{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T03:00:04Z","timestamp":1790391604722,"version":"4.1.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003999","name":"Science Fund for Creative Research Groups","doi-asserted-by":"publisher","award":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100003999","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3358411","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T18:37:49Z","timestamp":1706207869000},"page":"6542-6558","source":"Crossref","is-referenced-by-count":36,"title":["Fast, Accurate, and Lightweight Memory-Enhanced Embedding Learning Framework for Image-Text Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4716-614X","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, 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":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2911359"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075242"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3254530"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/111"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref32","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280734"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.300"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.772"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01280"},{"key":"ref50","article-title":"Memory networks","author":"Weston","year":"2014","journal-title":"arXiv:1410.3916"},{"key":"ref51","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sukhbaatar"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272319"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01154"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref59","first-page":"4516","article-title":"MeGA-CDA: Memory guided attention for category-aware unsupervised domain adaptive object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Vibashan"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877122"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975594"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235523"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.19"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463061"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref71","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref76","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3261443"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"issue":"11","key":"ref80","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10414133.pdf?arnumber=10414133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T04:01:10Z","timestamp":1720152070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10414133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":80,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3358411","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}