{"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/lsta-long-short-term-attention-for-egocentric","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","arxiv_id":"1811.10698","date":"2018-11-26","proceeding":"CVPR 2019 6","authors":["Swathikiran Sudhakaran","Sergio Escalera","Oswald Lanz"],"abstract":"Egocentric activity recognition is one of the most challenging tasks in video\nanalysis. It requires a fine-grained discrimination of small objects and their\nmanipulation. While some methods base on strong supervision and attention\nmechanisms, they are either annotation consuming or do not take spatio-temporal\npatterns into account. In this paper we propose LSTA as a mechanism to focus on\nfeatures from spatial relevant parts while attention is being tracked smoothly\nacross the video sequence. We demonstrate the effectiveness of LSTA on\negocentric activity recognition with an end-to-end trainable two-stream\narchitecture, achieving state of the art performance on four standard\nbenchmarks.","url_abs":"http://arxiv.org/abs/1811.10698v3","url_pdf":"http://arxiv.org/pdf/1811.10698v3.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":"lsta-long-short-term-attention-for-egocentric","repo_url":"https://github.com/swathikirans/LSTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"egocentric-activity-recognition","task_name":"Egocentric Activity Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/egocentric-activity-recognition-on-egtea-1","task":"Egocentric Activity Recognition","dataset":"EGTEA","model":"LSTA","rank_in_archive_order":5,"of":6,"metrics":{"Average Accuracy":"61.9","Mean class accuracy":"-"},"uses_additional_data":false},{"leaderboard":"/sota/egocentric-activity-recognition-on-epic-1","task":"Egocentric Activity Recognition","dataset":"EPIC-KITCHENS-55","model":"LSTA","rank_in_archive_order":7,"of":7,"metrics":{"Actions Top-1 (S2)":"16.63"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.10698","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}