{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T19:10:11Z","timestamp":1741374611945,"version":"3.38.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62376069","62236003"],"award-info":[{"award-number":["62376069","62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program through CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515012027"],"award-info":[{"award-number":["2024A1515012027"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091203008"],"award-info":[{"award-number":["ZDSYS20230626091203008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3528394","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:51:08Z","timestamp":1736797868000},"page":"2912-2923","source":"Crossref","is-referenced-by-count":0,"title":["Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-2169","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0247-5221","authenticated-orcid":false,"given":"Jianlong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1390-7424","authenticated-orcid":false,"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuzheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"article-title":"PLLaVA : Parameter-free LLaVA extension from images to videos for video dense captioning","year":"2024","author":"Xu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref6","first-page":"23 634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref8","first-page":"1","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language representation alignment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue"},{"key":"ref9","first-page":"2156","article-title":"M2-RAAP: A multi-modal recipe for advancing adaptation-based pre-training towards effective and efficient zero-shot video-text retrieval","volume-title":"Proc. Int. ACM SIGIR Conf. Res. Develop. Informat. Retrieval","author":"Dong"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3173208"},{"key":"ref11","first-page":"1","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref12","first-page":"1","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref14","first-page":"29 406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318002"},{"key":"ref16","first-page":"1","article-title":"Improving multimodal datasets with image captioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.66"},{"key":"ref18","first-page":"1","article-title":"Tailoring language generation models under total variation distance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ji"},{"key":"ref19","first-page":"1","article-title":"Error norm truncation: Robust training in the presence of data noise for text generation models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref21","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01300"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref25","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref29","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref30","first-page":"1","article-title":"Improving CLIP training with language rewrites","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref31","first-page":"13\u2009320","article-title":"VeCLIP: Improving CLIP training via visual-enriched captions","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lai"},{"key":"ref32","first-page":"12\u2009888","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":"ref33","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","first-page":"1","article-title":"Judging LLM-as-a-judge with MT-bench and Chatbot arena","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","year":"2023","author":"Lin","key":"ref37"},{"article-title":"LLaVA-NeXT: A strong zero-shot video understanding model","year":"2024","author":"Zhang","key":"ref38"},{"article-title":"VideoChat: Chat-centric video understanding","year":"2023","author":"Li","key":"ref39"},{"article-title":"VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners","year":"2023","author":"Yan","key":"ref40"},{"key":"ref41","first-page":"19 730","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"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref43","first-page":"88","article-title":"Text generation by learning from demonstrations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pang"},{"key":"ref44","article-title":"Probability in highDimension","volume-title":"Lecture Notes","author":"Van Handel","year":"2014"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Stat. Learn.: Data Mining, Inference, and Prediction","volume":"2","author":"Hastie","year":"2009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"article-title":"Valley: Video assistant with large language model enhanced ability","year":"2023","author":"Luo","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref50","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"article-title":"LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention","year":"2023","author":"Zhang","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"article-title":"Vista-LLaMA: Reliable video narrator via equal distance to visual tokens","year":"2023","author":"Ma","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref57","first-page":"5696","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612152"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"article-title":"InternVideo: General video foundation models via generative and discriminative learning","year":"2022","author":"Wang","key":"ref61"},{"key":"ref62","first-page":"1","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10839067.pdf?arnumber=10839067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:40:49Z","timestamp":1741372849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":63,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3528394","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}