{"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/ictcas-ucas-tal-submission-to-the-ava","title":"ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021","arxiv_id":null,"date":"2021-06-01","proceeding":"The ActivityNet Large-Scale Activity Recognition Challenge Workshop, CVPR 2021 6","authors":["Yuanhang Zhang","Susan Liang","Shuang Yang","Xiao Liu","Zhongqin Wu","Shiguang Shan"],"abstract":"This report presents a brief description of our method for the AVA Active Speaker Detection (ASD) task at ActivityNet\r\nChallenge 2021. Our solution, the Extended Unified Context Network (Extended UniCon) is based on a novel Unified\r\nContext Network (UniCon) designed for robust ASD, which combines multiple types of contextual information to optimize all candidates jointly. We propose a few changes to the original UniCon in terms of audio features, temporal modeling architecture, and loss function design. Together, our best model ensemble sets a new state-of-the-art at 93.4% mAP on the AVA-ActiveSpeaker test set without any form of pretraining, and currently ranks first on the ActivityNet challenge leaderboard.","url_abs":"http://research.google.com/ava/2021/S1_ICTCAS-UCAS-TAL.pdf","url_pdf":"http://research.google.com/ava/2021/S1_ICTCAS-UCAS-TAL.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":[],"tasks":[{"task_slug":"active-speaker-detection","task_name":"Active Speaker Detection"},{"task_slug":"audio-visual-active-speaker-detection","task_name":"Audio-Visual Active Speaker Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","task":"Audio-Visual Active Speaker Detection","dataset":"AVA-ActiveSpeaker","model":"Extended UniCon","rank_in_archive_order":9,"of":20,"metrics":{"validation mean average precision":"93.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}