{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:37Z","timestamp":1784268637224,"version":"3.55.0"},"reference-count":96,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00761","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8120-8132","source":"Crossref","is-referenced-by-count":3,"title":["Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation"],"prefix":"10.1109","author":[{"given":"Ziyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Wang","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuofan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojian","family":"Ma","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxiong","family":"Jia","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Yu","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Object goal navigation using goal-oriented semantic exploration","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref8","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref19","article-title":"The one ring: a robotic indoor navigation generalist","author":"Eftekhar","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01537"},{"key":"ref21","article-title":"Embodied videoagent: Persistent memory from egocentric videos and embodied sensors enables dynamic scene understanding","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.770442"},{"key":"ref31","article-title":"An embodied generalist agent in 3d world","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang","year":"2024"},{"key":"ref32","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang","year":"2022"},{"key":"ref33","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_20"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref40","article-title":"Uniclip: Unified framework for contrastive language-image pretraining","author":"Lee","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref42","article-title":"Behavior-1k: A human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref46","article-title":"Navcot: Boosting 11 m -based vision-andlanguage navigation via learning disentangled reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2025.3574943"},{"key":"ref48","article-title":"Sqa3d: Situated question answering in 3d scenes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2343"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0677-82"},{"key":"ref53","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref58","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","volume-title":"7th Annual Conference on Robot Learning","author":"Rana","year":"2023"},{"key":"ref59","article-title":"Explore until confident: Efficient exploration for embodied question answering","author":"Allen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref62","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref66","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","author":"Szot","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref70","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0561"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref73","article-title":"Embodiedsam: Online segment any 3d thing in real time","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280773"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802709"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161059"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref82","article-title":"Poliformer: Scaling on-policy rl with transformers results in masterful navigators","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.013"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref87","article-title":"Task-oriented sequential grounding and navigation in 3d scenes","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref89","article-title":"Fast segment anything","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref90","article-title":"3d-vla: A 3d vision-language-action generative world model","author":"Zhen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref94","first-page":"188","article-title":"Unifying 3d vision-language understanding via promptable queries","volume-title":"European Conference on Computer Vision","author":"Zhu","year":"2024"},{"key":"ref95","article-title":"Tango: Training-free embodied ai agents for open-world tasks","author":"Ziliotto","year":"2024","journal-title":"arXiv preprint"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11443524.pdf?arnumber=11443524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:03Z","timestamp":1777529823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00761","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}