{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:35:44Z","timestamp":1784820944839,"version":"3.55.0"},"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\/iccv51701.2025.02316","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24977-24988","source":"Crossref","is-referenced-by-count":1,"title":["LookOut: Real-World Humanoid Egocentric Navigation"],"prefix":"10.1109","author":[{"given":"Boxiao","family":"Pan","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam W.","family":"Harley","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francis","family":"Engelmann","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas J.","family":"Guibas","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Bochkovskii","year":"2024","journal-title":"Depth pro: Sharp monocular metric depth in less than a second"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.018"},{"key":"ref5","article-title":"Geometry-aware recurrent neural networks for active visual recognition","volume":"31","author":"Cheng","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref7","author":"Engel","year":"2023","journal-title":"Project aria: A new tool for egocentric multi-modal ai research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00569"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00132"},{"key":"ref12","author":"Adam","year":"2019","journal-title":"Learning from unlabelled videos using contrastive predictive neural 3d mapping"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3329626"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624927"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843613500217"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01374"},{"key":"ref25","first-page":"119411","article-title":"Human-aware vision-and-language navigation: bridging simulation to reality with dynamic human interactions","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00687"},{"key":"ref28","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref29","author":"Lv","year":"2024","journal-title":"Aria everyday activities dataset"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979661"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967730"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00061"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref36","first-page":"74427447","article-title":"Toward human-like social robot navigation: A large-scale, multi-modal, social human navigation dataset","volume-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Duc","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912455720"},{"key":"ref38","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00485"},{"key":"ref41","author":"Payandeh","year":"2024","journal-title":"Social-llava: Enhancing robot navigation through human-language reasoning in social spaces"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128366"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SAS60918.2024.10636369"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref46","author":"Radosavovic","year":"2024","journal-title":"Learning humanoid locomotion over challenging terrain"},{"key":"ref47","article-title":"Humanoid locomotion as next token prediction","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Radosavovic","year":"2024"},{"key":"ref48","author":"Raina","year":"2023","journal-title":"Egoblur: Responsible innovation in aria"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01129"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980235"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307213"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/s21237898"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00254"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3511409"},{"key":"ref57","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00782"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00270"},{"key":"ref63","author":"Wang","year":"2024","journal-title":"Egonav: Egocentric scene-aware human trajectory prediction"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01583"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00663"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802709"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01582"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"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\/11444575.pdf?arnumber=11444575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:56Z","timestamp":1777613396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02316","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}