{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:59:32Z","timestamp":1778255972409,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Project of New Generation Artificial Intelligence of China","doi-asserted-by":"publisher","award":["2018AAA0102500"],"award-info":[{"award-number":["2018AAA0102500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125207"],"award-info":[{"award-number":["62125207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032022"],"award-info":[{"award-number":["62032022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272443"],"award-info":[{"award-number":["62272443"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936203"],"award-info":[{"award-number":["U1936203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["Z190020"],"award-info":[{"award-number":["Z190020"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ22012"],"award-info":[{"award-number":["JQ22012"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX201700255"],"award-info":[{"award-number":["BX201700255"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3263110","type":"journal-article","created":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T17:34:02Z","timestamp":1681234442000},"page":"2608-2619","source":"Crossref","is-referenced-by-count":17,"title":["Multi-Object Navigation Using Potential Target Position Policy Function"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1538-461X","authenticated-orcid":false,"given":"Haitao","family":"Zeng","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0895-1076","authenticated-orcid":false,"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01652"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967584"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref53","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref17","article-title":"Rearrangement: A challenge for embodied AI","author":"batra","year":"2020","journal-title":"arXiv 2011 01975"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref19","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"2018","journal-title":"arXiv 1810 06543"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475575"},{"key":"ref45","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018","journal-title":"arXiv 1807 06757"},{"key":"ref48","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref47","article-title":"Learning exploration policies for navigation","author":"chen","year":"2019","journal-title":"arXiv 1903 01959"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref41","article-title":"Learning active camera for multi-object navigation","author":"chen","year":"2022","journal-title":"arXiv 2210 07505"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref43","article-title":"Learning hierarchical relationships for object-goal navigation","author":"qiu","year":"2020","journal-title":"arXiv 2003 06749"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01559"},{"key":"ref8","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"chaplot","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00284"},{"key":"ref9","article-title":"Learning to explore using active neural SLAM","author":"chaplot","year":"2020","journal-title":"arXiv 2004 05155"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818931"},{"key":"ref6","article-title":"DD-PPO: Learning near-perfect PointGoal navigators from 2.5 billion frames","author":"wijmans","year":"2019","journal-title":"arXiv 1911 00357"},{"key":"ref5","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"kolve","year":"2017","journal-title":"arXiv 1712 05474"},{"key":"ref40","first-page":"7357","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","volume":"34","author":"moudgil","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"MemoNav: Selecting informative memories for visual navigation","author":"li","year":"2022","journal-title":"arXiv 2208 09610"},{"key":"ref34","first-page":"12875","article-title":"Neural topological SLAM for visual navigation","author":"chaplot","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref33","first-page":"26661","article-title":"No Rl, no simulation: Learning to navigate without navigating","volume":"34","author":"hahn","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"4283","article-title":"Semantic visual navigation by watching YouTube videos","volume":"33","author":"chang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref39","first-page":"14738","article-title":"Pathdreamer: A world model for indoor navigation","author":"koh","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref24","first-page":"13086","article-title":"Seal: Self-supervised embodied active learning using exploration and 3D consistency","volume":"34","author":"chaplot","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"VTNet: Visual transformer network for object goal navigation","author":"du","year":"2021","journal-title":"arXiv 2105 09447"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01662"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01388"},{"key":"ref27","first-page":"9700","article-title":"MultiON: Benchmarking semantic map memory using multi-object navigation","volume":"33","author":"wani","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","first-page":"17","article-title":"SoundSpaces: Audio-visual navigation in 3D environments","author":"chen","year":"2020","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10100678.pdf?arnumber=10100678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:48:16Z","timestamp":1685382496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10100678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3263110","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}