{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:44:03Z","timestamp":1785822243107,"version":"3.56.0"},"reference-count":61,"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":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202204"],"award-info":[{"award-number":["62202204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["JUSRP123032"],"award-info":[{"award-number":["JUSRP123032"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3715851","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:07:11Z","timestamp":1785265631000},"page":"8195-8205","source":"Crossref","is-referenced-by-count":0,"title":["Probabilistic Embeddings With Evidence Learning and Refinement for Text\u2013Video Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0918","authenticated-orcid":false,"given":"Donglin","family":"Zhang","sequence":"first","affiliation":[{"name":"Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Rao","sequence":"additional","affiliation":[{"name":"Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-9205","authenticated-orcid":false,"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[{"name":"University of Surrey","place":["Guildford, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3611174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574925"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3514352"},{"key":"ref5","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"arXiv:2109.04290"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3627167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980944"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02645-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3587575"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-024-00335-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"ref18","article-title":"Multi-scale temporal difference transformer for video-text retrieval","author":"Wang","year":"2024","journal-title":"arXiv:2406.16111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"ref20","article-title":"TempMe: Video temporal token merging for efficient text-video retrieval","author":"Shen","year":"2024","journal-title":"arXiv:2409.01156"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32935"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3422869"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3664963"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3410329"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25113"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02242"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1515\/9780691214696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112145"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref37","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2022","journal-title":"arXiv:2209.06430"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611714"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680839"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3429192"},{"key":"ref41","article-title":"Advancing high-resolution video-language representation with large-scale video transcriptions","author":"Xue","year":"2021","journal-title":"arXiv:2111.10337"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3522124"},{"key":"ref43","article-title":"Modeling uncertainty with hedged instance embedding","author":"Oh","year":"2018","journal-title":"arXiv:1810.00319"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref47","first-page":"3183","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Sensoy"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1068"},{"key":"ref49","article-title":"Classification is a strong baseline for deep metric learning","author":"Zhai","year":"2018","journal-title":"arXiv:1811.12649"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01107"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0127"},{"key":"ref55","article-title":"TokenBinder: Text-video retrieval with one-to-many alignment paradigm","author":"Zhang","year":"2024","journal-title":"arXiv:2409.19865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32778"},{"issue":"86","key":"ref57","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref58","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref59","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref60","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Hanson"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1119\/1.2339436"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11627158.pdf?arnumber=11627158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:48:12Z","timestamp":1785818892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11627158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3715851","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}