{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:46Z","timestamp":1778051506144,"version":"3.51.4"},"reference-count":51,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/wacv61042.2026.00433","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4451-4460","source":"Crossref","is-referenced-by-count":0,"title":["Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Yuliang","family":"Huang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxu","family":"Wei","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Tibet University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3604"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref5","author":"Cheng","year":"2021","journal-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss"},{"key":"ref6","article-title":"Improved probabilistic image-text representations","volume-title":"ICLR","author":"Chun"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref10","author":"Fang","year":"2021","journal-title":"Clip2video: Mastering video-text retrieval via image clip"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref13","author":"Gao","year":"2021","journal-title":"Clip2tv: An empirical study on transformer-based methods for video-text retrieval"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406485"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00257"},{"key":"ref20","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-eacl.101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1068"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635757"},{"key":"ref26","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref27","author":"Loshchilov","year":"2016","journal-title":"Sgdr: Stochastic gradient descent with warm restarts"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref30","volume-title":"Machine learning: a probabilistic perspective","author":"Murphy","year":"2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00501"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3374571"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32778"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref40","author":"Wang","year":"2022","journal-title":"Disentangled representation learning for text-video retrieval"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.46"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref45","author":"Xue","year":"2022","journal-title":"Clip-vip: Adapting pretrained image-text model to video-language representation alignment"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611714"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680839"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_18"}],"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\/11492145.pdf?arnumber=11492145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:14:51Z","timestamp":1778048091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00433","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}