{"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/naver-at-activitynet-challenge-2019-task-b","title":"Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)","arxiv_id":"1906.10555","date":"2019-06-25","proceeding":null,"authors":["Joon Son Chung"],"abstract":"This report describes our submission to the ActivityNet Challenge at CVPR 2019. We use a 3D convolutional neural network (CNN) based front-end and an ensemble of temporal convolution and LSTM classifiers to predict whether a visible person is speaking or not. Our results show significant improvements over the baseline on the AVA-ActiveSpeaker dataset.","url_abs":"https://arxiv.org/abs/1906.10555v1","url_pdf":"https://arxiv.org/pdf/1906.10555v1.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":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","task":"Audio-Visual Active Speaker Detection","dataset":"AVA-ActiveSpeaker","model":"VGG-{LSTM+TCN} (ensemble)","rank_in_archive_order":17,"of":20,"metrics":{"validation mean average precision":"87.8%"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.10555","atlas_url":"https://app.syntology.ai/?focus=1906.10555","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}