{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:28:22Z","timestamp":1784140102455,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62371343"],"award-info":[{"award-number":["62371343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024-1-ZD-02"],"award-info":[{"award-number":["2024-1-ZD-02"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3618550","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:36Z","timestamp":1759772256000},"page":"9723-9734","source":"Crossref","is-referenced-by-count":2,"title":["Similarity Shuffled Criss-Cross Transformer With Angle Loss for Image-Text Matching"],"prefix":"10.1109","volume":"27","author":[{"given":"Ran","family":"Chen","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4357-1095","authenticated-orcid":false,"given":"Taiyi","family":"Su","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3682-6288","authenticated-orcid":false,"given":"Zhangkai","family":"Ni","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086591"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2997020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243665"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369968"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref20","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. Int. Conf. Learn. Representations Workshops","author":"Mikolov","year":"2013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref22","first-page":"595","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref30","article-title":"Order-embeddings of images and language","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vendrov","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref39","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref45","article-title":"VSE : Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/111"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00183"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374221"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11194259.pdf?arnumber=11194259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:38Z","timestamp":1766082878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11194259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3618550","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}