{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:15:18Z","timestamp":1766128518861,"version":"3.48.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172022"],"award-info":[{"award-number":["62172022"]}],"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":["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":["62572017"],"award-info":[{"award-number":["62572017"]}],"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":["62476179"],"award-info":[{"award-number":["62476179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3608295","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:47:24Z","timestamp":1757526444000},"page":"8981-8994","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Multi-Modal Transformer for Cross-Modal Long Document Classification"],"prefix":"10.1109","volume":"27","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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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 School of Information Science and Technology Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.470"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.160"},{"article-title":"Longformer: The long-document transformer","year":"2020","author":"Beltagy","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3316\/QRJ0902027"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772731"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","first-page":"5754","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"key":"ref10","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.29"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109419"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21366"},{"key":"ref23","article-title":"Linformer: Self-attention with linear complexity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13350"},{"key":"ref25","first-page":"12437","article-title":"Poolingformer: Long document modeling with pooling attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50417-5_29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00227"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01935"},{"key":"ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.10.030"},{"key":"ref37","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Yang","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1408"},{"key":"ref46","article-title":"Gated multimodal units for information fusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Arevalo","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref51","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.41"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11155132.pdf?arnumber=11155132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:11:36Z","timestamp":1766128296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11155132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3608295","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}