{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:45:17Z","timestamp":1780512317216,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["2020AAA0106502"],"award-info":[{"award-number":["2020AAA0106502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073105"],"award-info":[{"award-number":["62073105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province of China","doi-asserted-by":"publisher","award":["ZD2022F002"],"award-info":[{"award-number":["ZD2022F002"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003472","name":"State Key Laboratory of Robotics and System [Harbin Institute of Technology (HIT)]","doi-asserted-by":"publisher","award":["SKLRS-2019-KF-14"],"award-info":[{"award-number":["SKLRS-2019-KF-14"]}],"id":[{"id":"10.13039\/501100003472","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003472","name":"State Key Laboratory of Robotics and System [Harbin Institute of Technology (HIT)]","doi-asserted-by":"publisher","award":["SKLRS-202003D"],"award-info":[{"award-number":["SKLRS-202003D"]}],"id":[{"id":"10.13039\/501100003472","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Heilongjiang Touyan Innovation Team Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3220051","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:34:17Z","timestamp":1668112457000},"page":"7154-7164","source":"Crossref","is-referenced-by-count":16,"title":["Latent Space Semantic Supervision Based on Knowledge Distillation for Cross-Modal Retrieval"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8752-8315","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0956-8757","authenticated-orcid":false,"given":"Xiangqian","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref38","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00319"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2879846"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref30","first-page":"139","article-title":"Collecting image annotations using Amazon’s Mechanical Turk","author":"rashtchian","year":"2010","journal-title":"Proc Workshop Creating Speech Lang Data Amazon’s Mech Turk"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_17"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351055"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3362065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref28","first-page":"39","article-title":"The MIR Flickr retrieval evaluation","author":"huiskes","year":"2008","journal-title":"Proc ACM Int Conf Multimedia Inf Retrieval (MIR)"},{"key":"ref4","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume":"abs 1411 2539","author":"kiros","year":"2014","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967212"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref8","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc Brit Mach Vis Conf (BMVC)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref21","first-page":"7","article-title":"Distilling the knowledge in a neural network","volume":"abs 1503 2531","author":"hinton","year":"2015","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref24","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475451"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref25","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09945996.pdf?arnumber=9945996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:47:04Z","timestamp":1670874424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3220051","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}