{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:28:58Z","timestamp":1784737738534,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371343"],"award-info":[{"award-number":["62371343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535394","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:54:42Z","timestamp":1737986082000},"page":"4584-4596","source":"Crossref","is-referenced-by-count":4,"title":["Vision-Language Relational Transformer for Video-to-Text Generation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2244-0567","authenticated-orcid":false,"given":"Tengpeng","family":"Li","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1519-0914","authenticated-orcid":false,"given":"Qinyu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3682-6288","authenticated-orcid":false,"given":"Zhangkai","family":"Ni","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3303083"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"ref11","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref12","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref16","article-title":"GLM-130B: An open bilingual pre-trained model","author":"Zeng","year":"2022"},{"key":"ref17","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref18","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref20","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230934"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.04.013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058555"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183402"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936526"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref39","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref42","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref46","article-title":"Taking an emotional look at video paragraph captioning","author":"Li","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref48","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Assoc. Comput. Linguistics Workshop","author":"Banerjee","year":"2005"},{"key":"ref49","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Assoc. Comput. Linguistics Workshop","author":"Lin","year":"2004"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref56","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.29"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897766"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10855568.pdf?arnumber=10855568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T18:15:29Z","timestamp":1754072129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535394","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}