{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:03:45Z","timestamp":1767989025135,"version":"3.49.0"},"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100704"],"award-info":[{"award-number":["2018AAA0100704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"publisher","award":["62076162"],"award-info":[{"award-number":["62076162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010098","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/100010098","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Key Project","award":["20511100300"],"award-info":[{"award-number":["20511100300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3123553","type":"journal-article","created":{"date-parts":[[2021,11,5]],"date-time":"2021-11-05T19:20:58Z","timestamp":1636140058000},"page":"9193-9207","source":"Crossref","is-referenced-by-count":38,"title":["Memorize, Associate and Match: Embedding Enhancement via Fine-Grained Alignment for Image-Text Retrieval"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-4053","authenticated-orcid":false,"given":"Jiangtong","family":"Li","sequence":"first","affiliation":[]},{"given":"Liu","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1970-8634","authenticated-orcid":false,"given":"Li","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7597-8503","authenticated-orcid":false,"given":"Liqing","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1027"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref33","article-title":"Memory networks","author":"weston","year":"2014","journal-title":"arXiv 1410 3916"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952085"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref37","first-page":"1","article-title":"Structured attention networks","author":"kim","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref35","article-title":"Neural Turing machines","author":"graves","year":"2014","journal-title":"arXiv 1410 5401"},{"key":"ref34","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892802"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015084"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref2","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc 29th Brit Mach Vis Conf"},{"key":"ref1","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc 28th Annu Conf Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2466106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2592800"},{"key":"ref24","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent"},{"key":"ref23","first-page":"827","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc 28th Annu Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis (ECCV)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc 2nd Int Conf Learn Represent"},{"key":"ref52","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc 31th Annu Conf Neural Inf Process Syst (Autodiff Workshop)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.95.5.2703"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975594"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350974"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc CVPR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2018","journal-title":"Proc 32th Annu Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref47","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.651"},{"key":"ref44","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc CVPR"},{"key":"ref43","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09605203.pdf?arnumber=9605203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:04Z","timestamp":1652194204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9605203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3123553","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}