{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T01:02:32Z","timestamp":1774400552664,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62176187"],"award-info":[{"award-number":["62176187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Laboratory for Advanced Computing and Intelligence Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3609288","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:31:21Z","timestamp":1757611881000},"page":"807-823","source":"Crossref","is-referenced-by-count":0,"title":["M$^{3}$3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5815-135X","authenticated-orcid":false,"given":"Jiang","family":"Liu","sequence":"first","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-5540","authenticated-orcid":false,"given":"Bobo","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Foreign Languages and Literature, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Foreign Languages and Literature, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1816-1761","authenticated-orcid":false,"given":"Fei","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9613-5927","authenticated-orcid":false,"given":"Donghong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.215"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29919"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.372"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995551"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bionlp-1.2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.218"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01399"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26309"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1074"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.422"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.473"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"key":"ref27","first-page":"285","article-title":"GRAVL-BERT: Graphical visual-linguistic representations for multimodal coreference resolution","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Guo"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.376"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.823"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1373"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00175"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.189"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"ref44","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00064"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref49","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3430545"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty"},{"key":"ref54","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref55","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref57","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref60","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref61","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.197"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11159622.pdf?arnumber=11159622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:31:36Z","timestamp":1774398696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11159622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":66,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3609288","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}