{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T21:57:34Z","timestamp":1780351054873,"version":"3.54.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Science and Technology of China","award":["2020AAA0108401"],"award-info":[{"award-number":["2020AAA0108401"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072026"],"award-info":[{"award-number":["62072026"]}],"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":["72225011"],"award-info":[{"award-number":["72225011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2022XKRC015"],"award-info":[{"award-number":["2022XKRC015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Open Research Fund of the State Key Laboratory of Multimodal Artificial Intelligence Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Association for Artificial Intelligence (CAAI)-Compute Architecture for Neural Networks (CANN) Open Fund, Developed on OpenI Community"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3437437","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:42:36Z","timestamp":1722620556000},"page":"12425-12436","source":"Crossref","is-referenced-by-count":4,"title":["Entity Dependency Learning Network With Relation Prediction for Video Visual Relation Detection"],"prefix":"10.1109","volume":"34","author":[{"given":"Guoguang","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4314-7550","authenticated-orcid":false,"given":"Yepeng","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-8995","authenticated-orcid":false,"given":"Chunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0405-5458","authenticated-orcid":false,"given":"Xiaolong","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems and the State Key Laboratory of Management and Control for Complex System, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277621"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277827"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01085"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068214"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref17","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Dong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12274"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356076"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351058"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01067"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s21093164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01827"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"ref30","doi-asserted-by":"crossref","first-page":"3072","DOI":"10.1109\/TAI.2023.3339593","article-title":"Semantic coherence guided multiview similarity for image classification with varied supervision","volume":"5","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3329457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2875728"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214431"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120319"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3185252"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183646"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281475"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3296901"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3381823"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094533"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920783"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2934576"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903628"},{"key":"ref46","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref47","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref48","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3388004"},{"key":"ref52","first-page":"1","article-title":"Disentangled counterfactual learning for physical audiovisual commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378477"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103141"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295090"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28516"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3413599"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref63","article-title":"Word embeddings: A survey","author":"Almeida","year":"2019","journal-title":"arXiv:1901.09069"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413764"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475540"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.029"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01323"},{"key":"ref74","article-title":"What and when to look: Temporal span proposal network for video relation detection","author":"Woo","year":"2021","journal-title":"arXiv:2107.07154"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109430"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338078"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270328"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10621651.pdf?arnumber=10621651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:39:59Z","timestamp":1734982799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":78,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3437437","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}