{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:05Z","timestamp":1777889105930,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01936","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20824-20835","source":"Crossref","is-referenced-by-count":0,"title":["MobileViCLIP: An Efficient Video-Text Model for Mobile Devices"],"prefix":"10.1109","author":[{"given":"Min","family":"Yang","sequence":"first","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Jia","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilin","family":"Dai","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Guo","sequence":"additional","affiliation":[{"name":"MyBank, Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref4","first-page":"4","author":"Bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding? In ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref12","article-title":"Democratizing contrastive language-image pretraining: A clip benchmark of data, model, and supervision","author":"Cui","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref15","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","article-title":"Violet: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"36","author":"Gadre","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref21","article-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref25","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref27","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref29","article-title":"Learning spatiotemporal features via video and text pair discrimination","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01771"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"In Text summarization branches out"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","article-title":"Fixing weight decay regularization in adam","volume":"5","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref40","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref42","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref44","volume-title":"Parameter-efficient image-tovideo transfer learning for action recognition","author":"Pan","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref49","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00127"},{"key":"ref52","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Eva-clip18b: Scaling clip to 18 billion parameters","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref56","first-page":"5785","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","volume-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Vasu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref62","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Fastclip: A suite of optimization techniques to accelerate clip training with limited resources","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01757"},{"key":"ref71","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Videoprism: A foundational visual encoder for video understanding","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Repnext: A fast multi-scale cnn using structural reparameterization","author":"Zhao","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444448.pdf?arnumber=11444448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:07Z","timestamp":1777612027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01936","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}