{"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/temporal-aggregate-representations-for-long","title":"Temporal Aggregate Representations for Long-Range Video Understanding","arxiv_id":"2006.00830","date":"2020-06-01","proceeding":"ECCV 2020 8","authors":["Fadime Sener","Dipika Singhania","Angela Yao"],"abstract":"Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular temporal aggregation framework. We show that it is possible to achieve state of the art in both next action and dense anticipation with simple techniques such as max-pooling and attention. To demonstrate the anticipation capabilities of our model, we conduct experiments on Breakfast, 50Salads, and EPIC-Kitchens datasets, where we achieve state-of-the-art results. With minimal modifications, our model can also be extended for video segmentation and action recognition.","url_abs":"https://arxiv.org/abs/2006.00830v2","url_pdf":"https://arxiv.org/pdf/2006.00830v2.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":"temporal-aggregate-representations-for-long","repo_url":"https://github.com/dibschat/tempAgg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-aggregate-representations-for-long","repo_url":"https://github.com/dipika-singhania/multi-scale-action-banks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"future-prediction","task_name":"Future prediction"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-anticipation-on-assembly101","task":"Action Anticipation","dataset":"Assembly101","model":"TempAgg","rank_in_archive_order":2,"of":2,"metrics":{"Actions Recall@5":"8.53","Objects Recall@5":"26.27","Verbs Recall@5":"59.11"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}