{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T11:10:46Z","timestamp":1785582646292,"version":"3.56.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB1402600"],"award-info":[{"award-number":["2018YFB1402600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702009"],"award-info":[{"award-number":["61702009"]}],"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":["61822208"],"award-info":[{"award-number":["61822208"]}],"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":["61632019"],"award-info":[{"award-number":["61632019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","award":["2018497"],"award-info":[{"award-number":["2018497"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61836011"],"award-info":[{"award-number":["61836011"]}],"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":[[2021]]},"DOI":"10.1109\/tip.2020.3038354","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T02:14:24Z","timestamp":1606270464000},"page":"617-627","source":"Crossref","is-referenced-by-count":49,"title":["Deep Relation Embedding for Cross-Modal Retrieval"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7650-1109","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3048-6980","authenticated-orcid":false,"given":"Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5165-4325","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"arXiv 1511 06361"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref32","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00174"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941858"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240559"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref27","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240684"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2864919"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2372616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/124"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref25","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref50","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref54","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"},{"key":"ref11","first-page":"3715","article-title":"Learning visually-grounded semantics from contrastive adversarial samples","author":"shi","year":"2018","journal-title":"Proc Int Conf Comput Linguistics (ICCL)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2564638"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2592800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref18","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref19","article-title":"Dual-path convolutional image-text embedding with instance loss","author":"zheng","year":"2017","journal-title":"arXiv 1711 05535"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240527"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123317"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2606441"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351055"},{"key":"ref44","first-page":"1","article-title":"Learning to hash on partial multi-modal data","author":"wang","year":"2015","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09269483.pdf?arnumber=9269483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:12Z","timestamp":1652194212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9269483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3038354","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}