{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:05:05Z","timestamp":1789254305816,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369680","type":"print"},{"value":"9783032369697","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\/978-3-032-36969-7_11","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:20:43Z","timestamp":1789251643000},"page":"192-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Spatial Tuning"],"prefix":"10.1007","author":[{"given":"Rui","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjia","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"11_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Ahmadyan, A., Zhang, L., Ablavatski, A., Wei, J., Grundmann, M.: ObjectRon: a large scale dataset of object-centric videos in the wild with pose annotations. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"11_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"11_CR4","unstructured":"Baruch, G., et al.: ArkitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. arXiv preprint arXiv:2111.08897 (2021)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Bigverdi, M., et al.: Perception tokens enhance visual reasoning in multimodal language models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00363"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., Gkioxari, G.: Omni3D: a large benchmark and model for 3D object detection in the wild. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"11_CR7","unstructured":"Brohan, A., et al.: RT-1: robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: MatterPort3D: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"11_CR10","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"11_CR11","unstructured":"Chen, L., et\u00a0al.: Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330 (2024)"},{"key":"11_CR12","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: SpatialRGPT: grounded spatial reasoning in vision-language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-4293"},{"key":"11_CR15","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Daxberger, E., et al.: MM-Spatial: exploring 3D spatial understanding in multimodal LLMs. arXiv preprint arXiv:2503.13111 (2025)","DOI":"10.1109\/ICCV51701.2025.00694"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Molmo and PixMo: open weights and open data for state-of-the-art vision-language models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: VLMEvalKit: an open-source toolkit for evaluating large multi-modality models. In: ACMM (2024)","DOI":"10.1145\/3664647.3685520"},{"key":"11_CR20","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. arXiv preprint arXiv:2505.20279 (2025)"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Fu, X., et al.: BLINK: multimodal large language models can see but not perceive. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15081. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73337-6_9","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"11_CR23","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: CVPR (2022)"},{"key":"11_CR24","unstructured":"Guo, D., et\u00a0al.: Seed1.5-VL technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"issue":"2","key":"11_CR25","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.intell.2005.09.005","volume":"34","author":"M Hegarty","year":"2006","unstructured":"Hegarty, M., Montello, D.R., Richardson, A.E., Ishikawa, T., Lovelace, K.: Spatial abilities at different scales: individual differences in aptitude-test performance and spatial-layout learning. Intelligence 34(2), 151\u2013176 (2006)","journal-title":"Intelligence"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: RayZer: a self-supervised large view synthesis model. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00468"},{"key":"11_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"11_CR28","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"issue":"1\u20132","key":"11_CR29","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Nav. Res. Logist. Q."},{"key":"11_CR30","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"11_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1939"},{"key":"11_CR33","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15064. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"issue":"12","key":"11_CR34","doi-asserted-by":"publisher","first-page":"220102","DOI":"10.1007\/s11432-024-4235-6","volume":"67","author":"Y Liu","year":"2024","unstructured":"Liu, Y., et al.: OCRBench: on the hidden mystery of OCR in large multimodal models. Sci. China Inf. Sci. 67(12), 220102 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Ma, W., Chen, H., Zhang, G., Chou, Y.C., de\u00a0Melo, C.M., Yuille, A.: 3DSRBench: a comprehensive 3D spatial reasoning benchmark. arXiv preprint arXiv:2412.07825 (2024)","DOI":"10.1109\/ICCV51701.2025.00651"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J., Zhang, J.J.: Total3DUnderstanding: joint layout, object pose and mesh reconstruction for indoor scenes from a single image. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"11_CR39","unstructured":"Ouyang, K., et al.: SpaceR: reinforcing MLLMs in video spatial reasoning. arXiv preprint arXiv:2504.01805 (2025)"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Piaget, J.: Child\u2019s Conception of Space: Selected Works, vol. 4. Routledge (2013)","DOI":"10.4324\/9781315006239"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Shukla, S.N., Poursaeed, O., Ryoo, M.S., Lin, T.Y.: Learning to localize objects improves spatial reasoning in visual-LLMs. In: CVPR, pp. 12977\u201312987 (2024)","DOI":"10.1109\/CVPR52733.2024.01233"},{"key":"11_CR42","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"11_CR43","unstructured":"Ray, A., et al.: SAT: dynamic spatial aptitude training for multimodal language models. arXiv preprint arXiv:2412.07755 (2024)"},{"key":"11_CR44","unstructured":"RemyxAI: VQASynth SpaceLLaVA (2024). https:\/\/huggingface.co\/datasets\/remyxai\/vqasynth_spacellava"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"11_CR46","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"11_CR49","unstructured":"Chameleon Team: Chameleon: mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818 (2024)"},{"key":"11_CR50","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Tong, P., et\u00a0al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. In: NeurIPS (2024)","DOI":"10.52202\/079017-2771"},{"key":"11_CR52","unstructured":"Wang, H., et\u00a0al.: GRUtopia: dream general robots in a city at scale. arXiv preprint arXiv:2407.10943 (2024)"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"11_CR54","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: Mind\u2019s eye of LLMs: visualization-of-thought elicits spatial reasoning in large language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-2866"},{"key":"11_CR56","unstructured":"X.ai: Grok-1.5 vision preview (2024). https:\/\/x.ai\/blog\/grok-1.5v"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Xie, T., et\u00a0al.: OSWorld: benchmarking multimodal agents for open-ended tasks in real computer environments. In: NeurIPS (2024)","DOI":"10.52202\/079017-1650"},{"key":"11_CR58","unstructured":"Xu, R., et al.: Multi-SpatialMLLM: multi-frame spatial understanding with multi-modal large language models. arXiv preprint arXiv:2505.17015 (2025)"},{"key":"11_CR59","unstructured":"Yang, A., et\u00a0al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"11_CR61","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything V2. In: NeurIPS (2024)","DOI":"10.52202\/079017-0688"},{"key":"11_CR62","unstructured":"Yang, S., et\u00a0al.: MMSI-Bench: a benchmark for multi-image spatial intelligence. arXiv preprint arXiv:2505.23764 (2025)"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: a high-fidelity dataset of 3D indoor scenes. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"11_CR64","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. arXiv preprint arXiv:2506.21458 (2025)"},{"key":"11_CR65","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"11_CR66","unstructured":"Yue, Z., et\u00a0al.: MiMo-VL technical report. arXiv preprint arXiv:2506.03569, 5 (2025)"},{"key":"11_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cui, Z., Zhang, Y., Zeng, B., Pollefeys, M., Liu, S.: Holistic 3D scene understanding from a single image with implicit representation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"11_CR68","unstructured":"Zhang, H., et\u00a0al.: Ferret-v2: an improved baseline for referring and grounding with large language models. arXiv preprint arXiv:2404.07973 (2024)"},{"key":"11_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, J., et\u00a0al.: From flatland to space: teaching vision-language models to perceive and reason in 3D. arXiv preprint arXiv:2503.22976 (2025)","DOI":"10.52202\/085713-5180"},{"key":"11_CR70","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"11_CR71","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 3D-VisTa: pre-trained transformer for 3D vision and text alignment. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"11_CR72","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: CoRL (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\/978-3-032-36969-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:20:51Z","timestamp":1789251651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36969-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369680","9783032369697"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36969-7_11","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":"13 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"}}]}}