{"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-actions-a-video-dataset-of-everyday","title":"STAIR Actions: A Video Dataset of Everyday Home Actions","arxiv_id":"1804.04326","date":"2018-04-12","proceeding":null,"authors":["Yuya Yoshikawa","Jiaqing Lin","Akikazu Takeuchi"],"abstract":"A new large-scale video dataset for human action recognition, called STAIR\nActions is introduced. STAIR Actions contains 100 categories of action labels\nrepresenting fine-grained everyday home actions so that it can be applied to\nresearch in various home tasks such as nursing, caring, and security. In STAIR\nActions, each video has a single action label. Moreover, for each action\ncategory, there are around 1,000 videos that were obtained from YouTube or\nproduced by crowdsource workers. The duration of each video is mostly five to\nsix seconds. The total number of videos is 102,462. We explain how we\nconstructed STAIR Actions and show the characteristics of STAIR Actions\ncompared to existing datasets for human action recognition. Experiments with\nthree major models for action recognition show that STAIR Actions can train\nlarge models and achieve good performance. STAIR Actions can be downloaded from\nhttp://actions.stair.center","url_abs":"http://arxiv.org/abs/1804.04326v3","url_pdf":"http://arxiv.org/pdf/1804.04326v3.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-actions-a-video-dataset-of-everyday","repo_url":"https://github.com/STAIR-Lab-CIT/STAIR-actions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.04326","atlas_url":"https://app.syntology.ai/?focus=1804.04326","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}