{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:57Z","timestamp":1777865337462,"version":"3.51.4"},"reference-count":103,"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\/iccv51701.2025.02097","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22586-22598","source":"Crossref","is-referenced-by-count":0,"title":["Streaming Videollms for Real-Time Procedural Video Understanding"],"prefix":"10.1109","author":[{"given":"Dibyadip","family":"Chatterjee","sequence":"first","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edoardo","family":"Remelli","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yale","family":"Song","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bugra","family":"Tekin","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhay","family":"Mittal","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bharat","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Necati Cihan","family":"Camg\u00f6z","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shreyas","family":"Hampali","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Sauser","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shugao","family":"Ma","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fadime","family":"Sener","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0722"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2966"},{"key":"ref4","article-title":"Video-mined task graphs for keystep recognition in instructional videos","volume":"36","author":"Ashutosh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref6","article-title":"Peters, and Arman Cohan. Longformer: The long-document transformer","author":"Beltagy","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00430"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1440"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref18","article-title":"Every mistake counts in assembly","author":"Ding","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"ref20","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref31","article-title":"Ruler: What\u2019s the real context size of your longcontext language models?","author":"Hsieh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Edward","year":"2022"},{"key":"ref33","article-title":"Propose, assess, search:Harnessing 11 ms for goaloriented planning in instructional videos","author":"Mohaiminul Islam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","volume-title":"THUMOS challenge: Action recognition with a large number of classes","author":"Jiang","year":"2014"},{"key":"ref35","article-title":"and William Yang Wang. Wikihow: A large scale text summarization dataset","author":"Koupaee","year":"2018","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Human action anticipation: A survey","author":"Lai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01765"},{"key":"ref38","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref42","article-title":"Vedit: Latent prediction architecture for procedural video representation learning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_31"},{"key":"ref50","article-title":"Learning and verification of task structure in instructional videos","author":"Narasimhan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref52","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00813"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"ref55","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Pope","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref57","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"Openai"},{"issue":"8","key":"ref58","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103558"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1895"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_25"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00989"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_33"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1688"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01289"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref75","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref77","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00484"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref82","volume-title":"How to do anything","year":"2005"},{"key":"ref83","article-title":"Videollm-mod: Efficient video-language streaming with mixture-of-depths vision computation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02385-8"},{"key":"ref86","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref87","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222914"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_23"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01278"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref93","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref94","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00295"},{"key":"ref96","article-title":"AntGPT: Can large language models help long-term action anticipation from videos?","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhao","year":"2024"},{"key":"ref97","first-page":"485","article-title":"and Philipp Kr\u00e4henb\u00fchl. Real-time online video detection with temporal smoothing transformers","volume-title":"European Conference on Computer Vision","author":"Zhao","year":"2022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01245"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref102","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00365"}],"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\/11444631.pdf?arnumber=11444631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:25Z","timestamp":1777529845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02097","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}