](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch)   
107 |     + [Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution( Apr 2019)](https://arxiv.org/abs/1904.05049)[[Pytorch]](https://github.com/xiaoketongxue/octconv-pytorch)   
108 |     + [Convolutional Neural Networks with Layer Reuse](https://arxiv.org/abs/1901.09615)
109 |     + [Generalizing discrete convolutions for unstructured point clouds(Apr 2019)](https://arxiv.org/abs/1904.02375)[[Pytorch]](https://github.com/aboulch/ConvPoint)
110 |     + [Hybrid Cosine Based Convolutional Neural Networks(Apr 2019)](https://arxiv.org/abs/1904.01987)
111 |     + [Res2Net: A New Multi-scale Backbone Architecture(Apr 2019)](https://arxiv.org/abs/1904.01169)
112 |     + [G-softmax: Improving Intra-class Compactness and Inter-class Separability of Features(Apr 2019)](https://arxiv.org/abs/1904.04317)
113 |     + [ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification(Apr 2019)](https://arxiv.org/abs/1904.03775)
114 |     + [A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids(Apr 2019)](https://arxiv.org/abs/1904.06008)
115 |     + [Compressing deep neural networks by matrix product operators(Apr 2019)](https://arxiv.org/abs/1904.06194)
116 |     + [Local Relation Networks for Image Recognition( Apr 2019)](https://arxiv.org/abs/1904.11491)
117 |   - 3D   
118 |     + [Resource Efficient 3D Convolutional Neural Networks(Apr 2019)](https://arxiv.org/abs/1904.02422)[[Code]](https://github.com/okankop/Efficient-3DCNNs)
119 | ## 2017
120 |   - CVPR 2017
121 |     + [DenseNet:Densely Connected Convolutional Networks(Aug 2016)](https://arxiv.org/abs/1608.06993)
122 |     
123 | # Graph Neural Networks
124 |   - 2019
125 |     + [Neighborhood Enlargement in Graph Neural Networks(May 2019)](https://arxiv.org/abs/1905.08509)[[Pytorch]](https://github.com/CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network)
126 |     + [A Comparison of Stereo-Matching Cost between Convolutional Neural Network and Census for Satellite Images(May 2019)](https://arxiv.org/abs/1905.09147)
127 | 
128 | # Super-Resolution 
129 | ## 2019
130 |   - ICCV 2019
131 |     + [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://arxiv.org/abs/1908.06382)[[Code]](https://wenlongzhang0724.github.io/Projects/RankSRGAN)
132 |   - CVPR 2019
133 |      + [3D Appearance Super-Resolution with Deep Learning](https://arxiv.org/abs/1906.00925)[[Pytorch]](https://github.com/ofsoundof/3D_Appearance_SR)
134 |      + [Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images](https://arxiv.org/abs/1907.01376)
135 |   - BMVC2019
136 |      + [Gated Multiple Feedback Network for Image Super-Resolution](https://arxiv.org/abs/1907.04253)[[Code]](https://github.com/liqilei/GMFN)
137 |   - Medical
138 |     + [Medical image super-resolution method based on dense blended attention network](https://arxiv.org/abs/1905.05084)
139 |     + [Progressive Generative Adversarial Networks for Medical Image Super resolution(Feb 2019)](https://arxiv.org/abs/1902.02144)
140 |     + [How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach](https://arxiv.org/abs/1901.03419)[ISBI2019]
141 |   - Arxiv
142 |     + [Multi-grained Attention Networks for Single Image Super-Resolution](https://arxiv.org/abs/1909.11937)
143 |     + [s-LWSR: Super Lightweight Super-Resolution Network](https://arxiv.org/abs/1909.10774)
144 |     + [Hybrid Residual Attention Network for Single Image Super Resolution](https://arxiv.org/pdf/1907.05514.pdf)
145 |     + [FC2N: Fully Channel-Concatenated Network for Single Image Super-Resolution](https://arxiv.org/pdf/1907.03221.pdf)
146 |     + [Super-Resolution of PROBA-V Images Using Convolutional Neural Networks](https://arxiv.org/abs/1907.01821)
147 |     + [Edge-Aware Deep Image Deblurring](https://arxiv.org/abs/1907.02282)
148 |     + [Lightweight Image Super-Resolution with Adaptive Weighted Learning Network(Apr 2019)](https://arxiv.org/abs/1904.02358)[[Code]](https://github.com/ChaofWang/AWSRN)
149 |     + [Multi-scale deep neural networks for real image super-resolution(Apr 2019)](https://arxiv.org/abs/1904.10698)
150 |     + [Adaptive Transform Domain Image Super-resolution Via Orthogonally Regularized Deep Networks](https://arxiv.org/abs/1904.10082)
151 | ## 2018
152 |   - Medical
153 |     + [Brain MRI super-resolution using 3D generative adversarial networks(Dec 2018)](https://arxiv.org/abs/1812.11440)[MIDL][3D]
154 |     + [CT-image Super Resolution Using 3D Convolutional Neural Network(Jun 2018)](https://arxiv.org/abs/1806.09074)[3D]
155 |     + [Super-resolution MRI through Deep Learning](https://arxiv.org/abs/1810.06776)
156 |     + [Channel Splitting Network for Single MR Image Super-Resolution](https://arxiv.org/abs/1810.06453)
