{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:39:24Z","timestamp":1784072364805,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006222"],"award-info":[{"award-number":["62006222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association of CAS","award":["2021153"],"award-info":[{"award-number":["2021153"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3280734","type":"journal-article","created":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:38:37Z","timestamp":1685381917000},"page":"1361-1372","source":"Crossref","is-referenced-by-count":21,"title":["Towards Fast and Accurate Image-Text Retrieval With Self-Supervised Fine-Grained Alignment"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1598-0764","authenticated-orcid":false,"given":"Jiamin","family":"Zhuang","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-511X","authenticated-orcid":false,"given":"Jing","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3658-8099","authenticated-orcid":false,"given":"Xiangyan","family":"Qu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4416-3974","authenticated-orcid":false,"given":"Yue","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","first-page":"15509","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bachman","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref4","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref10","first-page":"344","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.,","author":"Faghri","year":"2018"},{"key":"ref11","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frome","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref17","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref19","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref22","article-title":"Efficient self-supervised vision transformers for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.772"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref35","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tian","year":"2021"},{"key":"ref36","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref38","article-title":"Order-embeddings of images and language","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vendrov","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10138045.pdf?arnumber=10138045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:48:52Z","timestamp":1705690132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10138045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3280734","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}