{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T04:38:04Z","timestamp":1791261484840,"version":"4.1.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2039"],"award-info":[{"award-number":["U19B2039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research and Development Program of Beijing Municipal Education Commission","award":["KZ202210005008"],"award-info":[{"award-number":["KZ202210005008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3366935","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T20:21:08Z","timestamp":1708374068000},"page":"6376-6390","source":"Crossref","is-referenced-by-count":11,"title":["Hierarchical Multi-Modal Prompting Transformer for Multi-Modal Long Document Classification"],"prefix":"10.1109","volume":"34","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, Faculty of Information 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, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"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, The University of Sydney Business School, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0872-384X","authenticated-orcid":false,"given":"Yanfeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"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, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/16168658.2021.2019430"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"},{"key":"ref13","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Nagrani"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref17","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv:2201.02184"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185295"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"LongFormer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref26","first-page":"17283","article-title":"Big Bird: Transformers for longer sequences","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurlPS)","author":"Zaheer"},{"key":"ref27","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Kitaev"},{"key":"ref28","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3264524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136330"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref36","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020","journal-title":"arXiv:2004.00849"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref40","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref41","article-title":"Learning domain invariant prompt for vision-language models","author":"Zhao","year":"2022","journal-title":"arXiv:2212.04196"},{"key":"ref42","article-title":"Multitask vision-language prompt tuning","author":"Shen","year":"2022","journal-title":"arXiv:2211.11720"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref44","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"ref46","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Yang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1408"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.107"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.01992"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"ref59","first-page":"1","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10439279.pdf?arnumber=10439279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T04:44:09Z","timestamp":1720241049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10439279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":59,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3366935","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}