157 | ## 2017
158 |   - CVPR 2017
159 |     + [Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Coding(May 2017)](https://arxiv.org/abs/1705.02596)
160 |   - MICCAI 2017
161 |     + [Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution](https://arxiv.org/abs/1705.00664)
162 |     + [DOTE: Dual cOnvolutional filTer lEarning for Super-Resolution and Cross-Modality Synthesis in MRI](https://arxiv.org/abs/1706.04954)
163 | # Registration
164 |   - SCI 
165 |     + [3D Convolutional Neural Networks Image Registration Based on Efficient Supervised Learning from Artificial Deformations](https://arxiv.org/abs/1908.10235)[[TMI]]
166 |   - ICCV
167 |     + [Recursive Cascaded Networks for Unsupervised Medical Image Registration](https://arxiv.org/abs/1907.12353)
168 |   - MICCAI2019
169 |     + [Conv2Warp: An unsupervised deformable image registration with continuous convolution and warping](https://arxiv.org/abs/1908.06194)
170 |     + [Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks](https://arxiv.org/abs/1907.10931)[Code](https://github.com/multimodallearning/pdd_net)
171 |     + [Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration](https://arxiv.org/abs/1907.01922)
172 |     + [Unsupervised Deformable Image Registration Using Cycle-Consistent CNN](https://arxiv.org/abs/1907.01319)
173 |     + [Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization(Jul 2019)](https://arxiv.org/abs/1907.01406)
174 |     + [Conditional Segmentation in Lieu of Image Registration(30 Jun)](https://arxiv.org/abs/1907.00438)
175 |   - arxiv
176 |     + [Zero Shot Learning for Multi-Modal Real Time Image Registration](https://arxiv.org/abs/1908.06213)
177 |     + [Automated Image Registration Quality Assessment Utilizing Deep-learning based Ventricle Extraction in Clinical Data(Jul 2019))](https://arxiv.org/abs/1907.00695)
178 |     + [Robust, fast and accurate: a 3-step method for automatic histological image registration(Mar 2019)](https://arxiv.org/abs/1903.12063)
179 |     + [3DRegNet: A Deep Neural Network for 3D Point Registration( Apr 2019)](https://arxiv.org/abs/1904.01701)
180 |     + [Non-Rigid Point Set Registration Networks(Apr 2019)](https://arxiv.org/abs/1904.01428)[[Pytorch]](https://github.com/Lingjing324/PR-Net)   
181 |     + [Automatic Nonrigid Histological Image Registration with Adaptive Multistep Algorithm(Apr 2019)](https://arxiv.org/abs/1904.00982)
182 |     + [Palmprint image registration using convolutional neural networks and Hough transform(Apr 2019)](https://arxiv.org/abs/1904.00579)
183 | # Face
184 |   - 2019
185 |     
186 | # Reconstruction
187 |   - 2019
188 |     + [Recon-GLGAN: A Global-Local context based Generative Adversarial Network for MRI Reconstruction](https://github.com/Bala93/Recon-GLGAN)[[MLMI]]
189 |     +[Fast Dynamic Perfusion and Angiography Reconstruction using an end-to-end 3D Convolutional Neural Network](https://arxiv.org/abs/1908.08947)
190 |     + [Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging](https://arxiv.org/abs/1908.10842)
191 | # Normalization
192 |   - 2019
193 |     [Positional Normalization](https://arxiv.org/abs/1907.04312)
194 | # Survey
195 |   - 2019
196 |     + [AutoML: A Survey of the State-of-the-Art](https://arxiv.org/abs/1908.00709)
197 |     + [A Survey on Deep Learning of Small Sample in Biomedical Image Analysis](https://arxiv.org/abs/1908.00473)
198 |     + [Understanding Deep Learning Techniques for Image Segmentation](https://arxiv.org/abs/1907.06119)
199 |     + [An Attentive Survey of Attention Models(Apr 2019)](https://arxiv.org/abs/1904.02874)
200 |     + [Object Detection in 20 Years: A Survey](https://arxiv.org/abs/1905.05055)
201 |     + [AI in the media and creative industries](https://arxiv.org/abs/1905.04175)
202 |     + [Advancements in Image Classification using Convolutional Neural Network](https://arxiv.org/abs/1905.03288)
203 |     + [A Review on Deep Learning in Medical Image Reconstruction](https://arxiv.org/abs/1906.10643)
204 |     + [A Review of Point Cloud Semantic Segmentation](https://arxiv.org/abs/1908.08854)
205 | # Dataset
206 | ## Medical
207 |   - [All Challenges](https://grand-challenge.org/challenges/)
208 |   - [SPair-71k: A Large-scale Benchmark for Semantic Correspondence](https://arxiv.org/abs/1908.10543)
209 |   - [Image Harmonization Datasets: HCOCO, HAdobe5k, HFlickr, and Hday2night](https://arxiv.org/abs/1908.10526)
210 |   - [Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery](https://arxiv.org/abs/1910.09570)
211 |   - [RWF-2000: An Open Large Scale Video Database for Violence Detection](https://arxiv.org/abs/1911.05913)
212 |   - [A Benchmark for Anomaly Segmentation](https://arxiv.org/abs/1911.11132)[[Code]](https://github.com/hendrycks/anomaly-seg)
