{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:56Z","timestamp":1775815196999,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFC2009903"],"award-info":[{"award-number":["2022YFC2009903"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFC2009900"],"award-info":[{"award-number":["2022YFC2009900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61872064"],"award-info":[{"award-number":["61872064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2022119"],"award-info":[{"award-number":["2022119"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004806","name":"Fok Ying Tong Education Foundation","doi-asserted-by":"publisher","award":["171106"],"award-info":[{"award-number":["171106"]}],"id":[{"id":"10.13039\/501100004806","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Songshan Laboratory","award":["YYJC012022019"],"award-info":[{"award-number":["YYJC012022019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3323491","type":"journal-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T14:52:28Z","timestamp":1703170348000},"page":"1092-1103","source":"Crossref","is-referenced-by-count":19,"title":["Visual Commonsense-Aware Representation Network for Video Captioning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"first","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1015-7338","authenticated-orcid":false,"given":"Haonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3495636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCICT50803.2021.9510102"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475241"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475301"},{"key":"ref5","first-page":"1","article-title":"Human\u2013computer interaction","volume-title":"Proc. Harlow UA","author":"Dix"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref14","first-page":"1","article-title":"Multi-modal dependency tree for video captioning","volume-title":"Proc. NeurIPS","volume":"34","author":"Zhao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462989"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.43"},{"key":"ref18","first-page":"1835","article-title":"Ask&Confirm: Active detail enriching for cross-modal retrieval with partial query","volume-title":"Proc. ICCV","author":"Cai"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01090"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475519"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017530"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475326"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref36","article-title":"Image captioning for effective use of language models in knowledge-based visual question answering","author":"Salaberria","year":"2021","journal-title":"arXiv:2109.08029"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00036"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6731"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.122"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref57","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. ACL","author":"Chen"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref61","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. ACL","author":"Papineni"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref63","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref67","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv:1512.01274"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref69","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref71","first-page":"1","article-title":"A neural compositional paradigm for image captioning","volume-title":"Proc. NeurIPS","volume":"31","author":"Dai"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10368165.pdf?arnumber=10368165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:17Z","timestamp":1764959957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10368165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":75,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3323491","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}