{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:55:25Z","timestamp":1782312925773,"version":"3.54.5"},"reference-count":80,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293540"],"award-info":[{"award-number":["62293540"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293542"],"award-info":[{"award-number":["62293542"]}],"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.2024.3396063","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T17:42:45Z","timestamp":1715103765000},"page":"3341-3352","source":"Crossref","is-referenced-by-count":12,"title":["Deep Boosting Learning: A Brand-New Cooperative Approach for Image-Text Matching"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4156-5417","authenticated-orcid":false,"given":"Haiwen","family":"Diao","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Holdings Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4500-7516","authenticated-orcid":false,"given":"Xiang","family":"Ruan","sequence":"additional","affiliation":[{"name":"Tiwaki Company Ltd., Kusatsu, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. NIPS","author":"Frome"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_17"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref17","first-page":"12","article-title":"VSE+: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7006"},{"key":"ref22","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. ICLR","author":"Romero"},{"key":"ref23","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. ICLR","author":"Zagoruyko"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00302"},{"key":"ref34","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","volume":"119","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01280"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00183"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref57","first-page":"1849","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. NIPS","author":"Sohn"},{"key":"ref58","first-page":"4170","article-title":"Learning deep embeddings with histogram loss","volume-title":"Proc. NIPS","author":"Ustinova"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995884"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref73","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref75","volume-title":"Efficient estimations from a slowly convergent robbins-monro process","author":"Ruppert","year":"1988"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref78","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref80","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10522595.pdf?arnumber=10522595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:44:18Z","timestamp":1715795058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3396063","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}