{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:28Z","timestamp":1777888948111,"version":"3.51.4"},"reference-count":42,"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\/iccv51701.2025.01987","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21398-21407","source":"Crossref","is-referenced-by-count":0,"title":["LV-MAE: Learning Long Video Representations Through Masked-Embedding Autoencoders"],"prefix":"10.1109","author":[{"given":"Ilan","family":"Naiman","sequence":"first","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuel","family":"Ben-Baruch","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oron","family":"Anschel","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alon","family":"Shoshan","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Kviatkovsky","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manoj","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G\u00e9rard","family":"Medioni","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Introducing claude 3.5 sonnet. Anthropic News"},{"key":"ref2","article-title":"BEit: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref5","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"ref9","volume-title":"Finevideo","author":"Farr\u00e9","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref11","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref12","article-title":"Turbo training with token dropout","volume-title":"British Machine Vision Conference","author":"Han"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref16","article-title":"Videograph: Recognizing minutes-long human activities in videos","author":"Hussein","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"ref18","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"ArXiv, abs\/1705.06950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref20","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"International conference on machine learning","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1039"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref24","article-title":"Video-llava: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"ArXiv, abs\/2311"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref27","article-title":"Efficient estimation of word representations in vector space","volume-title":"arXiv preprint","author":"Mikolov","year":"2013"},{"key":"ref28","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01398"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3263387"},{"key":"ref34","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"ArXiv, abs\/2403.15377"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref36","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"ArXiv, abs\/2404"},{"key":"ref37","article-title":"Clip-vip: Adapting pretrained image-text model to video-language alignment","volume-title":"International Conference on Learning Representations","author":"Xue"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref39","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref41","article-title":"LanguageBind: Extending video-language pretraining to n modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu"},{"key":"ref42","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"ArXiv, abs\/2401"}],"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\/11445905.pdf?arnumber=11445905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:20Z","timestamp":1777611800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01987","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}