{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:05:12Z","timestamp":1790111112062,"version":"4.0.1"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109323","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T07:11:13Z","timestamp":1783494673000},"page":"109323","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Interactive 3D scene graph alignment for zero-shot object navigation"],"prefix":"10.1016","volume":"205","author":[{"given":"Yu","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4177-7188","authenticated-orcid":false,"given":"Kang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109323_bib0001","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"19456","article-title":"R2c: Mapping room to chessboard to unlock LLM as low-level action planner","author":"Bai","year":"2025"},{"issue":"1","key":"10.1016\/j.neunet.2026.109323_bib0002","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1109\/MRA.2008.931629","article-title":"Street smarts for boss","volume":"16","author":"Baker","year":"2009","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"10.1016\/j.neunet.2026.109323_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120496","article-title":"MFFCG\u2013multi feature fusion for hyperspectral image classification using graph attention network","volume":"229","author":"Bhatti","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109323_bib0004","series-title":"Neural information processing systems (NIPS)","first-page":"1","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"10.1016\/j.neunet.2026.109323_bib0005","doi-asserted-by":"crossref","unstructured":"Cai, W., Huang, S., Cheng, G., Long, Y., Gao, P., Sun, C., & Dong, H. (2023). Bridging zero-shot object navigation and foundation models through pixel-guided navigation skill. arXiv: 2309.10309.","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"10.1016\/j.neunet.2026.109323_bib0006","series-title":"International conference on 3D vision (3DV)","article-title":"MatterPort3D: Learning from RGB-d data in indoor environments","author":"Chang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109323_bib0007","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109323_bib0008","series-title":"Proceedings of robotics: Science and system XIX","first-page":"075","article-title":"How to not train your dragon: Training-free embodied object goal navigation with semantic frontiers","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0009","series-title":"Proceedings of the 30th ACM International conference on multimedia","first-page":"3617","article-title":"Unbiased directed object attention graph for object navigation","author":"Dang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0010","series-title":"Proceedings of the 36th International conference on neural information processing systems","first-page":"5982","article-title":"ProcTHOR: Large-scale embodied AI using procedural generation","author":"Deitke","year":"2022"},{"issue":"5","key":"10.1016\/j.neunet.2026.109323_bib0011","doi-asserted-by":"crossref","first-page":"4083","DOI":"10.1109\/LRA.2023.3346800","article-title":"Can an embodied agent find your \u201ccat-shaped mug\u201d? llm-based zero-shot object navigation","volume":"9","author":"Dorbala","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109323_bib0012","series-title":"European conference on computer vision","first-page":"368","article-title":"Navigation instruction generation with bev perception and large language models","author":"Fan","year":"2025"},{"key":"10.1016\/j.neunet.2026.109323_bib0013","series-title":"Acm siggraph 2011 papers","first-page":"1","article-title":"Characterizing structural relationships in scenes using graph kernels","author":"Fisher","year":"2011"},{"key":"10.1016\/j.neunet.2026.109323_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"23171","article-title":"Cows on pasture: Baselines and benchmarks for language-driven zero-shot object navigation","author":"Gadre","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0015","series-title":"Proceedings of the IEEE International conference on computer vision","first-page":"1440","article-title":"Fast r-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.neunet.2026.109323_bib0016","doi-asserted-by":"crossref","unstructured":"Gu, Q., Kuwajerwala, A., Morin, S., Jatavallabhula, K. M., Bipasha, S., Agarwal, A., Rivera, C., Paul, W., Ellis, K., Chellappa, R. et al. (2023). Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning. arXiv: 2309.16650.","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"10.1016\/j.neunet.2026.109323_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"9235","article-title":"Ow-DETR: Open-world detection transformer","author":"Gupta","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0018","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., & Du, D. (2021). BEVDet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv: 2112.11790."},{"key":"10.1016\/j.neunet.2026.109323_bib0019","series-title":"Conference on robot learning","first-page":"393","article-title":"Topological semantic graph memory for image-goal navigation","author":"Kim","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0020","unstructured":"Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., Weihs, L., Herrasti, A., Gordon, D., Zhu, Y., Gupta, A., & Farhadi, A. (2017). Ai2-thor: An interactive 3d environment for visual ai. arXiv: 1712.05474."