Skip to content
STAIR captions: large-scale Japanese image caption dataset
Branch: master
Clone or download

Latest commit

Fetching latest commit…
Cannot retrieve the latest commit at this time.


Type Name Latest commit message Commit time
Failed to load latest commit information.

STAIR Captions

We developed a large-scale Japanese image caption dataset, named STAIR Captions. STAIR Captions website is .

Annotation Format

STAIR Captions dataset is provided as JSON files. The annotation format of STAIR Captions follows the one of MS-COCO:

  "id"                : int,
  "image_id"          : int,
  "caption"           : str,
  "tokenized_caption" : str,

For the details of the annotation format, please see MS-COCO download page.


  • 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]
  • 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]


Creative Commons Attribution 4.0 License.

You can’t perform that action at this time.