├── DATASET.md ├── FINETUNE.md ├── INSTALL.md ├── LICENSE ├── MODEL_ZOO.md ├── README.md ├── alphaction ├── __init__.py ├── config │ ├── __init__.py │ ├── defaults.py │ └── paths_catalog.py ├── csrc │ ├── ROIAlign3d.h │ ├── ROIPool3d.h │ ├── SigmoidFocalLoss.h │ ├── SoftmaxFocalLoss.h │ ├── cpu │ │ └── vision.h │ ├── cuda │ │ ├── ROIAlign3d_cuda.cu │ │ ├── ROIPool3d_cuda.cu │ │ ├── SigmoidFocalLoss_cuda.cu │ │ ├── SoftmaxFocalLoss_cuda.cu │ │ └── vision.h │ └── vision.cpp ├── dataset │ ├── __init__.py │ ├── build.py │ ├── collate_batch.py │ ├── datasets │ │ ├── __init__.py │ │ ├── ava.py │ │ ├── concat_dataset.py │ │ └── evaluation │ │ │ ├── __init__.py │ │ │ └── ava │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── ava_eval.py │ │ │ └── pascal_evaluation │ │ │ ├── __init__.py │ │ │ ├── label_map_util.py │ │ │ ├── metrics.py │ │ │ ├── np_box_list.py │ │ │ ├── np_box_list_ops.py │ │ │ ├── np_box_mask_list.py │ │ │ ├── np_box_mask_list_ops.py │ │ │ ├── np_box_ops.py │ │ │ ├── np_mask_ops.py │ │ │ ├── object_detection_evaluation.py │ │ │ ├── per_image_evaluation.py │ │ │ └── standard_fields.py │ ├── samplers │ │ ├── __init__.py │ │ ├── distributed.py │ │ ├── grouped_batch_sampler.py │ │ └── iteration_based_batch_sampler.py │ └── transforms │ │ ├── __init__.py │ │ ├── build.py │ │ ├── object_transforms.py │ │ └── video_transforms.py ├── engine │ ├── __init__.py │ ├── inference.py │ └── trainer.py ├── layers │ ├── __init__.py │ ├── batch_norm.py │ ├── roi_align_3d.py │ ├── roi_pool_3d.py │ ├── sigmoid_focal_loss.py │ └── softmax_focal_loss.py ├── modeling │ ├── __init__.py │ ├── backbone │ │ ├── __init__.py │ │ ├── backbone.py │ │ ├── i3d.py │ │ └── slowfast.py │ ├── common_blocks.py │ ├── detector │ │ ├── __init__.py │ │ └── action_detector.py │ ├── nonlocal_block.py │ ├── poolers.py │ ├── registry.py │ ├── roi_heads │ │ ├── __init__.py │ │ ├── action_head │ │ │ ├── IA_structure.py │ │ │ ├── __init__.py │ │ │ ├── action_head.py │ │ │ ├── inference.py │ │ │ ├── loss.py │ │ │ ├── metric.py │ │ │ ├── roi_action_feature_extractor.py │ │ │ └── roi_action_predictors.py │ │ └── roi_heads_3d.py │ └── utils.py ├── solver │ ├── __init__.py │ ├── build.py │ └── lr_scheduler.py ├── structures │ ├── __init__.py │ ├── bounding_box.py │ └── memory_pool.py └── utils │ ├── IA_helper.py │ ├── __init__.py │ ├── c2_model_loading.py │ ├── checkpoint.py │ ├── comm.py │ ├── logger.py │ ├── metric_logger.py │ ├── model_serialization.py │ ├── random_seed.py │ ├── registry.py │ └── video_decode.py ├── data ├── __init__.py ├── ava.py ├── ava_eval.py └── transforms.py ├── datasets.py ├── engine_for_finetuning.py ├── figs └── videomae.png ├── modeling_finetune.py ├── optim_factory.py ├── run_class_finetuning.py ├── scripts └── ava │ ├── videomae_vit_base_k400_pretrain+finetune │ └── run.sh │ ├── videomae_vit_base_k400_pretrain │ └── run.sh │ ├── videomae_vit_huge_k400_pretrain+finetune │ └── run.sh │ ├── videomae_vit_huge_k400_pretrain │ └── run.sh │ ├── videomae_vit_large_k400_pretrain+finetune │ └── run.sh │ ├── videomae_vit_large_k400_pretrain │ └── run.sh │ ├── videomae_vit_small_k400_pretrain+finetune │ └── run.sh │ └── videomae_vit_small_k400_pretrain │ └── run.sh └── utils.py /DATASET.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/DATASET.md -------------------------------------------------------------------------------- /FINETUNE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/FINETUNE.md -------------------------------------------------------------------------------- /INSTALL.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/INSTALL.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/LICENSE -------------------------------------------------------------------------------- /MODEL_ZOO.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/MODEL_ZOO.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/README.md -------------------------------------------------------------------------------- /alphaction/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/config/__init__.py: -------------------------------------------------------------------------------- 1 | from .defaults import _C as cfg 2 | -------------------------------------------------------------------------------- /alphaction/config/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/config/defaults.py -------------------------------------------------------------------------------- /alphaction/config/paths_catalog.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/config/paths_catalog.py -------------------------------------------------------------------------------- /alphaction/csrc/ROIAlign3d.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/ROIAlign3d.h -------------------------------------------------------------------------------- /alphaction/csrc/ROIPool3d.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/ROIPool3d.h -------------------------------------------------------------------------------- /alphaction/csrc/SigmoidFocalLoss.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/SigmoidFocalLoss.h -------------------------------------------------------------------------------- /alphaction/csrc/SoftmaxFocalLoss.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/SoftmaxFocalLoss.h -------------------------------------------------------------------------------- /alphaction/csrc/cpu/vision.h: -------------------------------------------------------------------------------- 1 | #pragma once 2 | #include 3 | -------------------------------------------------------------------------------- /alphaction/csrc/cuda/ROIAlign3d_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/cuda/ROIAlign3d_cuda.cu -------------------------------------------------------------------------------- /alphaction/csrc/cuda/ROIPool3d_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/cuda/ROIPool3d_cuda.cu -------------------------------------------------------------------------------- /alphaction/csrc/cuda/SigmoidFocalLoss_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/cuda/SigmoidFocalLoss_cuda.cu -------------------------------------------------------------------------------- /alphaction/csrc/cuda/SoftmaxFocalLoss_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/cuda/SoftmaxFocalLoss_cuda.cu -------------------------------------------------------------------------------- /alphaction/csrc/cuda/vision.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/cuda/vision.h -------------------------------------------------------------------------------- /alphaction/csrc/vision.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/csrc/vision.cpp -------------------------------------------------------------------------------- /alphaction/dataset/__init__.py: -------------------------------------------------------------------------------- 1 | from .build import make_data_loader 2 | -------------------------------------------------------------------------------- /alphaction/dataset/build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/build.py -------------------------------------------------------------------------------- /alphaction/dataset/collate_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/collate_batch.