{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:20:18Z","timestamp":1785334818744,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Scientific Technological Innovation Research Project by the Ministry of Education"},{"DOI":"10.13039\/501100001809","name":"State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836009"],"award-info":[{"award-number":["61836009"]}],"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":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"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":["62006177"],"award-info":[{"award-number":["62006177"]}],"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":["61902298"],"award-info":[{"award-number":["61902298"]}],"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":["61573267"],"award-info":[{"award-number":["61573267"]}],"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":["61906150"],"award-info":[{"award-number":["61906150"]}],"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":["62276199"],"award-info":[{"award-number":["62276199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT 15R53"],"award-info":[{"award-number":["IRT 15R53"]}]},{"name":"Science and Technology (ST) Innovation Project from the Chinese Ministry of Education"},{"name":"Key Research and Development Program in Shaanxi Province of China","award":["2019ZDLGY03-06"],"award-info":[{"award-number":["2019ZDLGY03-06"]}]},{"name":"National Science Basic Research Plan in Shaanxi Province of China","award":["2022JQ-607"],"award-info":[{"award-number":["2022JQ-607"]}]},{"name":"China Postdoctoral Fund","award":["2022T150506"],"award-info":[{"award-number":["2022T150506"]}]},{"name":"Scientific Research Project of Education Department in Shaanxi Province of China","award":["20JY023"],"award-info":[{"award-number":["20JY023"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["zyts23066"],"award-info":[{"award-number":["zyts23066"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3322470","type":"journal-article","created":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T18:02:58Z","timestamp":1696615378000},"page":"3819-3833","source":"Crossref","is-referenced-by-count":21,"title":["MBSI-Net: Multimodal Balanced Self-Learning Interaction Network for Image Classification"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6802-539X","authenticated-orcid":false,"given":"Mengru","family":"Ma","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8872-2195","authenticated-orcid":false,"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4796-5737","authenticated-orcid":false,"given":"Shuyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3015691"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4018\/joeuc.20211101.oa6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547924"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3148257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197420"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125995"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02064-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3187025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2768386"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2911113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3090585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3274545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3045474"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3053062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3130716"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3082289"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3156646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3273577"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3118221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20267"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2750220"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3064571"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.12.008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121490"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3170312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414517"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3224068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073673"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975566"},{"key":"ref35","article-title":"Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing","author":"Mikriukov","year":"2022","journal-title":"arXiv:2201.08125"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01235"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109872"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/187"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"An image is worth 16 \u2717 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref41","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01732"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074414"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168192"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02166-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108833"},{"key":"ref49","article-title":"Multimodal adaptive distillation for leveraging unimodal encoders for vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2204.10496"},{"key":"ref50","first-page":"24261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2810267"},{"key":"ref52","article-title":"Visual recognition with deep nearest centroids","author":"Wang","year":"2022","journal-title":"arXiv:2209.07383"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_42"},{"key":"ref54","first-page":"1","article-title":"DeepNCM: Deep nearest class mean classifiers","volume-title":"Proc. ICLR","author":"Guerriero"},{"key":"ref55","article-title":"CLUSTSEG: Clustering for universal segmentation","author":"Liang","year":"2023","journal-title":"arXiv:2305.02187"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/s22218116"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-181922"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106114"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272826"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10035-z"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3171290"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11634-020-00394-8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.29220\/CSAM.2021.28.2.161"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3177607"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3048792"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10273708.pdf?arnumber=10273708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:34:18Z","timestamp":1715362458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10273708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":70,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3322470","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}