├── README.md └── stair_captions_v1.2.tar.gz /README.md: -------------------------------------------------------------------------------- 1 | # STAIR Captions 2 | We developed a large-scale Japanese image caption dataset, named STAIR Captions. 3 | STAIR Captions website is http://captions.stair.center . 4 | 5 | ## Annotation Format 6 | STAIR Captions dataset is provided as JSON files. 7 | The annotation format of STAIR Captions follows the one of MS-COCO: 8 | ``` 9 | annotation{ 10 | "id" : int, 11 | "image_id" : int, 12 | "caption" : str, 13 | "tokenized_caption" : str, 14 | } 15 | ``` 16 | 17 | For the details of the annotation format, please see [MS-COCO download page](http://mscoco.org/dataset/#download). 18 | 19 | 20 | ## Publications 21 | - Yuya Yoshikawa, Yutaro Shigeto, Akikazu Takeuchi, ``STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset,'' Annual Meeting of the Association for Computational Linguistics (ACL), Short Paper, 2017. [[arXiv](https://arxiv.org/abs/1705.00823)] 22 | - 吉川友也, 重藤優太郎, 竹内彰一, ``STAIR Captions: 大規模日本語画像キャプションデータセット'', 言語処理学会第23回年次大会 (NLP2017), 2017. (In Japanese) [PDF] 23 | 24 | ## License 25 | [Creative Commons Attribution 4.0 License.](https://creativecommons.org/licenses/by/4.0/legalcode) 26 | -------------------------------------------------------------------------------- /stair_captions_v1.2.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/STAIR-Lab-CIT/STAIR-captions/6ac656e65d80cbe2c914d93626a1d5454e35a5d6/stair_captions_v1.2.tar.gz --------------------------------------------------------------------------------