{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:18:53Z","timestamp":1783437533207,"version":"3.54.6"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742738"],"award-info":[{"award-number":["2023M742738"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"DOI":"10.13039\/501100001809","name":"Key Scientific Technological Innovation Research Project by the Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3402242","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T18:09:17Z","timestamp":1715969357000},"page":"10507-10520","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Grained Gradual Inference Model for Multimedia Event Extraction"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7446-9336","authenticated-orcid":false,"given":"Long","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, the International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19906"},{"key":"ref3","article-title":"Event extraction: A survey","author":"Lai","year":"2022","journal-title":"arXiv:2210.03419"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/PRML56267.2022.9882203"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.49"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.274"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.492"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.448"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00479"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2764624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1156"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2002831"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3236837"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296196"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102351"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016529"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1629235.1629236"},{"key":"ref23","first-page":"254","article-title":"Refining event extraction through cross-document inference","volume-title":"Proc. ACL, HLT","author":"Ji"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.69"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3194869"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3174873"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2060"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554425"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612526"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00284"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126433"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3289293"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.73"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1522"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428100"},{"key":"ref41","article-title":"Structured prediction as translation between augmented natural languages","author":"Paolini","year":"2021","journal-title":"arXiv:2101.05779"},{"key":"ref42","article-title":"DEGREE: A data-efficient generation-based event extraction model","author":"Hsu","year":"2021","journal-title":"arXiv:2108.12724"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_19"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1033"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00736"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2918852"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3016863"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2918591"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207518"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301827"},{"key":"ref51","article-title":"A knowledge-based hierarchical causal inference network for video action recognition","author":"Liu","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28347"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248271"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193857"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3190135"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3259430"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3119892"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216663"},{"key":"ref59","article-title":"Grounded situation recognition with transformers","author":"Cho","year":"2021","journal-title":"arXiv:2111.10135"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20167"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01904"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1201\/9781003118688"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548283"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_28"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197972"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316077"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220297"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548061"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101989"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3266423"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612401"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25204"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3546971"},{"key":"ref85","article-title":"LLM4VG: Large language models evaluation for video grounding","author":"Feng","year":"2023","journal-title":"arXiv:2312.14206"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6437"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref89","first-page":"178","article-title":"Abstract meaning representation for sembanking","volume-title":"Proc. 7th Linguistic Annotation Workshop Interoperability Discourse","author":"Banarescu"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2141"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref93","first-page":"45","article-title":"ACE 2005 multilingual training corpus","volume":"57","author":"Walker","year":"2005","journal-title":"Linguistic Data Consortium, Philadelphia"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref96","article-title":"Event extraction with generative adversarial imitation learning","author":"Zhang","year":"2018","journal-title":"arXiv:1804.07881"},{"key":"ref97","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref98","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739869\/10533232.pdf?arnumber=10533232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:19:54Z","timestamp":1732666794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10533232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":98,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3402242","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}