{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:01:26Z","timestamp":1790319686435,"version":"4.1.0"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371959","type":"print"},{"value":"9783032371966","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\/978-3-032-37196-6_19","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:32:35Z","timestamp":1789032755000},"page":"341-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MobileVLA-R1: Reinforcing Vision-Language-Action for\u00a0Mobile Robots"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5042-0908","authenticated-orcid":false,"given":"Ting","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8819-3741","authenticated-orcid":false,"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2386-2533","authenticated-orcid":false,"given":"Zida","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2077-1246","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"19_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":"19_CR2","unstructured":"An, D., et al.: 1st place solutions for rxr-habitat vision-and-language navigation competition. In: CVPR (2022)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"19_CR4","unstructured":"Brohan, A., et al.: Do as i can, not as i say: Grounding language in robotic affordances. In: Conference on Robot Learning, pp. 287\u2013318. PMLR (2023)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: International Conference on 3D Vision (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"19_CR6","first-page":"4247","volume":"33","author":"DS Chaplot","year":"2020","unstructured":"Chaplot, D.S., Gandhi, D.P., Gupta, A., Salakhutdinov, R.R.: Object goal navigation using goal-oriented semantic exploration. Adv. Neural. Inf. Process. Syst. 33, 4247\u20134258 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_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, pp. 23568\u201323576 (2025)","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"19_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":"19_CR9","doi-asserted-by":"publisher","first-page":"38149","DOI":"10.52202\/068431-2764","volume":"35","author":"P Chen","year":"2022","unstructured":"Chen, P.: 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":"19_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":"19_CR11","unstructured":"Chen, Y., et al.: Integrating chain-of-thought for multimodal alignment: A study on 3d vision-language learning. arXiv preprint arXiv:2503.06232 (2025)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: Navila: legged robot vision-language-action model for navigation, RSS (2025)","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"19_CR13","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities (2025). arXiv preprintarXiv:2507.06261"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Ding, P., et al.: Quar-vla: vision-language-action model for quadruped robots. In: European Conference on Computer Vision, pp. 352\u2013367. Springer (2024)","DOI":"10.1007\/978-3-031-72652-1_21"},{"key":"19_CR15","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. In: Proceedings of the 40th International Conference on Machine Learning (2023)"},{"key":"19_CR16","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Advances in neural information processing systems, p. 31 (2018)"},{"key":"19_CR17","unstructured":"Gao, C., et al.: Octonav: towards generalist embodied navigation. arXiv preprint arXiv:2506.09839 (2025)"},{"key":"19_CR18","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":"19_CR19","doi-asserted-by":"crossref","unstructured":"Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: Computer Vision and Pattern Recognition, pp. 13137\u201313146 (2020)","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"19_CR20","first-page":"7685","volume":"33","author":"Y Hong","year":"2020","unstructured":"Hong, Y., Rodriguez, C., Qi, Y., Wu, Q., Gould, S.: Language and visual entity relationship graph for agent navigation. Adv. Neural. Inf. Process. Syst. 33, 7685\u20137696 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR21","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":"19_CR22","doi-asserted-by":"crossref","unstructured":"Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., Gould, S.: A recurrent vision-and-language bert for navigation. In: Conference on Computer Vision and Pattern Recognition, pp. 1643\u20131653 (2021)","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: Learning navigational visual representations with semantic map supervision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3055\u20133067 (2023)","DOI":"10.1109\/ICCV51070.2023.00284"},{"issue":"2","key":"19_CR24","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. Iclr 1(2), 3 (2022)","journal-title":"Iclr"},{"key":"19_CR25","unstructured":"Huang, T., Zhang, Z., Tang, H.: 3d-r1: enhancing reasoning in 3d vlms for unified scene understanding. arXiv preprint arXiv:2507.23478 (2025)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Huang, T., Zhang, Z., Wang, Y., Tang, H.: 3d coca: Contrastive learners are 3d captioners. In: Thirteenth International Conference on 3D Vision (2026)","DOI":"10.1109\/3DV69130.2026.00168"},{"key":"19_CR27","unstructured":"Huang, T., Zhang, Z., Zhang, R., Zhao, Y.: Dc-scene: Data-centric learning for 3d scene understanding. arXiv preprint arXiv:2505.15232 (2025)"},{"key":"19_CR28","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: International Conference on Machine Learning, pp. 9118\u20139147. PMLR (2022)"},{"key":"19_CR29","unstructured":"Hurst, A., et al.: Gpt-4o system card (2024). arXiv preprintarXiv:2410.21276"},{"key":"19_CR30","unstructured":"Kim, M.J., et al.: Openvla: An open-source vision-language-action model (2024). arXiv preprint arXiv:2406.09246"},{"key":"19_CR31","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":"19_CR32","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":"19_CR33","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. In: Empirical Methods in Natural Language Processing, pp. 4392\u20134412 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR35","unstructured":"Liu, Q., Huang, T., Zhang, Z., Tang, H.: Nav-r1: Reasoning and navigation in embodied scenes (2025). arXiv:2509.10884 arXiv preprint"},{"key":"19_CR36","unstructured":"Long, Y., Cai, W., Wang, H., Zhan, G., Dong, H.: Instructnav: zero-shot system for generic instruction navigation in unexplored environment (2024). arXiv preprint arXiv:2406.04882"},{"key":"19_CR37","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. arXiv preprint arXiv:1901.03035 (2019)"},{"key":"19_CR38","doi-asserted-by":"publisher","first-page":"655","DOI":"10.52202\/075280-0031","volume":"36","author":"A Majumdar","year":"2023","unstructured":"Majumdar, A.: Where are we in the search for an artificial visual cortex for embodied intelligence? Adv. Neural. Inf. Process. Syst. 36, 655\u2013677 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR39","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: The road to know-where: An object-and-room informed sequential bert for indoor vision-language navigation. In: International Conference on Computer Vision, pp. 1655\u20131664 (2021)","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"19_CR41","unstructured":"Qi, Z., Zhang, Z., Yu, Y., Wang, J., Zhao, H.: Vln-r1: vision-language navigation via reinforcement fine-tuning (2025). arXiv preprintarXiv:2506.17221"},{"key":"19_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Rajvanshi, A., Sikka, K., Lin, X., Lee, B., Chiu, H.P., Velasquez, A.: Saynav: grounding large language models for dynamic planning to navigation in new environments. