{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:10:41Z","timestamp":1776057041879,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021XD-A01-1"],"award-info":[{"award-number":["2021XD-A01-1"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202049"],"award-info":[{"award-number":["4202049"]}],"id":[{"id":"10.13039\/501100004826","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":[[2023,3]]},"DOI":"10.1109\/tcsvt.2022.3207910","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:16:23Z","timestamp":1663618583000},"page":"1438-1453","source":"Crossref","is-referenced-by-count":28,"title":["Temporal Multimodal Graph Transformer With Global-Local Alignment for Video-Text Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3987-0591","authenticated-orcid":false,"given":"Zerun","family":"Feng","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Zhimin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-4520","authenticated-orcid":false,"given":"Caili","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Laboratory of Advanced Information Networks, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2535-2523","authenticated-orcid":false,"given":"Zheng","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014889"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3131721"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578746"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.341"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/140"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref14","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018","journal-title":"arXiv:1804.02516"},{"key":"ref15","first-page":"279","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref17","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Patrick"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475703"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506267"},{"key":"ref23","article-title":"Simple BERT models for relation extraction and semantic role labeling","author":"Shi","year":"2019","journal-title":"arXiv:1904.05255"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref26","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref27","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"Karpathy","year":"2014","journal-title":"arXiv:1406.5679"},{"key":"ref28","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref29","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref42","first-page":"1","article-title":"DeBERTa: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"He"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.10.005"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/S1930297500002205"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref52","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_27"},{"key":"ref55","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014","journal-title":"arXiv:1406.2227"},{"key":"ref56","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932005"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028289"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023609"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107562"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10061510\/09895256.pdf?arnumber=9895256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:47:33Z","timestamp":1705960053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9895256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":64,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3207910","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}