{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:00:09Z","timestamp":1779886809299,"version":"3.53.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["2022YFC3321003"],"award-info":[{"award-number":["2022YFC3321003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302501"],"award-info":[{"award-number":["62302501"]}],"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":["62192782"],"award-info":[{"award-number":["62192782"]}],"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":["62036011"],"award-info":[{"award-number":["62036011"]}],"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":["62122086"],"award-info":[{"award-number":["62122086"]}],"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":["U2033210"],"award-info":[{"award-number":["U2033210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223003"],"award-info":[{"award-number":["L223003"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"name":"Project of Beijing Science and Technology Committee","award":["Z231100005923046"],"award-info":[{"award-number":["Z231100005923046"]}]},{"name":"Key Research and Development Program Foundation of Xinjiang Autonomous Region of China","award":["2023B01005"],"award-info":[{"award-number":["2023B01005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3365739","type":"journal-article","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:44:10Z","timestamp":1707936250000},"page":"5192-5208","source":"Crossref","is-referenced-by-count":2,"title":["Chinese Title Generation for Short Videos: Dataset, Metric and Algorithm"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5937-183X","authenticated-orcid":false,"given":"Ziqi","family":"Zhang","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"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1980-9379","authenticated-orcid":false,"given":"Zongyang","family":"Ma","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\/0000-0003-2219-4961","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7854-1072","authenticated-orcid":false,"given":"Yuxin","family":"Chen","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\/0000-0002-0371-5584","authenticated-orcid":false,"given":"Peijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, 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 Lab at Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6583-3877","authenticated-orcid":false,"given":"Chenglei","family":"Hao","sequence":"additional","affiliation":[{"name":"Huake Xingsheng Electric Power Engineering Technology, Beijing, 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\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab at Tencent PCG, Shenzhen, 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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2113-9119","authenticated-orcid":false,"given":"Stephen","family":"Maybank","sequence":"additional","affiliation":[{"name":"Computer Science and Information Systems, Birkbeck College, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref6","first-page":"6634","article-title":"Multi-modal dependency tree for video captioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01741"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475519"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref16","article-title":"VALUE: A multi-task benchmark for video-and-language understanding evaluation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01383"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01740"},{"key":"ref21","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403325"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_38"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413880"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475431"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref36","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"issue":"8","key":"ref37","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref39","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref41","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330725"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1230"},{"key":"ref48","first-page":"1017","article-title":"Generating text with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref49","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/n15-1173"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240677"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_42"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.157"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018965"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475179"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref74","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref76","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref77","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref78","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref79","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"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref81","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref82","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% chatgpt quality","author":"Chiang","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10436633.pdf?arnumber=10436633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:55:36Z","timestamp":1719345336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10436633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":82,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3365739","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}