{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:02:00Z","timestamp":1773414120900,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["62222203"],"award-info":[{"award-number":["62222203"]}],"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":["61976049"],"award-info":[{"award-number":["61976049"]}],"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":["62072080"],"award-info":[{"award-number":["62072080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Association for Artificial Intelligence (CAAI)-Huawei MindSpore Open Fund"},{"name":"Open Research Projects of Zhejiang Laboratory","award":["2021KH0AB01"],"award-info":[{"award-number":["2021KH0AB01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3306738","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:08:40Z","timestamp":1692641320000},"page":"2959-2972","source":"Crossref","is-referenced-by-count":23,"title":["Multi-Grained Attention Network With Mutual Exclusion for Composed Query-Based Image Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"first","affiliation":[{"name":"Center for Future Multimedia, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-651X","authenticated-orcid":false,"given":"Xun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-6260","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer, Huaqiao University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-13709-0_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref15","article-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","author":"Delmas","year":"2022","journal-title":"arXiv:2203.08101"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref19","first-page":"1","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ging"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"ref21","first-page":"515","article-title":"Learning to decompose and disentangle representations for video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hsieh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref24","first-page":"676","article-title":"Dialog-based interactive image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2473415"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2928180"},{"key":"ref32","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00376"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3138302"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref56","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00448"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10225420.pdf?arnumber=10225420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:53:24Z","timestamp":1712692404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10225420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3306738","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}