{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:21Z","timestamp":1778048301953,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00444","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4566-4576","source":"Crossref","is-referenced-by-count":0,"title":["LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling"],"prefix":"10.1109","author":[{"given":"Xianhang","family":"Li","sequence":"first","affiliation":[{"name":"UC Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongru","family":"Zhu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sucheng","family":"Ren","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Yang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cihang","family":"Xie","sequence":"additional","affiliation":[{"name":"UC Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00749"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"ref7","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref9","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01549"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref17","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Scalable pre-training of large autoregressive image models","author":"El-Nouby","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref21","article-title":"Data-comp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"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":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref27","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref29","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01328"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126682"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref41","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref43","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref44","article-title":"Rejuvenating image-gpt as strong vi sual representation learners","author":"Ren","year":"2023"},{"key":"ref45","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018"},{"key":"ref48","article-title":"Stylegan-v: A continuous video generator with the price, image quality and perks of stylegan2","author":"Skorokhodov","year":"2021"},{"key":"ref49","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093290"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref54","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref60","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2022","journal-title":"ICLR"},{"key":"ref61","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475436"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492062.pdf?arnumber=11492062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:42Z","timestamp":1778046822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00444","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}