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/__init__.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/ava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/ava.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/concat_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/concat_dataset.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/__init__.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/README.md -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/__init__.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/ava_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/ava_eval.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/label_map_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/label_map_util.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/metrics.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list_ops.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list_ops.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_ops.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_mask_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_mask_ops.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/object_detection_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/object_detection_evaluation.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/per_image_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/per_image_evaluation.py -------------------------------------------------------------------------------- /alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/standard_fields.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/standard_fields.py -------------------------------------------------------------------------------- /alphaction/dataset/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/samplers/__init__.py -------------------------------------------------------------------------------- /alphaction/dataset/samplers/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/samplers/distributed.py -------------------------------------------------------------------------------- /alphaction/dataset/samplers/grouped_batch_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/samplers/grouped_batch_sampler.py -------------------------------------------------------------------------------- /alphaction/dataset/samplers/iteration_based_batch_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/samplers/iteration_based_batch_sampler.py -------------------------------------------------------------------------------- /alphaction/dataset/transforms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/transforms/__init__.py -------------------------------------------------------------------------------- /alphaction/dataset/transforms/build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/transforms/build.py -------------------------------------------------------------------------------- /alphaction/dataset/transforms/object_transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/transforms/object_transforms.py -------------------------------------------------------------------------------- /alphaction/dataset/transforms/video_transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/dataset/transforms/video_transforms.py -------------------------------------------------------------------------------- /alphaction/engine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/engine/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/engine/inference.py -------------------------------------------------------------------------------- /alphaction/engine/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/engine/trainer.py -------------------------------------------------------------------------------- /alphaction/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/__init__.py -------------------------------------------------------------------------------- /alphaction/layers/batch_norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/batch_norm.py -------------------------------------------------------------------------------- /alphaction/layers/roi_align_3d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/roi_align_3d.py -------------------------------------------------------------------------------- /alphaction/layers/roi_pool_3d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/roi_pool_3d.py -------------------------------------------------------------------------------- /alphaction/layers/sigmoid_focal_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/sigmoid_focal_loss.py -------------------------------------------------------------------------------- /alphaction/layers/softmax_focal_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/layers/softmax_focal_loss.py -------------------------------------------------------------------------------- /alphaction/modeling/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/modeling/backbone/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/backbone/__init__.py -------------------------------------------------------------------------------- /alphaction/modeling/backbone/backbone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/backbone/backbone.py -------------------------------------------------------------------------------- /alphaction/modeling/backbone/i3d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/backbone/i3d.py -------------------------------------------------------------------------------- /alphaction/modeling/backbone/slowfast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/backbone/slowfast.py -------------------------------------------------------------------------------- /alphaction/modeling/common_blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/common_blocks.py -------------------------------------------------------------------------------- /alphaction/modeling/detector/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/detector/__init__.py -------------------------------------------------------------------------------- /alphaction/modeling/detector/action_detector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/detector/action_detector.py -------------------------------------------------------------------------------- /alphaction/modeling/nonlocal_block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/nonlocal_block.py -------------------------------------------------------------------------------- /alphaction/modeling/poolers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/poolers.py -------------------------------------------------------------------------------- /alphaction/modeling/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/registry.