213 | ### Brain
214 |   - Brain Tissue Segmentation
215 |     + [MRBrainS2018](https://mrbrains18.isi.uu.nl/)
216 |     + [iSeg-2017 challenge:segmentation of 6-month infant brain tissues](http://iseg2017.web.unc.edu/)
217 |     + [NEATBrainS15](https://www.isi.uu.nl/research/challenges/neatbrains/)
218 |     + [MRBrainS2013](http://mrbrains13.isi.uu.nl/)
219 |     + [NeoBrainS2012](http://neobrains12.isi.uu.nl/mainResults.php)
220 |     
221 |   - MS Lesion Segmentation
222 |     + [2016 MS segmentation challenge](https://portal.fli-iam.irisa.fr/msseg-challenge/overview)
223 |     + [2015 Longitudinal MS Lesion Segmentation Challenge](http://iacl.ece.jhu.edu/index.php/MSChallenge)
224 |     + [2008 MS lesion segmentation challenge ](http://www.ia.unc.edu/MSseg/)
225 |     
226 |   - Multimodal Brain Tumor Segmentation
227 |     + [Multimodal Brain Tumor Segmentation Challenge 2018](https://www.med.upenn.edu/sbia/brats2018.html)
228 |     + [Multimodal Brain Tumor Segmentation Challenge 2017](https://www.med.upenn.edu/sbia/brats2017.html)
229 |     + [Multimodal Brain Tumor Segmentation Challenge 2016](https://www.med.upenn.edu/sbia/brats2016.html)
230 |     
231 |   - Ischemic Stroke Lesion Segmentation
232 |     + [Ischemic Stroke Lesion Segmentation (ISLES) 2018](http://www.isles-challenge.org/)
233 |     + [Ischemic Stroke Lesion Segmentation (ISLES) 2017](http://www.isles-challenge.org/ISLES2017/)
234 |     + [Ischemic Stroke Lesion Segmentation (ISLES) 2016](http://www.isles-challenge.org/ISLES2016/)
235 |     + [Ischemic Stroke Lesion Segmentation (ISLES) 2016](http://www.isles-challenge.org/ISLES2015/)
236 |     
237 |   - White Matter Hyperintensities
238 |     + [WMH Segmentation Challenge 2017](https://wmh.isi.uu.nl/)
239 |     
240 |   - EM segmentation challenge
241 |     + [ISBI Challenge: Segmentation of neuronal structures in EM stacks](http://brainiac2.mit.edu/isbi_challenge/)
242 | 
243 | #  Conference and Journal 
244 | ## Medical Image Processing Conference and Journal 
245 | ### Conference
246 |  [MICCAI](https://www.miccai2019.org/)  
247 |  Submission Deadline：2018-03-02  
248 |  Accept/Reject Notification：  
249 |  
250 |  [ISBI](https://biomedicalimaging.org/2019/)  
251 |  Submission Deadline：Oct 16, 2018  
252 |  Accept/Reject Notification：Dec 18, 2018 
253 |  
254 |  [IPMI](https://ipmi2019.cse.ust.hk/)  
255 |  Submission Deadline:13 December 2018  
256 |  Accept/Reject Notification：25 February 2019  
257 |  
258 |  [EMBC](https://embc.embs.org/2019/)[CCF C]     
259 |  Submission Deadline:February 19, 2019   
260 |  Accept/Reject Notification：April 12, 2019   
261 |  
262 |  [BIBM2019](http://ieeebibm.org/BIBM2019/CallPapers.html)[CCF B]    
263 |  Submission Deadline: Aug 17, 2019  
264 |  Accept/Reject Notification：Oct 1, 2019  
265 |  
266 |  [ICASSP](https://2019.ieeeicassp.org/)[CCF B]   
267 |  Submission Deadline:October 29  
268 |  Accept/Reject Notification：February 1  
269 |  
270 |  [MIDL](http://2019.midl.io/important-dates/)    
271 |  Submission Deadline:17 December 2018   
272 |  Accept/Reject Notification：27 February 2019   
273 |  
274 | ### Journal
275 | [Medical Image Analysis,MIA](https://www.journals.elsevier.com/medical-image-analysis/)   
276 | [IEEE Transactions on Medical Imaging,TMI](https://www.baidu.com/link?url=mNdVbByvlcwxQgR23r2xFB9IXlQcufNo74D-DiXCnUottAlR7ihw-ilrPwYxFrRuAXkZsH-SuM9L6aerUD_LqtKvI7H0cHIwwsaSygbj9H3&wd=&eqid=b63236c700071acf000000025cdbe66d)  
277 | ## Image Processing Conference and Journal 
278 | ### Conference  
279 |  [CVPR](http://cvpr2019.thecvf.com/)   
280 |  Submission Deadline：2018-11-16
281 |  Accept/Reject Notification： 2019-03-02
282 |  
283 |  [ECCV](https://www.baidu.com/link?url=Ox_E6jGDljZO0FzW9AvYB5y_Eco2o2MgRFKkNkNc10I-DDKcILxQ6urkA9ItQ1Lj&wd=&eqid=d88692430019b620000000035cda6907)  
284 |  Submission Deadline：2018-03-14    
285 |  Accept/Reject Notification：2018-07-01   
286 |  
287 |  [ICCV](http://iccv2019.thecvf.com)
288 |  Submission Deadline：2019-03-15     
289 |  Accept/Reject Notification2019-06-07   
290 |  
291 |  ICML    
292 |  Submission Deadline：2019-01-18       
293 |  
294 |  ICLR  
295 |  Submission Deadline：2018-09-27      
296 |  
297 |  AAAI     
298 |  Submission Deadline：2018-08-30     
299 |  Accept/Reject Notification：2018-11-01   
300 |  
301 |  NeurIPS    
302 |  Submission Deadline：May 23, 2019    
303 |  Accept/Reject Notification：	Dec 2 - Dec 8, 2019    
304 |  
305 |  IJCAI    
306 |  Submission Deadline：2019-02-25   
307 |  Accept/Reject Notification：	2019-05-09    
308 |  
309 |  BMVC   
310 |  BMVC2019   
311 |  received 1008 submissions, of which 815 were valid. 
