{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T06:20:52Z","timestamp":1781072452904,"version":"3.54.1"},"reference-count":84,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006"],"award-info":[{"award-number":["62032006"]}],"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":["62102092"],"award-info":[{"award-number":["62102092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3357503","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T20:47:39Z","timestamp":1706042859000},"page":"4747-4762","source":"Crossref","is-referenced-by-count":19,"title":["Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5807","authenticated-orcid":false,"given":"Zuxuan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9706-6484","authenticated-orcid":false,"given":"Zejia","family":"Weng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6428-276X","authenticated-orcid":false,"given":"Wujian","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-241X","authenticated-orcid":false,"given":"Xitong","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4795-8374","authenticated-orcid":false,"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"Simular AI, San Mateo, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Larry S.","family":"Davis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1099"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0983-5"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. IEEE Int. Conf. Mach. Learn. Appl.","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref7","article-title":"Bridging clip and stylegan through latent alignment for image editing","author":"Zheng","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref9","article-title":"AI-generated content (AIGC) for various data modalities: A survey","author":"Foo","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref12","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20610"},{"key":"ref14","first-page":"31716","article-title":"CLIPood: Generalizing CLIP to out-of-distributions","volume-title":"Proc. IEEE Int. Conf. Mach. Learn. Appl.","author":"Shu"},{"key":"ref15","first-page":"35087","article-title":"Delving into out-of-distribution detection with vision-language representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ming"},{"key":"ref16","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref18","article-title":"One pass ImageNet","author":"Hu","year":"2021"},{"key":"ref19","article-title":"The effectiveness of memory replay in large scale continual learning","author":"Balaji","year":"2020"},{"key":"ref20","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref21","first-page":"36978","article-title":"Open-VCLIP: Transforming clip to an open-vocabulary video model via interpolated weight optimization","volume-title":"Proc. IEEE Int. Conf. Mach. Learn. Appl.","author":"Weng"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn. Appl.","author":"Jia"},{"key":"ref28","article-title":"Open-vocabulary image segmentation","author":"Ghiasi","year":"2021"},{"key":"ref29","first-page":"3762","article-title":"Orthogonal gradient descent for continual learning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Farajtabar"},{"key":"ref30","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref31","article-title":"Continual learning with second-order loss approximation","author":"Yin","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref33","article-title":"A survey on video diffusion models","author":"Xing","year":"2023"},{"key":"ref34","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. Appl.","author":"Li"},{"key":"ref35","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. Appl.","author":"Li"},{"key":"ref36","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref37","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref38","article-title":"FuseCap: Leveraging large language models to fuse visual data into enriched image captions","author":"Rotstein","year":"2023"},{"key":"ref39","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref40","article-title":"CapText: Large language model-based caption generation from image context and description","author":"Ghosh","year":"2023"},{"key":"ref41","article-title":"ChatGPT Asks, BLIP-2 answers: Automatic questioning towards enriched visual descriptions","author":"Zhu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref45","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bulat"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01804"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3572776"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"ref50","first-page":"29262","article-title":"Patching open-vocabulary models by interpolating weights","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ilharco"},{"key":"ref51","article-title":"Clip model is an efficient continual learner","author":"Thengane","year":"2022"},{"key":"ref52","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref54","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00047"},{"key":"ref56","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"Bishay","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16276"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01935"},{"key":"ref62","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"ref63","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref65","first-page":"26462","article-title":"ST-Adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref69","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ordonez"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref74","article-title":"LAION-400M: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref75","first-page":"5843","article-title":"The \u201csomething something","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Goyal"},{"key":"ref76","article-title":"UniFormerV2: Spatiotemporal learning by arming image ViTs with video uniformer","author":"Li","year":"2022"},{"key":"ref77","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":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref80","article-title":"Aquilachat2","year":"2023"},{"key":"ref81","article-title":"Phoenix: Democratizing chatgpt across languages","author":"Chen","year":"2023"},{"key":"ref82","article-title":"GLM-130B: An open bilingual pre-trained model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref83","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* chatgpt quality","year":"2023"},{"key":"ref84","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zheng"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10412661.pdf?arnumber=10412661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:58:25Z","timestamp":1719345505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10412661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":84,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3357503","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]]}}}