{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:02:49Z","timestamp":1790276569342,"version":"4.1.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-36984-0_24","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:56:35Z","timestamp":1790276195000},"page":"437-455","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Anchoring: Addressing State Drift in\u00a0Vision-Language Navigation"],"prefix":"10.1007","author":[{"given":"Kangyi","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengna","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailin","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingrong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"An, D., et al.: ETPNav: evolving topological planning for vision-language navigation in continuous environments. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"24_CR2","unstructured":"An, D., et al.: 1st place solutions for RXR-habitat vision-and-language navigation competition (CVPR 2022). arXiv preprint arXiv:2206.11610 (2022)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"24_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"24_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Bar, A., Zhou, G., Tran, D., Darrell, T., LeCun, Y.: Navigation world models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15791\u201315801 (2025)","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Lin, B., Liu, X., Ma, L., Liang, X., Wong, K.Y.K.: Affordances-oriented planning using foundation models for continuous vision-language navigation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 23568\u201323576 (2025)","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Chen, J.K., Chuang, J., V\u00e1zquez, M., Savarese, S.: Topological planning with transformers for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11276\u201311286 (2021)","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"24_CR9","doi-asserted-by":"publisher","first-page":"38149","DOI":"10.52202\/068431-2764","volume":"35","author":"P Chen","year":"2022","unstructured":"Chen, P., et al.: Weakly-supervised multi-granularity map learning for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 35, 38149\u201338161 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR10","first-page":"5834","volume":"34","author":"S Chen","year":"2021","unstructured":"Chen, S., Guhur, P.L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 34, 5834\u20135847 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Think global, act local: dual-scale graph transformer for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16537\u201316547 (2022)","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: Navila: legged robot vision-language-action model for navigation. arXiv preprint arXiv:2412.04453 (2024)","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"24_CR13","unstructured":"Contributors, I.: InternNav: InternRobotics\u2019 open platform for building generalized navigation foundation models (2025). https:\/\/github.com\/InternRobotics\/InternNav"},{"issue":"2","key":"24_CR14","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: From simulators to research tasks. IEEE Trans. Emerg. Top. Comput. Intell. 6(2), 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Forlizzi, J., DiSalvo, C.: Service robots in the domestic environment: a study of the roomba vacuum in the home. In: Proceedings of the 1st ACM SIGCHI\/SIGART Conference on Human-Robot Interaction, pp. 258\u2013265 (2006)","DOI":"10.1145\/1121241.1121286"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Georgakis, G., et al.: Cross-modal map learning for vision and language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15460\u201315470 (2022)","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Guo, X., Chai, W., Li, S.Y., Wang, G.: LLaVA-ultra: large Chinese language and vision assistant for ultrasound. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 8845\u20138854 (2024)","DOI":"10.1145\/3664647.3681584"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Hong, Y., Wang, Z., Wu, Q., Gould, S.: Bridging the gap between learning in discrete and continuous environments for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15439\u201315449 (2022)","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., Gould, S.: A recurrent vision-and-language BERT for navigation. arXiv preprint arXiv:2011.13922 (2020)","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"24_CR20","unstructured":"Hu, J., et\u00a0al.: Astranav-world: world model for foresight control and consistency. arXiv preprint arXiv:2512.21714 (2025)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Huang, T., Li, D., Yang, R., Zhang, Z., Yang, Z., Tang, H.: MobileVLA-R1: reinforcing vision-language-action for mobile robots. arXiv preprint arXiv:2511.17889 (2025)","DOI":"10.1007\/978-3-032-37196-6_19"},{"key":"24_CR22","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Krantz, J., Gokaslan, A., Batra, D., Lee, S., Maksymets, O.: Waypoint models for instruction-guided navigation in continuous environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15162\u201315171 (2021)","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Krantz, J., Lee, S.: Sim-2-sim transfer for vision-and-language navigation in continuous environments. In: European Conference on Computer Vision, pp. 588\u2013603. Springer (2022)","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Krantz, J., Wijmans, E., Majumdar, A., Batra, D., Lee, S.: Beyond the nav-graph: vision-and-language navigation in continuous environments. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Ku, A., Anderson, P., Patel, R., Ie, E., Baldridge, J.: Room-across-room: multilingual vision-and-language navigation with dense spatiotemporal grounding. arXiv preprint arXiv:2010.07954 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Li, P., Wu, K., Fu, J., Zhou, S.: REGNav: room expert guided image-goal navigation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 4860\u20134868 (2025)","DOI":"10.1609\/aaai.v39i5.32514"},{"key":"24_CR28","unstructured":"Li, P., Wu, K., Huang, W., Zhou, S., Wang, J.: Camera-aware label refinement for unsupervised person re-identification. arXiv preprint arXiv:2403.16450 (2024)"},{"key":"24_CR29","unstructured":"Li, P., et al.: SpaAct: spatially-activated transition learning with curriculum adaptation for vision-language navigation. arXiv preprint arXiv:2604.27620 (2026)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Think before go: hierarchical reasoning for image-goal navigation. arXiv preprint arXiv:2604.17407 (2026)","DOI":"10.18653\/v1\/2026.acl-long.1352"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Li, P., Wu, K., Zhou, S., Huang, Q., Wang, J.: Pseudo labels refinement with intra-camera similarity for unsupervised person re-identification. