{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:48Z","timestamp":1778048328640,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00111","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1074-1083","source":"Crossref","is-referenced-by-count":0,"title":["GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection"],"prefix":"10.1109","author":[{"given":"Yu","family":"Wang","sequence":"first","affiliation":[{"name":"Indiana University,Bloomington,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juhyung","family":"Ha","sequence":"additional","affiliation":[{"name":"Indiana University,Bloomington,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frangil M.","family":"Ramirez","sequence":"additional","affiliation":[{"name":"Indiana University,Bloomington,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[{"name":"Indiana University,Bloomington,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Crandall","sequence":"additional","affiliation":[{"name":"Indiana University,Bloomington,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-93806-1_15"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746991"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02440"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448124"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888235"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02399-2"},{"key":"ref17","article-title":"Quavf: Quality-aware audiovisual fusion for ego4d talking to me challenge","author":"Lin","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094306"},{"key":"ref19","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref20","article-title":"Intel labs at ego4d challenge 2022: A better baseline for audio-visual diarization","author":"Min","year":"2022"},{"key":"ref21","article-title":"Sthg: Spatial-temporal heterogeneous graph learning for advanced audio-visual diarization","author":"Min","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02567"},{"key":"ref24","article-title":"Unitalk: Towards universal active speaker detection in real world scenarios","author":"Phuc Nguyen","year":"2025"},{"key":"ref25","article-title":"Laser: Lip landmark assisted speaker detection for robustness","author":"Phuc Nguyen","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref27","article-title":"Gated attention for large language models: Non-linearity, sparsity, and attention-sink-free","author":"Qiu","year":"2025"},{"key":"ref28","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ijcb65343.2025.11410746"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3412821"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3520030"},{"key":"ref33","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref36","article-title":"Robust active speaker detection in noisy environments","author":"Nagender Vasireddy","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446769"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.01.002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685716"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55214.2022.9943352"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00552"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492497.pdf?arnumber=11492497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:59Z","timestamp":1778047019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00111","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}