{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:07:37Z","timestamp":1772935657791,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402549","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"6318-6324","source":"Crossref","is-referenced-by-count":0,"title":["A Cross-Modal Information Retrieval Framework Based on an Interactive Encoder and Re-Ranking Algorithm"],"prefix":"10.1109","author":[{"given":"Xiaoyan","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Intelligentization, Dongguan University of Technology,Dongguan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sichun","family":"Luo","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanxu","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Intelligentization, Dongguan University of Technology,Dongguan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref3","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref5","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref7","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref10","article-title":"Loopitr: Combining dual and cross encoder architectures for image-text retrieval","author":"Lei","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2605058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-1949-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873977"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1145\/3343031.3350875","article-title":"Matching images and text with multi-modal tensor fusion and re-ranking","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia","author":"Wang","year":"2019"},{"key":"ref18","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00385"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402549.pdf?arnumber=11402549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:37:43Z","timestamp":1772869063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402549","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}