{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:54:49Z","timestamp":1775768089940,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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","award":["62172443"],"award-info":[{"award-number":["62172443"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2022JJ30760"],"award-info":[{"award-number":["2022JJ30760"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcds.2025.3597151","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T18:41:47Z","timestamp":1754678507000},"page":"331-345","source":"Crossref","is-referenced-by-count":1,"title":["Augmented Hierarchical Scene Prior Learning With Context-Based Scene Completion Network for Visual Semantic Navigation"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2135-9532","authenticated-orcid":false,"given":"Jiaxu","family":"Kang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4964-3475","authenticated-orcid":false,"given":"Chengyang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Dundee International Institute of Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2784-011X","authenticated-orcid":false,"given":"Bolei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3393-8874","authenticated-orcid":false,"given":"Ping","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1558-7990","authenticated-orcid":false,"given":"Haonan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1123-2658","authenticated-orcid":false,"given":"Tao","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"ref3","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3238840"},{"key":"ref7","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560925"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref10","article-title":"Learning to explore using active neural slam","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Chaplot","year":"2020"},{"key":"ref11","first-page":"2737","article-title":"BEVBert: Multimodal map pre-training for language-guided navigation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"An","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01003"},{"key":"ref14","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01559"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3300888"},{"key":"ref18","first-page":"393","article-title":"Topological semantic graph memory for image-goal navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2025.3531367"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref21","first-page":"1","article-title":"Generalization of reinforcement learners with working and episodic memory","volume":"32","author":"Fortunato","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3139543"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref24","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"ref25","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS),","author":"Majumdar","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_10"},{"key":"ref28","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst. (NIPS).","author":"Ouyang","year":"2022"},{"key":"ref29","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2025.3543364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794310"},{"key":"ref33","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Anderson","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610677"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3368696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801462"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161387"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01144-x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3595184"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00585"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00412"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/80"},{"key":"ref46","first-page":"102","article-title":"IDRNet: Intervention-driven relation network for semantic segmentation","volume":"36","author":"Jin","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref47","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref48","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref54","article-title":"Learning to map for active semantic goal navigation","author":"Georgakis"},{"key":"ref55","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref57","article-title":"Rednet: Residual encoder-decoder network for indoor RGB-D semantic segmentation","author":"Jiang","year":"2018"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref60","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812330"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11477821\/11120834.pdf?arnumber=11120834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:48:28Z","timestamp":1775764108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11120834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":61,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3597151","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}