{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:46Z","timestamp":1777865326602,"version":"3.51.4"},"reference-count":68,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02071","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22305-22315","source":"Crossref","is-referenced-by-count":0,"title":["ResidualViT for Efficient Temporally Dense Video Encoding"],"prefix":"10.1109","author":[{"given":"Mattia","family":"Soldan","sequence":"first","affiliation":[{"name":"KAUST, King Abdullah University of Science and Technology."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian Caba","family":"Heilbron","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[{"name":"KAUST, King Abdullah University of Science and Technology."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[{"name":"CIIRC CTU, Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Russell","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"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":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref4","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","article-title":"Fitclip: Refining large-scale pretrained image-text models for zero-shot video understanding tasks","author":"Castro","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Scaling vision transformers to 22 billion parameters","author":"Dehghani","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01554"},{"key":"ref10","first-page":"10","article-title":"Zero-shot video moment retrieval with off-the-shelf models","volume-title":"Trans-fer Learning for Natural Language Processing Workshop","author":"Diwan","year":"2023"},{"key":"ref11","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","year":"2020","journal-title":"fvcore"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0731"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00495"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01815"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0666"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.262"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1704.04861"},{"key":"ref27","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref29","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-1-4842-6168-2_11","volume-title":"Mobilenetv3. In Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization","author":"Koonce","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref34","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00247"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00394"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref44","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"issue":"8","key":"ref50","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref53","article-title":"How much can clip benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Transforming clip to an open-vocabulary video model via interpolated weight optimization","author":"Weng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref65","article-title":"Clip-vip: Adapting pretrained image-text model to video-language representation alignment","author":"Xue","year":"2022","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref68","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","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\/11446277.pdf?arnumber=11446277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:36Z","timestamp":1777529796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02071","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}