{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:50:29Z","timestamp":1782334229363,"version":"3.54.5"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2025ZD1601300"],"award-info":[{"award-number":["2025ZD1601300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2049"],"award-info":[{"award-number":["624B2049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332002"],"award-info":[{"award-number":["62332002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425101"],"award-info":[{"award-number":["62425101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM901"],"award-info":[{"award-number":["JYB2025XDXM901"]}]},{"name":"Suzhou Key Core Technology Project","award":["SYG2025118"],"award-info":[{"award-number":["SYG2025118"]}]},{"name":"Beijing Science and Technology Plan","award":["Z241100004224011"],"award-info":[{"award-number":["Z241100004224011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3697617","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:09:12Z","timestamp":1780430952000},"page":"6645-6657","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Decoupled and Knowledge-Shared Probabilistic Mapping Network for Multi-Grained Cross-Modal Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-9016","authenticated-orcid":false,"given":"Wenrui","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeyu","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3178-9772","authenticated-orcid":false,"given":"Liang-Jian","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Multi-Hazard Early Warning Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9796-0478","authenticated-orcid":false,"given":"Ruiqin","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Institute of Digital Media, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of AI for Science, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02570"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01721"},{"key":"ref4","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021","journal-title":"arXiv:2104.11178"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3195874"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374791"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487908"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3396063"},{"key":"ref13","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3310870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611758"},{"key":"ref16","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"ref18","first-page":"1","article-title":"Jina CLIP: Your CLIP model is also your text retriever","volume-title":"Proc. Multi-Modal Found. Model Meets Embodied AI Workshop@ ICML","author":"Koukounas"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3339661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633657"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368964"},{"key":"ref26","first-page":"5660","article-title":"Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Mallasto"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32525"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3430080"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611759"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32605"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103716"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02485"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394551"},{"key":"ref50","first-page":"39787","article-title":"Improved probabilistic image-text representations","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Chun"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3568851"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3632893"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300155"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC61545.2025.10978250"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC61545.2025.10978706"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3488859"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/EIT63098.2024.10762270"},{"key":"ref61","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref64","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3572844"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28004"},{"key":"ref76","first-page":"8384","article-title":"Cross-modal feature alignment and fusion for composed image retrieval","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wan"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11547880.pdf?arnumber=11547880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:52:33Z","timestamp":1782330753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11547880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3697617","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}