{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:19:10Z","timestamp":1761895150261,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209593","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["MoPE: Mixture of Policy Experts and Verification with Multimodal Information for Instance ImageGoal Navigation"],"prefix":"10.1109","author":[{"given":"Yijie","family":"Zeng","sequence":"first","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexun","family":"Chen","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixuan","family":"Shen","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Luo","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Li","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00252"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"},{"journal-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","year":"2020","author":"Batra","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01545"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"ref6","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref10","article-title":"Fgprompt: fine-grained goal prompting for image-goal navigation","volume":"36","author":"Sun","year":"2024","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02223"},{"article-title":"Esc: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"ICML","author":"Zhou","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref18","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume":"34","author":"Szot","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"Instance-specific image goal navigation: Training embodied agents to find object instances","year":"2022","author":"Krantz","key":"ref20"},{"journal-title":"Ovrl-v2: A simple state-of-art baseline for imagenav and objectnav","year":"2023","author":"Yadav","key":"ref21"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209593.pdf?arnumber=11209593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:44:28Z","timestamp":1761889468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209593","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}