{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:06Z","timestamp":1777888806512,"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\/iccv51701.2025.01776","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19108-19118","source":"Crossref","is-referenced-by-count":0,"title":["An Empirical Study of Autoregressive Pre-Training from Videos"],"prefix":"10.1109","author":[{"given":"Jathushan","family":"Rajasegaran","sequence":"first","affiliation":[{"name":"Meta FAIR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilija","family":"Radosavovic","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Ravishankar","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Gandelsman","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Feichtenhofer","sequence":"additional","affiliation":[{"name":"Meta FAIR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[{"name":"Meta FAIR"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/h0054663"},{"key":"ref3","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","first-page":"99129924","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref10","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding."},{"key":"ref14","article-title":"Scalable pretraining of large autoregressive image models","author":"El-Nouby","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref17","article-title":"Data filtering networks","author":"Fang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2605"},{"key":"ref20","article-title":"Cater: A diagnostic dataset for compositional actions and temporal reasoning","author":"Girdhar","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref23","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref26","article-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume":"33","author":"Jabri","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref29","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Boesen","year":"2016"},{"key":"ref31","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Lee","year":"2019"},{"key":"ref32","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"2630","article-title":"Howto 100 m: Learning a text-video embedding by watching hundred million narrated video clips","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Miech","year":"2019"},{"key":"ref35","article-title":"Incontext learning and induction heads","author":"Olsson","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"4055","article-title":"Image transformer","volume-title":"International conference on machine learning","author":"Parmar","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1037\/11168-000"},{"key":"ref39","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref40","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training."},{"key":"ref41","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners."},{"key":"ref42","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2022"},{"key":"ref43","article-title":"Robot learning with sensorimotor pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00371"},{"key":"ref45","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref46","article-title":"Video (language) modeling: a baseline for generative models of natural videos","author":"Ranzato","year":"2014","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref49","article-title":"Hiera: A hierarchical vision transformer without the bells-andwhistles","author":"Ryali","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1951.tb01366.x"},{"key":"ref52","article-title":"Glu variants improve transformer","author":"Shazeer","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref55","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref57","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref61","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Scaling autoregressive video models","author":"Weissenborn","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref64","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref65","author":"Yang","year":"2022","journal-title":"Tensor programs v: Tuning large neural networks via zero-shot hyperparameter transfer"},{"key":"ref66","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref67","article-title":"Tfcnet: Temporal fully connected networks for static unbiased temporal reasoning","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","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\/11445741.pdf?arnumber=11445741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:05Z","timestamp":1777611425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01776","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}