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/IA_structure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/IA_structure.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/action_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/action_head.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/inference.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/loss.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/metric.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/roi_action_feature_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/roi_action_feature_extractor.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/action_head/roi_action_predictors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/action_head/roi_action_predictors.py -------------------------------------------------------------------------------- /alphaction/modeling/roi_heads/roi_heads_3d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/roi_heads/roi_heads_3d.py -------------------------------------------------------------------------------- /alphaction/modeling/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/modeling/utils.py -------------------------------------------------------------------------------- /alphaction/solver/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/solver/__init__.py -------------------------------------------------------------------------------- /alphaction/solver/build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/solver/build.py -------------------------------------------------------------------------------- /alphaction/solver/lr_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/solver/lr_scheduler.py -------------------------------------------------------------------------------- /alphaction/structures/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/structures/bounding_box.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/structures/bounding_box.py -------------------------------------------------------------------------------- /alphaction/structures/memory_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/structures/memory_pool.py -------------------------------------------------------------------------------- /alphaction/utils/IA_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/IA_helper.py -------------------------------------------------------------------------------- /alphaction/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alphaction/utils/c2_model_loading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/c2_model_loading.py -------------------------------------------------------------------------------- /alphaction/utils/checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/checkpoint.py -------------------------------------------------------------------------------- /alphaction/utils/comm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/comm.py -------------------------------------------------------------------------------- /alphaction/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/logger.py -------------------------------------------------------------------------------- /alphaction/utils/metric_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/metric_logger.py -------------------------------------------------------------------------------- /alphaction/utils/model_serialization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/model_serialization.py -------------------------------------------------------------------------------- /alphaction/utils/random_seed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/random_seed.py -------------------------------------------------------------------------------- /alphaction/utils/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/registry.py -------------------------------------------------------------------------------- /alphaction/utils/video_decode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/alphaction/utils/video_decode.py -------------------------------------------------------------------------------- /data/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /data/ava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/data/ava.py -------------------------------------------------------------------------------- /data/ava_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/data/ava_eval.py -------------------------------------------------------------------------------- /data/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/data/transforms.py -------------------------------------------------------------------------------- /datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/datasets.py -------------------------------------------------------------------------------- /engine_for_finetuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/engine_for_finetuning.py -------------------------------------------------------------------------------- /figs/videomae.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/figs/videomae.png -------------------------------------------------------------------------------- /modeling_finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/modeling_finetune.py -------------------------------------------------------------------------------- /optim_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/optim_factory.py -------------------------------------------------------------------------------- /run_class_finetuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/run_class_finetuning.py -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_base_k400_pretrain+finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_base_k400_pretrain+finetune/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_base_k400_pretrain/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_base_k400_pretrain/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_huge_k400_pretrain+finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_huge_k400_pretrain+finetune/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_huge_k400_pretrain/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_huge_k400_pretrain/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_large_k400_pretrain+finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_large_k400_pretrain+finetune/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_large_k400_pretrain/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_large_k400_pretrain/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_small_k400_pretrain+finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_small_k400_pretrain+finetune/run.sh -------------------------------------------------------------------------------- /scripts/ava/videomae_vit_small_k400_pretrain/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/scripts/ava/videomae_vit_small_k400_pretrain/run.sh -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MCG-NJU/VideoMAE-Action-Detection/HEAD/utils.py --------------------------------------------------------------------------------