{"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/action-recognition-using-visual-attention","title":"Action Recognition using Visual Attention","arxiv_id":"1511.04119","date":"2015-11-12","proceeding":null,"authors":["Shikhar Sharma","Ryan Kiros","Ruslan Salakhutdinov"],"abstract":"We propose a soft attention based model for the task of action recognition in\nvideos. We use multi-layered Recurrent Neural Networks (RNNs) with Long\nShort-Term Memory (LSTM) units which are deep both spatially and temporally.\nOur model learns to focus selectively on parts of the video frames and\nclassifies videos after taking a few glimpses. The model essentially learns\nwhich parts in the frames are relevant for the task at hand and attaches higher\nimportance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51\nand Hollywood2 datasets and analyze how the model focuses its attention\ndepending on the scene and the action being performed.","url_abs":"http://arxiv.org/abs/1511.04119v3","url_pdf":"http://arxiv.org/pdf/1511.04119v3.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":"action-recognition-using-visual-attention","repo_url":"https://github.com/kracwarlock/action-recognition-visual-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"action-recognition-using-visual-attention","repo_url":"https://github.com/gaoqianmiao/Summer-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.04119","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}