312 |  Of these, a total of 231 papers were accepted 
313 |  (38 as Oral Presentations, 193 as Poster Presentations).
314 |  This amounts to a 28% acceptance rate
315 |  ### Journal
316 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # AI-News 2020
  2 | - [x] [AI-News 2019](https://github.com/xiaoketongxue/AI-News/blob/master/CV2019.md)
  3 | - [x] [CV](#CV)
  4 | - [x] [NLP](https://github.com/xiaoketongxue/AI-News/blob/master/NLP2020.md)  
  5 | - [x] [Recommendation](https://github.com/xiaoketongxue/AI-News/blob/master/Recommendation.md)    
  6 | - [x] [Data-Competition](https://github.com/xiaoketongxue/AI-News/blob/master/Data-Competition2020.md)  []()
  7 | - [x] [Other-Awesome](https://github.com/xiaoketongxue/AI-News/blob/master/Other_Awesome.md)
  8 | 
  9 | # CV
 10 | - [x] [Semantic Segmentation](#Semantic-Segmentation)
 11 | - [x] [Medical Segmentation](#Medical-Segmentation)
 12 | - [x] [Other Segmentation](#Other-Segmentation)
 13 | - [x] [Re-Identification](#Panoptic-Segmentation)
 14 | - [x] [text detection and OCR](#Text-detection-and-OCR)
 15 | - [x] [Classification](#Classification)
 16 | - [x] [Super-Resolution](#Super-Resolution)
 17 | - [x] [Detection](#Detection)
 18 | 
 19 | ## Semantic Segmentation
 20 | ### AAAI
 21 |   - AAAI
 22 |     + [Segmenting Medical MRI via Recurrent Decoding Cell](https://arxiv.org/abs/1911.09401)[[Code]](https://github.com/beijixiong3510/OWM)
 23 |     + [F3Net: Fusion, Feedback and Focus for Salient Object Detection](https://arxiv.org/abs/1911.11445)[[Code]](https://github.com/weijun88/F3Net)
 24 |     + [An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation](https://arxiv.org/abs/1912.08954)
 25 |     + [JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds](https://arxiv.org/abs/1912.09654)[Code](https://github.com/dlinzhao/JSNet)
 26 | ### WACV
 27 |   - WACV
 28 |     + [Print Defect Mapping with Semantic Segmentation](https://arxiv.org/abs/2001.10111)
 29 | ### arxiv
 30 |   - Weakly Supervised
 31 |     + [Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Inputs](https://arxiv.org/abs/2001.09540)
 32 |   - Supervised  
 33 |     + [Gated Path Selection Network for Semantic Segmentation](https://arxiv.org/abs/2001.06819)  
 34 |     + [MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding](https://arxiv.org/abs/2001.03712)  
 35 |     + [HMANet: Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images](https://arxiv.org/abs/2001.02870)  
 36 |     + [Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation](https://arxiv.org/abs/2002.02255)[TMI]
 37 |     + [Universal Semantic Segmentation for Fisheye Urban Driving Images](https://arxiv.org/abs/2002.03736)[augmentation ]
 38 |     + [Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation](https://arxiv.org/abs/2002.03989)
 39 |     + [High-Order Paired-ASPP Networks for Semantic Segmenation](https://arxiv.org/abs/2002.07371)
 40 |   - Other
 41 |     + [SOLAR: Second-Order Loss and Attention for Image Retrieval](https://arxiv.org/abs/2001.08972)
 42 |   - Survey and Dataset
 43 |     + [Image Segmentation Using Deep Learning: A Survey](https://arxiv.org/abs/2001.05566)
 44 |     + [Evolution of Image Segmentation using Deep Convolutional Neural Network:  A Survey](https://arxiv.org/abs/2001.04074)
 45 |     + [Towards Open-Set Semantic Segmentation of Aerial Images](https://arxiv.org/abs/2001.10063)
 46 |     + [VIFB: A Visible and Infrared Image Fusion Benchmark](https://arxiv.org/abs/2002.03322)
 47 | 
 48 | ## Medical Segmentation
 49 | ### ISBI
 50 |   - Attention
 51 |     + [Complementary Network with Adaptive Receptive Fields for Melanoma Segmentation](https://arxiv.org/abs/2001.03893)[[Code]](https://github.com/Guo-Xiaoqing/Skin-Seg)   
