{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:20:41Z","timestamp":1782836441613,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["2020YFB1709201"],"award-info":[{"award-number":["2020YFB1709201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772359"],"award-info":[{"award-number":["61772359"]}],"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":["61872267"],"award-info":[{"award-number":["61872267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2019 Tianjin New Generation Artificial Intelligence Major Program","award":["19ZXZNGX00110"],"award-info":[{"award-number":["19ZXZNGX00110"]}]},{"name":"Open Funding Project of the Key Laboratory of Electromagnetic Space Information"},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Theoretical Research on Video Semantic Analysis for Content Security of Social Networks"},{"name":"Baidu Pinecone Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3128744","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T22:45:26Z","timestamp":1637189126000},"page":"543-556","source":"Crossref","is-referenced-by-count":42,"title":["Multi-Scale Fine-Grained Alignments for Image and Sentence Matching"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9609-6120","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5165-204X","authenticated-orcid":false,"given":"Yuting","family":"Su","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2227-207X","authenticated-orcid":false,"given":"Xuanya","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical, and Information Engineering, Tianjin University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science, and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00118"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413998"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref15","first-page":"212","article-title":"Stacked cross attention for image-text matching","volume":"11208","author":"lee","year":"0","journal-title":"Proc 15th Eur Conf Comput Vis"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2956975"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01392-1"},{"key":"ref54","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref16","first-page":"1","article-title":"VSE : Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751966"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953692"},{"key":"ref46","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 27 Annu Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_12"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351062"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952085"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946477"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref30","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"zhang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref32","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 26 27th Annu Conf Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2936805"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00311"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358104"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref62","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume":"8693","author":"lin","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref61","first-page":"2641","article-title":"Flickr30 k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"plummer","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09618772.pdf?arnumber=9618772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T18:54:32Z","timestamp":1677524072000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9618772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3128744","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}