},{"key":"10.1016\/j.neunet.2026.109323_bib0021","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"15890","article-title":"Visual graph memory with unsupervised representation for visual navigation","author":"Kwon","year":"2021"},{"key":"10.1016\/j.neunet.2026.109323_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"10965","article-title":"Grounded language-image pre-training","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0023","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1477","article-title":"BEVDepth: Acquisition of reliable depth for multi-view 3d object detection","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0024","series-title":"European conference on computer vision","first-page":"1","article-title":"BEVFormer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","author":"Li","year":"2022"},{"issue":"7","key":"10.1016\/j.neunet.2026.109323_bib0025","first-page":"5945","article-title":"Navcot: Boosting llm-based vision-and-language navigation via learning disentangled reasoning","volume":"47","author":"Lin","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intell- igence"},{"key":"10.1016\/j.neunet.2026.109323_bib0026","unstructured":"Lin, M., Chen, Y., Zhao, D., & Wang, Z. (2024). Advancing object goal navigation through LLM-enhanced object affinities transfer. arXiv: 2403.09971."},{"key":"10.1016\/j.neunet.2026.109323_bib0027","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.109323_bib0028","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"10968","article-title":"Bird\u2019s-eye-view scene graph for vision-language navigation","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0029","series-title":"2023\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"2774","article-title":"BEVFusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2026.109323_bib0030","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1109\/LRA.2025.3529324","article-title":"Multi-view spatial context and state constraints for object-goal navigation","volume":"10","author":"Lu","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109323_bib0031","unstructured":"Lu, H., Liu, W., Zhang, B., Wang, B., Dong, K., Liu, B., Sun, J., Ren, T., Li, Z., Sun, Y. et al. (2024). Deepseek-vl: Towards real-world vision-language understanding. arXiv: 2403.05525."},{"key":"10.1016\/j.neunet.2026.109323_bib0032","series-title":"2022\u202fIEEE\/RSJ International conference on intelligent robots and systems (IROS)","first-page":"3287","article-title":"Stubborn: A strong baseline for indoor object navigation","author":"Luo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4035","article-title":"SGFormer: Semantic graph transformer for point cloud-based 3d scene graph generation","volume":"vol. 38","author":"Lv","year":"2024"},{"key":"10.1016\/j.neunet.2026.109323_bib0034","doi-asserted-by":"crossref","first-page":"32340","DOI":"10.52202\/068431-2343","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"35","author":"Majumdar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.109323_bib0035","doi-asserted-by":"crossref","first-page":"3803","DOI":"10.1109\/LRA.2025.3546860","article-title":"Context-aware graph inference and generative adversarial imitation learning for object-goal navigation in unfamiliar environment","volume":"10","author":"Meng","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109323_bib0036","series-title":"European conference on computer vision","first-page":"728","article-title":"Simple open-vocabulary object detection","author":"Minderer","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0037","doi-asserted-by":"crossref","unstructured":"Pchelintsev, S., Patratskiy, M., Onishchenko, A., Korchemnyi, A., Medvedev, A., Vinogradova, U., Galuzinsky, I., Postnikov, A., Kovalev, A. K., & Panov, A. I. (2025). Lera: Replanning with visual feedback in instruction following. arXiv: 2507.05135.","DOI":"10.1109\/IROS60139.2025.11247303"},{"key":"10.1016\/j.neunet.2026.109323_bib0038","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, august 23\u201328, 2020, proceedings, part XIV 16","first-page":"194","article-title":"Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3D","author":"Philion","year":"2020"},{"key":"10.1016\/j.neunet.2026.109323_bib0039","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109323_bib0040","doi-asserted-by":"crossref","unstructured":"Rajvanshi, A., Sikka, K., Lin, X., Lee, B., Chiu, H.-P., & Velasquez, A. (2023). Saynav: Grounding large language models for dynamic planning to navigation in new environments. arXiv: 2309.04077.","DOI":"10.1609\/icaps.v34i1.31506"},{"key":"10.1016\/j.neunet.2026.109323_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"18890","article-title":"Poni: Potential functions for objectgoal navigation with interaction-free learning","author":"Ramakrishnan","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0042","series-title":"Thirty-fifth conference on neural information processing systems datasets and benchmarks track (round 2)","article-title":"Habitat-matterport 3D dataset (HM3d): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109323_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5173","article-title":"Habitat-web: Learning embodied object-search strategies from human demonstrations at scale","author":"Ramrakhya","year":"2022"},{"key":"10.1016\/j.neunet.2026.109323_bib0044","series-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"Ross","year":"2011"},{"issue":"4","key":"10.1016\/j.neunet.2026.109323_bib0045","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1073\/pnas.93.4.1591","article-title":"A fast marching level set method for monotonically advancing fronts","volume":"93","author":"Sethian","year":"1996","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.109323_bib0046","series-title":"Conference on robot learning","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","author":"Shah","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0047","series-title":"2023\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"11523","article-title":"Progprompt: Generating situated robot task plans using large language models","author":"Singh","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0048","doi-asserted-by":"crossref","unstructured":"Sun, S., Li, X., Di, D., Wei, M., Nie, L., Zhang, W.