 52 |     + [Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention](https://arxiv.org/abs/2001.03857)  
 53 |     + [Stan: Small tumor-aware network for breast ultrasound image segmentation](https://arxiv.org/abs/2002.01034)
 54 | ### arxiv
 55 |   -  Distillation 
 56 |     + [Knowledge Distillation for Brain Tumor Segmentation](https://arxiv.org/abs/2002.03688)
 57 |  ### SCI
 58 |   - TMI
 59 |     + [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://arxiv.org/abs/2001.03111)
 60 | 
 61 | ### arxiv
 62 |   - Neural Architecture Search  
 63 |     + [ENAS U-Net: Evolutionary Neural Architecture Search for Retinal Vessel Segmentation](https://arxiv.org/abs/2001.06678)
 64 |   - Adversarial and unsupervised and Weakly Supervised
 65 |     + [Abdominal multi-organ segmentation with cascaded convolutional and adversarial deep networks](https://arxiv.org/abs/2001.09521)
 66 |     + [Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives](https://arxiv.org/abs/2001.09501)
 67 |     + [e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation](https://arxiv.org/abs/2001.09313)
 68 |     + [Weakly Supervised Lesion Co-segmentation on CT Scans](https://arxiv.org/abs/2001.09174)
 69 |     + [Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation](https://arxiv.org/abs/2001.08590)
 70 |     + [A Two-Stream Meticulous Processing Network for Retinal Vessel Segmentation](https://arxiv.org/abs/2001.05829)
 71 |     + [An Unsupervised Learning Model for Medical Image Segmentation](https://arxiv.org/abs/2001.10155)
 72 |   - Attention  
 73 |     + [RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation](https://arxiv.org/abs/2001.09138)
 74 |     + [SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation](https://arxiv.org/abs/2001.07645)
 75 |     + [Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net](https://arxiv.org/abs/2001.10061)
 76 |     + [Edge-Gated CNNs for Volumetric Semantic Segmentation of Medical Images](https://arxiv.org/list/cs.CV/recent)[[underview MIDL]]
 77 |     + [Liver Segmentation in Abdominal CT Images via Auto-Context Neural Network and Self-Supervised Contour Attention](https://arxiv.org/abs/2002.05895)
 78 | 
 79 |   - Survey and Benchmark
 80 |     + [VerSe: A Vertebrae Labelling and Segmentation Benchmark](https://arxiv.org/abs/2001.09193)
 81 |     + [Deep Learning in Medical Ultrasound Image Segmentation: a Review](https://arxiv.org/abs/2002.07703)
 82 |    
 83 | 
 84 | ## Other Segmentation
 85 | ### ICCV
 86 |   - Zero-Shot Video Segmentation  
 87 |     + [Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks](https://arxiv.org/abs/2001.06807)
 88 | ### arxiv
 89 |   - Video
 90 |     + [Fast Video Object Segmentation using the Global Context Module](https://arxiv.org/abs/2001.11243)[Attention]
 91 |   - Instance  
 92 |     + [PatchPerPix for Instance Segmentation](https://arxiv.org/abs/2001.07626)
 93 | 
 94 | ## Re-Identification
 95 |   ## 2019
 96 |    - Awesome      
 97 |      + [Awesome Person Re-identification (Person ReID)](https://github.com/bismex/Awesome-person-re-identification)
 98 |   ## AAAI
 99 |    -2020
100 |      + [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://arxiv.org/abs/2002.04114)
101 |   ## arxiv  
102 |    - 2020  
103 |      + [VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification](https://arxiv.org/abs/2001.07354)
104 |      + [Learning Diverse Features with Part-Level Resolution for Person Re-Identification](https://arxiv.org/abs/2001.07442)
105 |      + [An Implicit Attention Mechanism for Deep Learning Pedestrian Re-identification Frameworks](https://arxiv.org/abs/2001.11267)[[Code]](https://github.com/Ehsan-Yaghoubi/reid-strong-baseline)
106 |      + [Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention](https://arxiv.org/abs/2002.02256)