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 366\u2013370. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10222317"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: VILA: on pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"24_CR33","unstructured":"Lin, X., Li, J., Wu, K., Tang, J., He, Q., Zhao, L.: MORN: metacognitive object-goal regulation for resource-rational long-horizon navigation. arXiv preprint arXiv:2605.16932 (2026)"},{"key":"24_CR34","unstructured":"Liu, F., et al.: NavForesee: a unified vision-language world model for hierarchical planning and dual-horizon navigation prediction (2025). https:\/\/arxiv.org\/abs\/2512.01550"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Mind the gap: aligning vision foundation models to image feature matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20313\u201320323 (2025)","DOI":"10.1109\/ICCV51701.2025.01889"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: ELVA: exploring ranking-driven universal multimodal retrieval. arXiv preprint arXiv:2606.20280 (2026)","DOI":"10.1007\/978-3-032-37517-9_21"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Semantic-aware representation learning for homography estimation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 2506\u20132514 (2024)","DOI":"10.1145\/3664647.3681021"},{"key":"24_CR38","unstructured":"Long, Y., Cai, W., Wang, H., Zhan, G., Dong, H.: InstructNav: zero-shot system for generic instruction navigation in unexplored environment. arXiv preprint arXiv:2406.04882 (2024)"},{"key":"24_CR39","unstructured":"Lyu, K., et\u00a0al.: HimemVLN: enhancing reliability of open-source zero-shot vision-and-language navigation with hierarchical memory system. arXiv preprint arXiv:2603.14807 (2026)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Martinez-Martin, E., del Pobil, A.P.: Personal robot assistants for elderly care: an overview. In: Personal Assistants: Emerging Computational Technologies, pp. 77\u201391 (2017)","DOI":"10.1007\/978-3-319-62530-0_5"},{"issue":"4","key":"24_CR41","doi-asserted-by":"publisher","first-page":"5339","DOI":"10.1109\/LRA.2020.3007462","volume":"5","author":"J Mi\u0161eikis","year":"2020","unstructured":"Mi\u0161eikis, J., et al.: Lio-a personal robot assistant for human-robot interaction and care applications. IEEE Robot. Autom. Lett. 5(4), 5339\u20135346 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Raychaudhuri, S., Wani, S., Patel, S., Jain, U., Chang, A.: Language-aligned waypoint (law) supervision for vision-and-language navigation in continuous environments. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4018\u20134028 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Wang, H., Liang, W., Van\u00a0Gool, L., Wang, W.: DreamWalker: mental planning for continuous vision-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10873\u201310883 (2023)","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Lookahead exploration with neural radiance representation for continuous vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13753\u201313762 (2024)","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, X., Yang, J., Liu, Y., Jiang, S.: GridMM: grid memory map for vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15625\u201315636 (2023)","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"24_CR46","unstructured":"Wei, M., et\u00a0al.: Ground slow, move fast: a dual-system foundation model for generalizable vision-and-language navigation. arXiv preprint arXiv:2512.08186 (2025)"},{"key":"24_CR47","unstructured":"Wei, M., et\u00a0al.: StreamVLN: streaming vision-and-language navigation via slowfast context modeling. arXiv preprint arXiv:2507.05240 (2025)"},{"issue":"3","key":"24_CR48","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1075\/is.10.3.06wis","volume":"10","author":"T Wisspeintner","year":"2009","unstructured":"Wisspeintner, T., Van Der Zant, T., Iocchi, L., Schiffer, S.: RoboCup@ home: scientific competition and benchmarking for domestic service robots. Interact. Stud. 10(3), 392\u2013426 (2009)","journal-title":"Interact. Stud."},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Wu, K., et al.: Event-equalized dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8417\u20138427 (2025)","DOI":"10.1109\/CVPR52734.2025.00788"},{"key":"24_CR50","unstructured":"Wu, K., et al.: Cem-net: cross-emotion memory network for emotional talking face generation. arXiv preprint arXiv:2508.12368 (2025)"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Yao, X., Gao, J., Xu, C.: NavMorph: a self-evolving world model for vision-and-language navigation in continuous environments. arXiv preprint arXiv:2506.23468 (2025)","DOI":"10.1109\/ICCV51701.2025.00525"},{"key":"24_CR52","unstructured":"Zhang, J., et\u00a0al.: Embodied navigation foundation model. arXiv preprint arXiv:2509.12129 (2025)"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Uni-navid: a video-based vision-language-action model for unifying embodied navigation tasks. arXiv preprint arXiv:2412.06224 (2024)","DOI":"10.15607\/RSS.2025.XXI.013"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: NaVid: video-based VLM plans the next step for vision-and-language navigation. arXiv preprint arXiv:2402.15852 (2024)","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"24_CR55","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"24_CR56","unstructured":"Zhang, Z., Zhang, H., Chen, X., Huang, K., Shi, C., Lu, H.: Latent-space autoregressive world model for efficient and robust image-goal navigation. arXiv e-prints, pp. arXiv\u20132511 (2025)"},{"key":"24_CR57","doi-asserted-by":"crossref","unstructured":"Zhou, G., Hong, Y., Wu, Q.: NavGPT: explicit reasoning in vision-and-language navigation with large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 7641\u20137649 (2024)","DOI":"10.1609\/aaai.v38i7.28597"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36984-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:56:51Z","timestamp":1790276211000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}