{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:30:30Z","timestamp":1777656630020,"version":"3.51.4"},"reference-count":43,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural 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\/iros60139.2025.11247165","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20394-20401","source":"Crossref","is-referenced-by-count":1,"title":["Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing"],"prefix":"10.1109","author":[{"given":"Jun","family":"Zhu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Du","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Astronautical Systems Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengbo","family":"Lan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zilong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ma","sequence":"additional","affiliation":[{"name":"Chengdu Aircraft Design & Research Institute,National Key Laboratory of Digital and Agile Aircraft Design AVIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences (IIIS)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Homerobot: Open-vocabulary mobile manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Yenamandra"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152855"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160736"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811881"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2975706"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref11","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref12","first-page":"32 340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Majumdar","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610499"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref17","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023"},{"key":"ref18","first-page":"24 993","article-title":"Fine-grained visual prompting","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref20","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref22","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref25","first-page":"19 769","article-title":"Segment everything everywhere all at once","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zou","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","article-title":"Samaug: Point prompt augmentation for segment anything model","author":"Dai","year":"2023"},{"key":"ref28","article-title":"Can sam segment anything? when sam meets camouflaged object detection","author":"Tang","year":"2023"},{"key":"ref29","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00901"},{"key":"ref31","article-title":"Palm-e: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess"},{"key":"ref32","first-page":"10342512","article-title":"L3mvn: Leveraging large language models for visual target navigation","volume-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS).","author":"Yu"},{"key":"ref33","article-title":"Esc: exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Zhou"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref35","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"7th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.075"},{"key":"ref37","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref40","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for embodied AI","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ramakrishnan"},{"key":"ref41","article-title":"Habitat challenge 2022","author":"Yadav","year":"2022"},{"key":"ref42","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref43","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Chaplot","year":"2020"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247165.pdf?arnumber=11247165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:56Z","timestamp":1766061476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247165","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}