107 |      + [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://arxiv.org/abs/2002.02295)[TPAMI]
108 |      + [An Empirical Study of Person Re-Identification with Attributes](https://arxiv.org/abs/2002.03752)
109 |      + [Diversity-Achieving Slow-DropBlock Network for Person Re-Identification](https://arxiv.org/abs/2002.04414)
110 |      + [Intra-Camera Supervised Person Re-Identification](https://arxiv.org/abs/2002.05046)
111 |     
112 | ## Text detection and OCR
113 | ### ICASSP
114 |   - 2020 
115 |     + [Efficient Scene Text Detection with Textual Attention Tower](https://arxiv.org/abs/2002.03741)
116 | ### arxiv
117 |   - 2020
118 |     + [Scene Text Recognition With Finer Grid Rectification](https://arxiv.org/abs/2001.09389)
119 |     + [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://arxiv.org/abs/2001.09099)
120 |     + [Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images](https://arxiv.org/abs/2002.06423)
121 |     
122 | ## Classification
123 | ### arxiv
124 |   - 2020
125 |     + [Depthwise-STFT based separable Convolutional Neural Networks](https://arxiv.org/abs/2001.09912)[[ICASSP]]  
126 | ## CCF
127 | ICCV: 23%-30%  
128 | CVPR: 24%-30%  
129 | ECCV: 26%-28%  
130 | ICME：30%  
131 | ACCV: 26%-29%  
132 | BMVC: 29%-35%  
133 | ICLR: ~30%  
134 | MICCAI: ~30%  
135 | ICPR: 48%-56%  
136 | COLT: 26%-52%  
137 | ICML: 25%-32%  
138 | IJCAI: 24%-34%  
139 | ICIP：50%  
140 | 
141 |      
142 |     
143 | 


--------------------------------------------------------------------------------
/Recommendation.md:
--------------------------------------------------------------------------------
 1 | # # Recommendation2020
 2 | - [x] [CTR](#CTR)
 3 | - [x] [Recommender Systems](#Recommender-Systems)
 4 | 
 5 | ## CTR
 6 |   - 2020
 7 |     + [DeepCTR](https://github.com/shenweichen/DeepCTR)
 8 |   - 2017 
 9 |     + [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/abs/1909.10351https://www.ijcai.org/Proceedings/2017/0239.pdf)
10 |   
11 | ## Recommender Systems
12 |   - 2020
13 |     + [A[]()
14 | 


--------------------------------------------------------------------------------
/Way.md:
--------------------------------------------------------------------------------
  1 | README
  2 | ===========================
  3 | 该文件用来测试和展示书写README的各种markdown语法。GitHub的markdown语法在标准的markdown语法基础上做了扩充，称之为`GitHub Flavored Markdown`。简称`GFM`，GFM在GitHub上有广泛应用，除了README文件外，issues和wiki均支持markdown语法。
  4 | 
  5 | ****
  6 | 	
  7 | |Author|果冻虾仁|
  8 | |---|---
  9 | |E-mail|Jelly.K.Wang@qq.com
 10 | 
 11 | 
 12 | ****
 13 | ## 目录
 14 | * [横线](#横线)
 15 | * [标题](#标题)
 16 | * [文本](#文本)
 17 |     * 普通文本
 18 |     * 单行文本
 19 |     * 多行文本
 20 |     * 文字高亮
 21 |     * 换行
 22 |     * 斜体
 23 |     * 粗体
 24 |     * 删除线
 25 | * [图片](#图片)
 26 |     * 来源于网络的图片
 27 |     * GitHub仓库中的图片
 28 | * [链接](#链接) 
 29 |     * 文字超链接
 30 |         *  链接外部URL
 31 |         *  链接本仓库里的URL
 32 |     *  锚点
 33 |     * [图片链接](#图片链接)
 34 | * [列表](#列表)
 35 |     * 无序列表
 36 |     * 有序列表
 37 |     * 复选框列表
 38 | * [块引用](#块引用)
 39 | * [代码高亮](#代码高亮)
 40 | * [表格](#表格) 
 41 | * [表情](#表情)
 42 | * [diff语法](#diff语法)
 43 | 
 44 | ### 横线
 45 | -----------
 46 | ***、---、___可以显示横线效果
 47 | 
 48 | ***
 49 | ---
 50 | ___
 51 | 
 52 | 
 53 | 
 54 | 标题
 55 | ------
 56 | 
 57 | # 一级标题  
 58 | ## 二级标题  
 59 | ### 三级标题  
 60 | #### 四级标题  
 61 | ##### 五级标题  
 62 | ###### 六级标题  
 63 | 
 64 | 
 65 | 文本
 66 | ------
 67 | ### 普通文本
 68 | 这是一段普通的文本
 69 | ### 单行文本
 70 |     Hello,大家好，我是果冻虾仁。
 71 | 在一行开头加入1个Tab或者4个空格。
 72 | ### 文本块
 73 | #### 语法1
 74 | 在连续几行的文本开头加入1个Tab或者4个空格。
 75 | 
 76 |     欢迎到访
 77 |     很高兴见到您
 78 |     祝您，早上好，中午好，下午好，晚安
 79 | 
 80 | #### 语法2
 81 | 使用一对各三个的反引号：
 82 | ```
 83 | 欢迎到访
 84 | 我是C++码农
 85 | 你可以在知乎、CSDN、简书搜索【果冻虾仁】找到我
 86 | ```
 87 | 该语法也可以实现代码高亮，见[代码高亮](#代码高亮)
 88 | ### 文字高亮
