{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:32:17Z","timestamp":1780763537014,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ21017"],"award-info":[{"award-number":["JQ21017"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972397"],"award-info":[{"award-number":["61972397"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036011"],"award-info":[{"award-number":["62036011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192782"],"award-info":[{"award-number":["62192782"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2033210"],"award-info":[{"award-number":["U2033210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial University Innovation Team Project","award":["2020KCXTD045"],"award-info":[{"award-number":["2020KCXTD045"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3299932","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:45:03Z","timestamp":1690825503000},"page":"2041-2055","source":"Crossref","is-referenced-by-count":1,"title":["DARTScore: DuAl-Reconstruction Transformer for Video Captioning Evaluation"],"prefix":"10.1109","volume":"34","author":[{"given":"Yuxin","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8298-4063","authenticated-orcid":false,"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"ARC Laboratory, Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-4961","authenticated-orcid":false,"given":"Chunfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"IPS Search, Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Laboratory, Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5888-6735","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9237-8825","authenticated-orcid":false,"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohu","family":"Qie","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165934"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref7","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019","journal-title":"arXiv:1904.09675"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.93"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01383"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058555"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058626"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2956593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551581"},{"key":"ref19","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01740"},{"key":"ref26","article-title":"From images to sentences through scene description graphs using commonsense reasoning and knowledge","author":"Aditya","year":"2015","journal-title":"arXiv:1511.03292"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref31","first-page":"139","article-title":"Collecting image annotations using Amazon\u2019s mechanical Turk","volume-title":"Proc. NAACL HLT Workshop Creating Speech Lang. Data Amazon\u2019s Mech. Turk","author":"Rashtchian"},{"key":"ref32","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref39","article-title":"CREATE: A benchmark for Chinese short video retrieval and title generation","author":"Zhang","year":"2022","journal-title":"arXiv:2203.16763"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10197520.pdf?arnumber=10197520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:52:09Z","timestamp":1712692329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10197520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3299932","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}