{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:40:17Z","timestamp":1778258417072,"version":"3.51.4"},"reference-count":61,"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\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021XD-A01-1"],"award-info":[{"award-number":["2021XD-A01-1"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program of National Natural Science Foundation of China","award":["92067202"],"award-info":[{"award-number":["92067202"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2020104"],"award-info":[{"award-number":["CX2020104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3261443","type":"journal-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T18:30:11Z","timestamp":1679682611000},"page":"103-116","source":"Crossref","is-referenced-by-count":27,"title":["Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2535-2523","authenticated-orcid":false,"given":"Zheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-4520","authenticated-orcid":false,"given":"Caili","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3987-0591","authenticated-orcid":false,"given":"Zerun","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongtian","family":"Du","sequence":"additional","affiliation":[{"name":"China Telecom Digital Intelligence Technology Company, Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00500"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref15","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref20","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":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2489841"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(00)00019-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.826752"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/76.718510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref38","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref40","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":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref43","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Ordonez","year":"2011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2906603"},{"key":"ref47","first-page":"2021","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Dosovitskiy"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref61","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10081045.pdf?arnumber=10081045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:57:20Z","timestamp":1705021040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10081045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3261443","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}