 89 | 文字高亮功能能使行内部分文字高亮，使用一对反引号。
 90 | 语法：
 91 | ```
 92 | `linux` `网络编程` `socket` `epoll` 
 93 | ```
 94 | 效果：`linux` `网络编程` `socket` `epoll`
 95 | 
 96 | 也适合做一篇文章的tag
 97 | #### 换行
 98 | 直接回车不能换行，  
 99 | 可以在上一行文本后面补两个空格，  
100 | 这样下一行的文本就换行了。
101 | 
102 | 或者就是在两行文本直接加一个空行。
103 | 
104 | 也能实现换行效果，不过这个行间距有点大。
105 | #### 斜体、粗体、删除线
106 | 
107 | |语法|效果|
108 | |----|-----|
109 | |`*斜体1*`|*斜体1*|
110 | |`_斜体2_`| _斜体2_|
111 | |`**粗体1**`|**粗体1**|
112 | |`__粗体2__`|__粗体2__|
113 | |`这是一个 ~~删除线~~`|这是一个 ~~删除线~~|
114 | |`***斜粗体1***`|***斜粗体1***|
115 | |`___斜粗体2___`|___斜粗体2___|
116 | |`***~~斜粗体删除线1~~***`|***~~斜粗体删除线1~~***|
117 | |`~~***斜粗体删除线2***~~`|~~***斜粗体删除线2***~~|
118 | 
119 |     斜体、粗体、删除线可混合使用
120 | 
121 | 图片
122 | ------
123 | 基本格式：
124 | ```
125 | ![alt](URL title)
126 | ```
127 | alt和title即对应HTML中的alt和title属性（都可省略）：
128 | - alt表示图片显示失败时的替换文本
129 | - title表示鼠标悬停在图片时的显示文本（注意这里要加引号）
130 | 
131 | URL即图片的url地址，如果引用本仓库中的图片，直接使用**相对路径**就可了，如果引用其他github仓库中的图片要注意格式，即：`仓库地址/raw/分支名/图片路径`，如：
132 | ```
133 | https://github.com/guodongxiaren/ImageCache/raw/master/Logo/foryou.gif
134 | ```
135 | 
136 | |#|语法|效果|
137 | |---|---|----
138 | |1|`![baidu](http://www.baidu.com/img/bdlogo.gif "百度logo")`|![baidu](http://www.baidu.com/img/bdlogo.gif "百度logo")
139 | |2|`![][foryou]`|![][foryou]
140 | 
141 | 注意例2的写法使用了**URL标识符**的形式，在[链接](#链接)一节有介绍。
142 | >在文末有foryou的定义：
143 | ```
144 | [foryou]:https://github.com/guodongxiaren/ImageCache/raw/master/Logo/foryou.gif
145 | ```
146 | 
147 | 链接
148 | ------
149 | ### 链接外部URL
150 | 
151 | |#|语法|效果|
152 | |---|----|-----|
153 | |1|`[我的博客](http://blog.csdn.net/guodongxiaren "悬停显示")`|[我的博客](http://blog.csdn.net/guodongxiaren "悬停显示")|
154 | |2|`[我的知乎][zhihu] `|[我的知乎][zhihu] |
155 | 
156 | 语法2由两部分组成：
157 | - 第一部分使用两个中括号，[ ]里的标识符（本例中zhihu），可以是数字，字母等的组合，标识符上下对应就行了（**姑且称之为URL标识符**）
158 | - 第二部分标记实际URL。
159 | 
160 | >使用URL标识符能达到复用的目的，一般把全文所有的URL标识符统一放在文章末尾，这样看起来比较干净。
161 | >>URL标识符是我起的名字，不知道是否准确。囧。。
162 | 
163 | ### 链接本仓库里的URL
164 | 
165 | |语法|效果|
166 | |----|-----|
167 | |`[我的简介](/example/profile.md)`|[我的简介](/example/profile.md)|
168 | |`[example](./example)`|[example](./example)|
169 | 
170 | ### 图片链接
171 | 给图片加链接的本质是混合图片显示语法和普通的链接语法。普通的链接中[ ]内部是链接要显示的文本，而图片链接[ ]里面则是要显示的图片。  
172 | 直接混合两种语法当然可以，但是十分啰嗦，为此我们可以使用URL标识符的形式。
173 | 
174 | |#|语法|效果|
175 | |---|----|:---:|
176 | |1|`[![weibo-logo]](http://weibo.com/linpiaochen)`|[![weibo-logo]](http://weibo.com/linpiaochen)|
177 | |2|`[![](/img/zhihu.png "我的知乎，欢迎关注")][zhihu]`|[![](/img/zhihu.png "我的知乎，欢迎关注")][zhihu]|
178 | |3|`[![csdn-logo]][csdn]`|[![csdn-logo]][csdn]|
179 | 
180 | 因为图片本身和链接本身都支持URL标识符的形式，所以图片链接也可以很简洁（见例3）。  
181 | 注意，此时鼠标悬停时显示的文字是图片的title，而非链接本身的title了。
182 | > 本文URL标识符都放置于文末
183 | 
184 | ### 锚点
185 | 其实呢，每一个标题都是一个锚点，和HTML的锚点（`#`）类似，比如我们 
186 | 
187 | |语法|效果|
188 | |---|---|
189 | |`[回到顶部](#readme)`|[回到顶部](#readme)|
190 | 
191 | 不过要注意，标题中的英文字母都被转化为**小写字母**了。
192 | > 以前GitHub对中文支持的不好，所以中文标题不能正确识别为锚点，但是现在已经没问题啦！
193 | 
194 | ## 列表
195 | ### 无序列表
196 | #### 语法
197 | ```
198 | * 昵称：果冻虾仁
199 | - 别名：隔壁老王
200 | * 英文名：Jelly
201 | ```
202 | #### 效果
203 | * 昵称：果冻虾仁
204 | - 别名：隔壁老王
205 | * 英文名：Jelly
206 | 
207 | ### 多级无序列表
208 | #### 语法
209 | ```
210 | * 编程语言
211 |     * 脚本语言
212 |         * Python
213 | ```
214 | #### 效果
215 | * 编程语言
216 |     * 脚本语言
217 |         * Python
218 | 
219 | ### 一级有序列表
220 | #### 语法
221 | 就是在数字后面加一个点，再加一个空格。不过看起来起来可能不够明显。 
222 | ```
223 | 面向对象的三个基本特征：
224 | 
225 | 1. 封装
226 | 2. 继承
227 | 3. 多态
228 | ```
229 | 
230 | #### 效果
231 | 面向对象的三个基本特征：
232 | 
233 | 1. 封装
234 | 2. 继承
235 | 3. 多态
236 | 
237 | 
238 | ### 多级有序列表
239 | 和无序列表一样，有序列表也有多级结构。
240 | #### 语法
241 | ```
242 | 1. 这是一级的有序列表，数字1还是1
243 |    1. 这是二级的有序列表，阿拉伯数字在显示的时候变成了罗马数字
244 |       1. 这是三级的有序列表，数字在显示的时候变成了英文字母
245 | ```
246 | 
247 | #### 效果
248 | 
249 | 1. 这是一级的有序列表，数字1还是1
