{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stair-captions-constructing-a-large-scale","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","arxiv_id":"1705.00823","date":"2017-05-02","proceeding":"ACL 2017 7","authors":["Yuya Yoshikawa","Yutaro Shigeto","Akikazu Takeuchi"],"abstract":"In recent years, automatic generation of image descriptions (captions), that\nis, image captioning, has attracted a great deal of attention. In this paper,\nwe particularly consider generating Japanese captions for images. Since most\navailable caption datasets have been constructed for English language, there\nare few datasets for Japanese. To tackle this problem, we construct a\nlarge-scale Japanese image caption dataset based on images from MS-COCO, which\nis called STAIR Captions. STAIR Captions consists of 820,310 Japanese captions\nfor 164,062 images. In the experiment, we show that a neural network trained\nusing STAIR Captions can generate more natural and better Japanese captions,\ncompared to those generated using English-Japanese machine translation after\ngenerating English captions.","url_abs":"http://arxiv.org/abs/1705.00823v1","url_pdf":"http://arxiv.org/pdf/1705.00823v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stair-captions-constructing-a-large-scale","repo_url":"https://github.com/William-N-Havard/VGS-dataset-metadata","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"stair-captions","name":"STAIR Captions","full_name":"STAIR Captions"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.00823","atlas_url":"https://app.syntology.ai/?focus=1705.00823","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}