-N., Zhan, D., Song, Y., & Fan, L. (2025). Llapa: A vision-language model framework for counterfactual-aware procedural planning. arXiv: 2507.08496.","DOI":"10.1145\/3746027.3755724"},{"key":"10.1016\/j.neunet.2026.109323_bib0049","series-title":"Advances in neural information processing systems","article-title":"FGPrompt: Fine-grained goal prompting for image-goal navigation","volume":"vol. 36","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2026.109323_bib0050","unstructured":"Wang, A., Song, L., Tian, Y., Peng, B., Yu, D., Mi, H., Su, J., & Yu, D. (2024). LiteSearch: Efficacious tree search for LLM. arXiv: 2407.00320."},{"key":"10.1016\/j.neunet.2026.109323_bib0051","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"5922","article-title":"Visual room rearrangement","author":"Weihs","year":"2021"},{"key":"10.1016\/j.neunet.2026.109323_bib0052","series-title":"International conference on pattern recognition","first-page":"389","article-title":"Zero-shot object navigation with vision-language models reasoning","author":"Wen","year":"2025"},{"key":"10.1016\/j.neunet.2026.109323_bib0053","unstructured":"Wu, P., Mu, Y., Wu, B., Hou, Y., Ma, J., Zhang, S., & Liu, C. (2024). VoroNav: Voronoi-based zero-shot object navigation with large language model. arXiv: 2401.02695."},{"key":"10.1016\/j.neunet.2026.109323_bib0054","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"9068","article-title":"Gibson env: Real-world perception for embodied agents","author":"Xia","year":"2018"},{"key":"10.1016\/j.neunet.2026.109323_bib0055","series-title":"Proceedings 1997\u202fIEEE international symposium on computational intelligence in robotics and automation CIRA\u201997.\u2019towards new computational principles for robotics and Automation\u2019","first-page":"146","article-title":"A frontier-based approach for autonomous exploration","author":"Yamauchi","year":"1997"},{"key":"10.1016\/j.neunet.2026.109323_bib0056","doi-asserted-by":"crossref","first-page":"19135","DOI":"10.1109\/TASE.2025.3593344","article-title":"Transformer-driven semantic-spatial adaptive fusion representation for object-goal navigation","volume":"22","author":"Yang","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"10.1016\/j.neunet.2026.109323_bib0057","doi-asserted-by":"crossref","first-page":"5285","DOI":"10.52202\/079017-0171","article-title":"SG-Nav: Online 3D scene graph prompting for llm-based zero-shot object navigation","volume":"37","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109323_bib0058","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11784","article-title":"Center-based 3D object detection and tracking","author":"Yin","year":"2021"},{"key":"10.1016\/j.neunet.2026.109323_bib0059","series-title":"2nd workshop on language and robot learning: language as grounding","article-title":"VLFM: Vision-language frontier maps for zero-shot semantic navigation","author":"Yokoyama","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0060","series-title":"2023\u202fIEEE\/RSJ International conference on intelligent robots and systems (IROS)","first-page":"3554","article-title":"L3MVN: Leveraging large language models for visual target navigation","author":"Yu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109323_bib0061","series-title":"Advances in neural information processing systems","article-title":"CommonScenes: Generating commonsense 3d indoor scenes with scene graphs","volume":"vol. 36","author":"Zhai","year":"2024"},{"key":"10.1016\/j.neunet.2026.109323_bib0062","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"15130","article-title":"Hierarchical object-to-zone graph for object navigation","author":"Zhang","year":"2021"},{"issue":"4","key":"10.1016\/j.neunet.2026.109323_bib0063","doi-asserted-by":"crossref","first-page":"10573","DOI":"10.1109\/LRA.2022.3187496","article-title":"ATF-3D: Semi-supervised 3D object detection with adaptive thresholds filtering based on confidence and distance","volume":"7","author":"Zhang","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109323_bib0064","series-title":"International conference on machine learning","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","author":"Zhou","year":"2023"},{"issue":"2","key":"10.1016\/j.neunet.2026.109323_bib0065","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1109\/TSMCA.2011.2159587","article-title":"Efficient role transfer based on kuhn\u2013munkres algorithm","volume":"42","author":"Zhu","year":"2011","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007835?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007835?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:09:56Z","timestamp":1790107796000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026007835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":65,"alternative-id":["S0893608026007835"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109323","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Interactive 3D scene graph alignment for zero-shot object navigation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109323","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109323"}}