{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:33:11Z","timestamp":1764401591375,"version":"3.46.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019923","name":"DEVCOM Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF2020157"],"award-info":[{"award-number":["W911NF2020157"]}],"id":[{"id":"10.13039\/100019923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249042","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2388-2393","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable Video-Text Alignment (VTA) for Cross-Modal Retrieval"],"prefix":"10.1109","author":[{"given":"Tsung-Shan","family":"Yang","sequence":"first","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun-Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengwei","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suya","family":"You","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.-C. Jay","family":"Kuo","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103685"},{"key":"ref4","article-title":"Learning languagevisual embedding for movie understanding with naturallanguage","author":"Torabi","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref9","first-page":"5696","article-title":"Omnivl: One foundation model for image-language and video-language tasks","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.03.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104390"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848810"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref16","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref17","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref21","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021","journal-title":"arXiv preprint"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249042.pdf?arnumber=11249042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:26:55Z","timestamp":1764401215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249042","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}