{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:47:12Z","timestamp":1778255232431,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["62125201"],"award-info":[{"award-number":["62125201"]}],"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":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"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":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3277827","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T18:10:47Z","timestamp":1684779047000},"page":"4484-4495","source":"Crossref","is-referenced-by-count":21,"title":["Concept Parser With Multimodal Graph Learning for Video Captioning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4539-4854","authenticated-orcid":false,"given":"Bofeng","family":"Wu","sequence":"first","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Buyu","family":"Liu","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Princeton, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5727-2790","authenticated-orcid":false,"given":"Peng","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Jun","family":"Bao","sequence":"additional","affiliation":[{"name":"Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, China"}]},{"given":"Peng","family":"Xi","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref57","article-title":"Support-set bottlenecks for video-text representation learning","author":"patrick","year":"2020","journal-title":"arXiv 2010 02824"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref58","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19945"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref55","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3131721"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref51","article-title":"VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners","author":"yan","year":"2022","journal-title":"arXiv 2212 04979"},{"key":"ref50","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"luo","year":"2020","journal-title":"arXiv 2002 06353"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref45","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"bertasius","year":"2021","journal-title":"Proc ICML"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref42","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"wang","year":"2022","journal-title":"arXiv 2205 14100"},{"key":"ref41","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"li","year":"2023","journal-title":"arXiv 2301 12597"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref43","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6731"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref33","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref1","article-title":"SwinBERT: End-to-end transformers with sparse attention for video captioning","author":"lin","year":"2021","journal-title":"arXiv 2111 13196"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/877"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref22","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc 49th Annu Meeting Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2956593"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10130340.pdf?arnumber=10130340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:43:31Z","timestamp":1695667411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":61,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3277827","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}