250 |    1. 这是二级的有序列表，阿拉伯数字在显示的时候变成了罗马数字
251 |       1. 这是三级的有序列表，数字在显示的时候变成了英文字母
252 | 	 
253 | 
254 | ### 复选框列表
255 | #### 语法
256 | ```
257 | - [x] 需求分析
258 | - [x] 系统设计
259 | - [x] 详细设计
260 | - [ ] 编码
261 | - [ ] 测试
262 | - [ ] 交付
263 | ```
264 | #### 效果
265 | 
266 | - [x] 需求分析
267 | - [x] 系统设计
268 | - [x] 详细设计
269 | - [ ] 编码
270 | - [ ] 测试
271 | - [ ] 交付
272 | 
273 | 您可以使用这个功能来标注某个项目各项任务的完成情况。
274 | > Tip:
275 | >> 在GitHub的**issue**中使用该语法是可以实时点击复选框来勾选或解除勾选的，而无需修改issue原文。
276 | 
277 | ## 块引用
278 | 
279 | ### 常用于引用文本
280 | #### 文本摘自《深入理解计算机系统》P27
281 | 　令人吃惊的是，在哪种字节顺序是合适的这个问题上，人们表现得非常情绪化。实际上术语“little endian”（小端）和“big endian”（大端）出自Jonathan Swift的《格利佛游记》一书，其中交战的两个派别无法就应该从哪一端打开一个半熟的鸡蛋达成一致。因此，争论沦为关于社会政治的争论。只要选择了一种规则并且始终如一的坚持，其实对于哪种字节排序的选择都是任意的。
282 | > **“端”（endian）的起源**  
283 | 以下是Jonathan Swift在1726年关于大小端之争历史的描述：  
284 | “……下面我要告诉你的是，Lilliput和Blefuscu这两大强国在过去36个月里一直在苦战。战争开始是由于以下的原因：我们大家都认为，吃鸡蛋前，原始的方法是打破鸡蛋较大的一端，可是当今的皇帝的祖父小时候吃鸡蛋，一次按古法打鸡蛋时碰巧将一个手指弄破了，因此他的父亲，当时的皇帝，就下了一道敕令，命令全体臣民吃鸡蛋时打破较小的一端，违令者重罚。”
285 | 
286 | ### 块引用有多级结构
287 | #### 语法
288 | ```
289 | > 数据结构
290 | >> 树
291 | >>> 二叉树
292 | >>>> 平衡二叉树
293 | >>>>> 满二叉树
294 | ```
295 | #### 效果
296 | > 数据结构
297 | >> 树
298 | >>> 二叉树
299 | >>>> 平衡二叉树
300 | >>>>> 满二叉树
301 | 
302 | 代码高亮
303 | ----------
304 | 
305 | ### 语法
306 | 在三个反引号后面加上编程语言的名字，另起一行开始写代码，最后一行再加上三个反引号。
307 | 
308 | ### 效果
309 | ```Java
310 | public static void main(String[]args){} //Java
311 | ```
312 | ```c
313 | int main(int argc, char *argv[]) //C
314 | ```
315 | ```Bash
316 | echo "hello GitHub" #Bash
317 | ```
318 | ```javascript
319 | document.getElementById("myH1").innerHTML="Welcome to my Homepage"; //javascipt
320 | ```
321 | ```cpp
322 | string &operator+(const string& A,const string& B) //cpp
323 | ```
324 | 表格
325 | --------
326 | 
327 | 表头1  | 表头2|
328 | --------- | --------|
329 | 表格单元  | 表格单元 |
330 | 表格单元  | 表格单元 |
331 | 
332 | | 表头1  | 表头2|
333 | | ---------- | -----------|
334 | | 表格单元   | 表格单元   |
335 | | 表格单元   | 表格单元   |
336 | 
337 | ### 对齐
338 | 表格可以指定对齐方式
339 | 
340 | | 左对齐 | 居中  | 右对齐 |
341 | | :------------ |:---------------:| -----:|
342 | | col 3 is      | some wordy text | $1600 |
343 | | col 2 is      | centered        |   $12 |
344 | | zebra stripes | are neat        |    $1 |
345 | 
346 | ### 混合其他语法
347 | 表格单元中的内容可以和其他大多数GFM语法配合使用，如：  
348 | #### 使用普通文本的删除线，斜体等效果
349 | 
350 | | 名字 | 描述 |
351 | | ------------- | ----------- |
352 | | Help      | ~~Display the~~ help window.|
353 | | Close     | _Closes_ a window     |
354 | 
355 | #### 表格中嵌入图片（链接）
356 | 其实前面介绍图片显示、图片链接的时候为了清晰就是放在在表格中显示的。
357 | 
358 | | 图片 | 描述 |
359 | | ---- | ---- |
360 | |![baidu][baidu-logo] | 百度|
361 | 
362 | 表情
363 | ----------
364 | Github的Markdown语法支持添加emoji表情，输入不同的符号码（两个冒号包围的字符）可以显示出不同的表情。
365 | 
366 | 比如`:blush:`，可以显示:blush:。
367 | 
368 | 具体每一个表情的符号码，可以查询GitHub的官方网页[http://www.emoji-cheat-sheet.com](http://www.emoji-cheat-sheet.com)。
369 | 
370 | 但是这个网页每次都打开**奇慢**。。所以我整理到了本repo中，大家可以直接在此查看[emoji](./emoji.md)。
371 | 
372 | diff语法
373 | ---------
374 | 版本控制的系统中都少不了diff的功能，即展示一个文件内容的增加与删除。
375 | GFM中可以显示的展示diff效果。使用绿色表示新增，红色表示删除。
376 | #### 语法
377 | 其语法与代码高亮类似，只是在三个反引号后面写diff，
378 | 并且其内容中，以 `+ `开头表示新增，`- `开头表示删除。
379 | 
380 | #### 效果
381 | 
382 | ```diff
383 | + 鸟宿池边树，僧敲月下门
384 | - 鸟宿池边树，僧推月下门
385 | ```
386 | 
387 | 
388 | 
389 | --------------------------------
390 | [csdn]:http://blog.csdn.net/guodongxiaren "我的博客"
391 | [zhihu]:https://www.zhihu.com/people/jellywong "我的知乎，欢迎关注"
392 | [weibo]:http://weibo.com/linpiaochen
393 | [baidu-logo]:http://www.baidu.com/img/bdlogo.gif "百度logo"
394 | [weibo-logo]:/img/weibo.png "点击图片进入我的微博"
395 | [csdn-logo]:/img/csdn.png "我的CSDN博客"
396 | [foryou]:https://github.com/guodongxiaren/ImageCache/raw/master/Logo/foryou.gif
397 | 


--------------------------------------------------------------------------------