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 34, pp. 464\u2013474 (2024)","DOI":"10.1609\/icaps.v34i1.31506"},{"key":"19_CR44","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":"19_CR45","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). arXiv:1707.06347 arXiv preprint"},{"key":"19_CR46","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Song, W., Zhao, H., Ding, P., Cui, C., Lyu, S., Fan, Y., Wang, D.: Germ: a generalist robotic model with mixture-of-experts for quadruped robot. In: IROS, pp. 11879\u201311886. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10801816"},{"key":"19_CR48","unstructured":"Tang, H., Huang, T., Zhang, Z.: 3d coca v2: contrastive learners with test-time search for generalizable spatial intelligence (2026). arXiv preprintarXiv:2601.06496"},{"key":"19_CR49","unstructured":"Tang, Y., Yu, W., Tan, J., Zen, H., Faust, A., Harada, T.: Saytap: language to quadrupedal locomotion (2023). arXiv preprintarXiv:2306.07580"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Tong, X., et\u00a0al.: Quart-online: Latency-free multimodal large language model for quadruped robot learning. In: ICRA, pp. 9533\u20139539. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127693"},{"key":"19_CR51","unstructured":"Wang, C., Huang, T., Sun, C., Ning, X., Wang, D., Tang, H.: Let geometry guide: Layer-wise unrolling of geometric priors in multimodal llms. arXiv preprint arXiv:2604.05695 (2026)"},{"key":"19_CR52","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":"19_CR53","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Computer Vision and Pattern Recognition, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Lamp: learning vision-language-action policies with 3d scene flow as latent motion prior. arXiv preprint arXiv:2603.25399 (2026)","DOI":"10.1007\/978-3-032-37013-6_13"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, X., Yang, J., Liu, Y., Hu, J., Jiang, M., Jiang, S.: 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":"19_CR56","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":"19_CR57","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR58","unstructured":"Wei, M., et\u00a0al.: Streamvln: Streaming vision-and-language navigation via slowfast context modeling. arXiv preprint arXiv:2507.05240 (2025)"},{"key":"19_CR59","first-page":"125312","volume":"38","author":"J Wu","year":"2026","unstructured":"Wu, J., Yin, S., Feng, N., Long, M.: Rlvr-world: training world models with reinforcement learning. Adv. Neural. Inf. Process. Syst. 38, 125312\u2013125350 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR60","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Point transformer v3: Simpler faster stronger. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4840\u20134851 (2024)","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"19_CR61","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., Zhao, H.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"Yu, B., Kasaei, H., Cao, M.: L3mvn: Leveraging large language models for visual target navigation. IROS, pp, 3554\u20133560. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"19_CR63","unstructured":"Yu, Z., Long, Y., Yang, Z., Zeng, C., Fan, H., Zhang, J., Dong, H.: Correctnav: Self-correction flywheel empowers vision-language-action navigation model (2025). arXiv preprintarXiv:2508.10416"},{"key":"19_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Uni-navid: a video-based vision-language-action model for unifying embodied navigation tasks. RSS (2025)","DOI":"10.15607\/RSS.2025.XXI.013"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Navid: Video-based vlm plans the next step for vision-and-language navigation. In: RSS (2024)","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"19_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wan, W., Huang, T., Fang, Z., Zhang, H.: Multigranularity-3dqa: Dynamic multi-granularity perception and gated dual-stage encoder-decoder for 3d question answering. Expert Systems with Applications, p. 131676 (2026)","DOI":"10.1016\/j.eswa.2026.131676"},{"key":"19_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: More: unlocking scalability in reinforcement learning for quadruped vision-language-action models. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 11212\u201311218. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128601"},{"key":"19_CR68","unstructured":"Zhao, X., et al.: Mm-helix: Boosting multimodal long-chain reflective reasoning with holistic platform and adaptive hybrid policy optimization (2025). arXiv preprint arXiv:2510.08540"},{"key":"19_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-language navigation with self-supervised auxiliary reasoning tasks. In: Computer Vision and Pattern Recognition, pp. 10012\u201310022 (2020)","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"19_CR70","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et\u00a0al.: Move to understand a 3d scene: Bridging visual grounding and exploration for efficient and versatile embodied navigation. In: International Conference on Computer Vision, pp. 8120\u20138132 (2025)","DOI":"10.1109\/ICCV51701.2025.00761"},{"key":"19_CR71","unstructured":"Zitkovich, B., et\u00a0al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"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\/978-3-032-37196-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:33:06Z","timestamp":1789032786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37196-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371959","9783032371966"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37196-6_19","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":"11 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"}}]}}