{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:17:19Z","timestamp":1769732239320,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687514","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Common Sense Language-Guided Exploration and Hierarchical Dense Perception for Instruction Following Embodied Agents"],"prefix":"10.1109","author":[{"given":"Yuanwen","family":"Chen","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Xinyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Yaran","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Yunzhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Beijing Research"}]},{"given":"Zhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Beijing Research"}]},{"given":"Pengfei","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent Beijing Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01504"},{"key":"ref3","article-title":"FILM: Following instructions in language with modular methods","volume-title":"Conference on Learning Representations","author":"Min"},{"key":"ref4","article-title":"Prompter: Utilizing large language model prompting for a data efficient embodied instruction following","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"Inoue"},{"key":"ref5","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","volume-title":"Conference on Robot Learning","author":"Blukis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref9","first-page":"42 829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"International Conference on Machine Learning","author":"Zhou"},{"key":"ref10","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Conference on Robot Learning","author":"Shah"},{"issue":"8","key":"ref11","first-page":"17","article-title":"A planning based neural-symbolic approach for embodied instruction following","volume":"9","author":"Liu","year":"2022","journal-title":"Interactions"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k18-2016"},{"key":"ref13","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3078573"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028964"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2998497"},{"key":"ref18","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178804"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01004"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687514.pdf?arnumber=10687514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:36:51Z","timestamp":1727764611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687514","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}