{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:28:19Z","timestamp":1784140099422,"version":"3.55.0"},"reference-count":56,"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":["61972312"],"award-info":[{"award-number":["61972312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3369968","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T20:07:31Z","timestamp":1708978051000},"page":"7555-7566","source":"Crossref","is-referenced-by-count":27,"title":["A Mutually Textual and Visual Refinement Network for Image-Text Matching"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7217-864X","authenticated-orcid":false,"given":"Shanmin","family":"Pang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3045-7628","authenticated-orcid":false,"given":"Yueyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0204-7932","authenticated-orcid":false,"given":"Jiawei","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4994-9343","authenticated-orcid":false,"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref9","first-page":"1","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/111"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243665"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p14-5010"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983872"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref53","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref54","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Zeng","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref56","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10444952.pdf?arnumber=10444952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:54:12Z","timestamp":1714762452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3369968","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}