{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T07:31:28Z","timestamp":1783582288931,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["62306171"],"award-info":[{"award-number":["62306171"]}],"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":["62136005"],"award-info":[{"award-number":["62136005"]}],"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":["62406218"],"award-info":[{"award-number":["62406218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112400"],"award-info":[{"award-number":["2021ZD0112400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Major Project of Shanxi","award":["202201020101006"],"award-info":[{"award-number":["202201020101006"]}]},{"name":"Young Scientists Fund of the Natural Science Foundation of Shanxi","award":["202203021222183"],"award-info":[{"award-number":["202203021222183"]}]},{"name":"Young Scientists Fund of the Natural Science Foundation of Shanxi","award":["20210302124549"],"award-info":[{"award-number":["20210302124549"]}]},{"name":"Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province","award":["CICIP2023005"],"award-info":[{"award-number":["CICIP2023005"]}]},{"name":"Science and Technology Innovation Plan for Colleges and Universities of Shanxi Province","award":["2022L296"],"award-info":[{"award-number":["2022L296"]}]},{"name":"Taiyuan University of Science and Technology Doctoral Research Start-Up Fund Project","award":["20222106"],"award-info":[{"award-number":["20222106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3470996","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:31:23Z","timestamp":1727703083000},"page":"1070-1083","source":"Crossref","is-referenced-by-count":8,"title":["Multi-Scale Features Are Effective for Multi-Modal Classification: An Architecture Search Viewpoint"],"prefix":"10.1109","volume":"35","author":[{"given":"Pinhan","family":"Fu","sequence":"first","affiliation":[{"name":"Institute of Big Data Science and Industry, Shanxi University, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2589-5392","authenticated-orcid":false,"given":"Xinyan","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Big Data Science and Industry, Shanxi University, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6772-4247","authenticated-orcid":false,"given":"Yuhua","family":"Qian","sequence":"additional","affiliation":[{"name":"Institute of Big Data Science and Industry, Shanxi University, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9189-7834","authenticated-orcid":false,"given":"Qian","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6529-8104","authenticated-orcid":false,"given":"Yayu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Big Data Science and Industry, Shanxi University, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0570-941X","authenticated-orcid":false,"given":"Qin","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Big Data Science and Industry, Shanxi University, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6236-2002","authenticated-orcid":false,"given":"Ke","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shenzhen Key Laboratory of Computational Intelligence, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3260349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3064943"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3243521"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037734"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.03.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113183"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3193569"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.01578"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_32"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3272663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59728-3_74"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29281"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20872"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref18","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/2200000119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17260"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3192635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082939"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3028422"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3351933"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366935"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275814"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015424"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2808769"},{"key":"ref39","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref43","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.4400"},{"key":"ref45","first-page":"1185","article-title":"Sparse feature learning for deep belief networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ranzato"},{"key":"ref46","article-title":"Pooling methods in deep neural networks, a review","author":"Gholamalinezhad","year":"2020","journal-title":"arXiv:2009.07485"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.01992"},{"key":"ref48","first-page":"III-1319","article-title":"Maxout networks","volume-title":"Proc. 30th Int. Conf. Int. Conf. Mach. Learn.","volume":"28","author":"Goodfellow"},{"key":"ref49","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00126"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00040"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087348"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10700772.pdf?arnumber=10700772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:41Z","timestamp":1767638501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3470996","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}