{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:00:23Z","timestamp":1755219623983,"version":"3.43.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099480","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Visual Keyword Spotting with Multi-Encoder for MAVSR 2025"],"prefix":"10.1109","author":[{"given":"Dejun","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Fosafer Information Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xupeng","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Fosafer Information Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Fosafer Information Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beijing Fosafer Information Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref2","article-title":"Lrs3-ted: a largescale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv:1809.00496"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3711129.3711207"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800480"},{"volume-title":"Signs in time: Encoding human motion as a temporal image","year":"2016","author":"Chung","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832305"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"volume-title":"Visual keyword spotting with attention","year":"2021","author":"Prajwal","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02511-4"},{"key":"ref23","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv preprint arXiv:2201.02184"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-99"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163160"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645400"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02556"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","start":{"date-parts":[[2025,5,26]]},"location":"Tampa\/Clearwater, FL, USA","end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099480.pdf?arnumber=11099480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:08:49Z","timestamp":1754543329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099480","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}