{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:17:53Z","timestamp":1784261873547,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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","award":["2022ZD0160403"],"award-info":[{"award-number":["2022ZD0160403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176178"],"award-info":[{"award-number":["62176178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2023.3348297","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T20:15:41Z","timestamp":1704485741000},"page":"595-609","source":"Crossref","is-referenced-by-count":58,"title":["USER: Unified Semantic Enhancement With Momentum Contrast for Image-Text Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2819-388X","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1586-0196","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref10","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Faghri"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11121-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/720"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref21","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3188569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3367-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref30","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref32","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref33","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Grill"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"ref35","article-title":"Representation learning with contrastive predictive coding","author":"v. d. Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref37","first-page":"1","article-title":"Text-based person search with limited data","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Han"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6823"},{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2592800"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref45","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref46","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kipf"},{"key":"ref47","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bahdanau"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038354"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048627"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref56","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref57","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref58","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","author":"Wang","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref63","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref67","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10382463.pdf?arnumber=10382463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T18:21:56Z","timestamp":1705170116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3348297","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}