{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T12:25:49Z","timestamp":1793103949703,"version":"4.5.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3307554","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:49:25Z","timestamp":1692726565000},"page":"2973-2988","source":"Crossref","is-referenced-by-count":30,"title":["Enhanced Semantic Similarity Learning Framework for Image-Text Matching"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9967-1992","authenticated-orcid":false,"given":"Huatian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4716-614X","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Anhui, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3254530"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3253548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859629"},{"key":"ref10","article-title":"Integrating listwise ranking into pairwise-based image-text retrieval","author":"Li","year":"2023","journal-title":"arXiv:2305.16566"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058626"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IEMCON53756.2021.9623131"},{"key":"ref17","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"ref20","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/158"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3046855"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/720"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3249754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/140"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207910"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3261443"},{"key":"ref53","author":"Bilenko","year":"2006","journal-title":"Learnable Similarity Functions and Their Application to Record Linkage and Clustering"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-019-00201-2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.299"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.193"},{"key":"ref57","first-page":"1","article-title":"Neural similarity learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu"},{"key":"ref58","article-title":"Fisher vectors derived from hybrid Gaussian\u2013Laplacian mixture models for image annotation","author":"Klein","year":"2014","journal-title":"arXiv:1411.7399"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref66","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref68","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref70","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karpathy"},{"key":"ref71","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref72","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10226265.pdf?arnumber=10226265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:52:33Z","timestamp":1712692353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10226265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":72,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3307554","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}