{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:42:23Z","timestamp":1783438943656,"version":"3.54.6"},"reference-count":69,"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\/iccv51701.2025.00598","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6342-6352","source":"Crossref","is-referenced-by-count":1,"title":["Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding"],"prefix":"10.1109","author":[{"given":"Yue","family":"Fan","sequence":"first","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojian","family":"Ma","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongpeng","family":"Su","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rujie","family":"Wu","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00170"},{"key":"ref7","article-title":"Clova: A closed-loop visual assistant with tool usage and update","author":"Gao","year":"2023","journal-title":"CVPR"},{"key":"ref8","article-title":"Mindagent: Emergent gaming interaction","author":"Gong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3675320"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680679"},{"key":"ref15","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2024","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref18","article-title":"Lemma: A multi-view dataset for le arning m ulti-agent m ulti-task a ctivities","author":"Jia","year":"2020","journal-title":"ECCV"},{"key":"ref19","article-title":"Egotaskqa: Understanding human tasks in egocentric videos","author":"Jia","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref25","article-title":"Egocentric video-language pretraining","author":"Lin","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Best practices and lessons learned on synthetic data","volume-title":"First Conference on Language Modeling","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2023","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref33","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","author":"Mangalam","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref35","article-title":"OpenAI. Gpt-4 technical report","year":"2023","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","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref40","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Conceptagent: Llm-driven precondition grounding and tree search for robust task planning and execution","author":"Rivera","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref44","article-title":"Scene representation networks: Continuous 3d-structureaware neural scene representations","author":"Sitzmann","year":"2019","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref46","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","author":"Szot","year":"2021","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref48","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref51","article-title":"Lstp: Language-guided spatial-temporal prompt learning for long-form video-text understanding","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref52","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3511593"},{"key":"ref54","article-title":"Omnijarvis: Unified vision-language-action tokenization enables open-world instruction following agents","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Compressed vision for efficient video understanding","author":"Wiles","year":"2022","journal-title":"ACCV"},{"key":"ref56","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref59","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Doraemongpt: Toward understanding dynamic scenes with large language models (exemplified as a video agent)","author":"Yang","year":"2024","journal-title":"ICML"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref62","article-title":"Worldqa: Multimodal world knowledge in videos through long-chain reasoning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Mmicl: Empowering vision-language model with multi-modal in-context learning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02071"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01840"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"},{"key":"ref69","article-title":"Move to understand a3d scene: Bridging visual grounding and exploration for efficient and versatile embodied navigation","author":"Zhu","year":"2025","journal-title":"ICCV"}],"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\/11444793.pdf?arnumber=11444793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:19Z","timestamp":1777613419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00598","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}