{"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/where-a-strong-backbone-meets-strong-features","title":"Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge","arxiv_id":"2211.09074","date":"2022-11-16","proceeding":null,"authors":["Fangzhou Mu","Sicheng Mo","Gillian Wang","Yin Li"],"abstract":"This report describes our submission to the Ego4D Moment Queries Challenge 2022. Our submission builds on ActionFormer, the state-of-the-art backbone for temporal action localization, and a trio of strong video features from SlowFast, Omnivore and EgoVLP. Our solution is ranked 2nd on the public leaderboard with 21.76% average mAP on the test set, which is nearly three times higher than the official baseline. Further, we obtain 42.54% Recall@1x at tIoU=0.5 on the test set, outperforming the top-ranked solution by a significant margin of 1.41 absolute percentage points. Our code is available at https://github.com/happyharrycn/actionformer_release.","url_abs":"https://arxiv.org/abs/2211.09074v1","url_pdf":"https://arxiv.org/pdf/2211.09074v1.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":"where-a-strong-backbone-meets-strong-features","repo_url":"https://github.com/happyharrycn/actionformer_release","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"where-a-strong-backbone-meets-strong-features","repo_url":"https://github.com/showlab/egovlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"moment-queries","task_name":"Moment Queries"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-action-localization-on-ego4d-mq-test","task":"Temporal Action Localization","dataset":"Ego4D MQ test","model":"ActionFormer (SlowFast+Omnivore+EgoVLP)","rank_in_archive_order":1,"of":1,"metrics":{"Average mAP":"21.76","Recall@1x (tIoU=0.5)":"42.54"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-ego4d-mq-val","task":"Temporal Action Localization","dataset":"Ego4D MQ val","model":"ActionFormer (SlowFast+Omnivore+EgoVLP)","rank_in_archive_order":1,"of":1,"metrics":{"Average mAP":"21.4","Recall@1x (tIoU=0.5)":"38.73"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}