{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:22:28Z","timestamp":1791303748081,"version":"4.1.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017366","name":"Research and Development Program of Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KZ202210005008"],"award-info":[{"award-number":["KZ202210005008"]}],"id":[{"id":"10.13039\/100017366","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":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3537759","type":"journal-article","created":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T13:33:19Z","timestamp":1738589599000},"page":"5776-5790","source":"Crossref","is-referenced-by-count":3,"title":["Tackling Real-World Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2739-5220","authenticated-orcid":false,"given":"Tengfei","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-438X","authenticated-orcid":false,"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6096-9858","authenticated-orcid":false,"given":"Mingjie","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-0078","authenticated-orcid":false,"given":"Junfei","family":"Yi","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory of Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"ReLER Laboratory, Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-0256","authenticated-orcid":false,"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[{"name":"Discipline of Business Analytics, University of Sydney Business School, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcorpfin.2023.102385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/1748-8583.12523"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25378"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136330"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02000"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3264524"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454366"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424566"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247822"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32248-9_50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00946"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.635"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref31","article-title":"Graph neural network based method for path planning problem","author":"Diao","year":"2023","journal-title":"arXiv:2309.14845"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3603374"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01219"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.climatenlp-1.5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","first-page":"1","article-title":"Gated multimodal units for information fusion","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Arevalo"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref44","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00256"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.41"},{"key":"ref48","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref49","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"ref52","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurlPS)","author":"Zaheer"},{"key":"ref53","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref54","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.107"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10869505.pdf?arnumber=10869505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:02Z","timestamp":1767638522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10869505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3537759","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}