{"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/technical-report-temporal-aggregate","title":"Technical Report: Temporal Aggregate Representations","arxiv_id":"2106.03152","date":"2021-06-06","proceeding":null,"authors":["Fadime Sener","Dibyadip Chatterjee","Angela Yao"],"abstract":"This technical report extends our work presented in [9] with more experiments. In [9], we tackle long-term video understanding, which requires reasoning from current and past or future observations and raises several fundamental questions. How should temporal or sequential relationships be modelled? What temporal extent of information and context needs to be processed? At what temporal scale should they be derived? [9] addresses these questions with a flexible multi-granular temporal aggregation framework. In this report, we conduct further experiments with this framework on different tasks and a new dataset, EPIC-KITCHENS-100.","url_abs":"https://arxiv.org/abs/2106.03152v2","url_pdf":"https://arxiv.org/pdf/2106.03152v2.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":"technical-report-temporal-aggregate","repo_url":"https://github.com/dibschat/tempAgg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100","model":"TempAgg","rank_in_archive_order":8,"of":9,"metrics":{"Recall@5":"14.73"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100-test","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100 (test)","model":"TempAgg","rank_in_archive_order":5,"of":8,"metrics":{"recall@5":"12.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-epic-kitchens-100","task":"Action Recognition","dataset":"EPIC-KITCHENS-100","model":"TempAgg","rank_in_archive_order":17,"of":32,"metrics":{"Action@1":"45.26","Noun@1":"53.35","Verb@1":"66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03152","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}