{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:10:30Z","timestamp":1789042230157,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","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:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":253,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introduce the first benchmark that probes geographical layout understanding from real-world videos, spanning up to 1km distances. Inspired by the cognitive science literature, we evaluate models against the hierarchical stages of human spatial awareness: anchoring via landmarks, connecting them through routes, and integrating these into global mental maps. Extensive experiments reveal a fundamental divergence in how current AI models process spatial information. Instead of utilising true path integration or forming geometric survey knowledge, we find that VLMs rely almost entirely on 2D visual recognition and text-matching to bypass complex spatial reasoning.<\/jats:p>\n                  <jats:p>\n                    The benchmark is publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/perception-test-challenge.github.io\/kilometervision.html\" ext-link-type=\"uri\">https:\/\/perception-test-challenge.github.io\/kilometervision.html<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/978-3-032-37020-4_11","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:23:30Z","timestamp":1789039410000},"page":"194-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KilometerVision: A New Frontier for\u00a0Large-Scale Spatial Intelligence in\u00a0VLMs"],"prefix":"10.1007","author":[{"given":"Aravindh","family":"Mahendran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew Koichi","family":"Grimes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tyler","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Heyward","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengda","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiry","family":"Ginosar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dima","family":"Damen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Osindero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noah","family":"Snavely","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Lynen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joa\u00e3o","family":"Carreira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viorica","family":"P\u0103tr\u0103ucean","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Akesson, S., Bostr\u00f6m, J., Liedvogel, M., Muheim, R.: Animal Navigation, pp. 151\u2013178. Oxford University Press (2014). https:\/\/doi.org\/10.1093\/acprof:oso\/9780199677184.003.0009","DOI":"10.1093\/acprof:oso\/9780199677184.003.0009"},{"key":"11_CR2","doi-asserted-by":"publisher","unstructured":"Andersen, P., Morris, R., Amaral, D., Bliss, T., O\u2019Keefe, J.: The Hippocampus Book. Oxford University Press (2006). https:\/\/doi.org\/10.1093\/acprof:oso\/9780195100273.001.0001","DOI":"10.1093\/acprof:oso\/9780195100273.001.0001"},{"key":"11_CR3","unstructured":"Anthropic: The Claude 3 model family: opus, sonnet, haiku (2024). https:\/\/www-cdn.anthropic.com\/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627\/Model_Card_Claude_3.pdf. Accessed 29 June 2026"},{"key":"11_CR4","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments. In: CVPR, pp. 12530\u201312539 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01282","DOI":"10.1109\/CVPR.2019.01282"},{"key":"11_CR8","unstructured":"Cheng, Z., et al.: VideoLLaMA 2: advancing spatial-temporal modeling and audio understanding in video-LLMs. arXiv preprint arXiv:2406.07476 (2024)"},{"key":"11_CR9","unstructured":"Cho, J.H., et al.: PerceptionLM: open-access data and models for detailed visual understanding (2025). https:\/\/arxiv.org\/abs\/2504.13180"},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Chrastil, E., Warren, W.: Active and passive spatial learning in human navigation: acquisition of graph knowledge. J. Exp. Psychol. Learn. Mem. Cogn. 41(11), 1162\u20131178 (2014). https:\/\/doi.org\/10.1037\/xlm0000082","DOI":"10.1037\/xlm0000082"},{"issue":"6","key":"11_CR11","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1177\/0278364908090961","volume":"27","author":"M Cummins","year":"2008","unstructured":"Cummins, M., Newman, P.: FAB-MAP: probabilistic localization and mapping in the space of appearance. Int. J. Robot. Res. 27(6), 647\u2013665 (2008)","journal-title":"Int. J. Robot. Res."},{"key":"11_CR12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for EPIC-KITCHENS-100. IJCV 130, 33\u201355 (2022)","journal-title":"IJCV"},{"key":"11_CR13","doi-asserted-by":"publisher","unstructured":"Floros, G., van\u00a0der Zander, B., Leibe, B.: OpenStreetSLAM: global vehicle localization using OpenStreetMaps. In: 2013 IEEE International Conference on Robotics and Automation, pp. 1054\u20131059 (2013). https:\/\/doi.org\/10.1109\/ICRA.2013.6630703","DOI":"10.1109\/ICRA.2013.6630703"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Kuo, W.C., Efros, A.A., Malik, J.: From lifestyle vlogs to everyday interactions. In: CVPR, pp. 4991\u20135000 (2018)","DOI":"10.1109\/CVPR.2018.00524"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis. In: CVPR, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"11_CR16","volume-title":"Frames of Mind: The Theory of Multiple Intelligences","author":"H Gardner","year":"1983","unstructured":"Gardner, H.: Frames of Mind: The Theory of Multiple Intelligences. Heinemann, London (1983)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"11_CR18","unstructured":"Girdhar, R., Ramanan, D.: CATER: a diagnostic dataset for compositional actions and TEmporal reasoning. In: ICLR (2020)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Gould, J.L., Gould, C.G.: Nature\u2019s Compass: The Mystery of Animal Navigation. Princeton University Press (2012)","DOI":"10.1515\/9781400841660"},{"key":"11_CR20","unstructured":"Grauman, K., et al.: Ego4D: around the world in 3, 000 hours of egocentric video. In: CVPR (2022)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Handa, A., Whelan, T., McDonald, J., Davison, A.J.: A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 1524\u20131531 (2014). https:\/\/doi.org\/10.1109\/ICRA.2014.6907054","DOI":"10.1109\/ICRA.2014.6907054"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Hoda\u0148, T., et al.: BOP: benchmark for 6D object pose estimation. In: ECCV, p. 19\u201335. Springer (2018)","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Horvath, V., Toth, C., Barsi, A.: Investigating the accuracy of Google\u2019s visual positioning system. In: 2025 IEEE\/ION Position, Location and Navigation Symposium (PLANS), pp. 1594\u20131600. IEEE (2025)","DOI":"10.1109\/PLANS61210.2025.11028337"},{"key":"11_CR25","doi-asserted-by":"publisher","unstructured":"Huang, J., tse Huang, J., Liu, Z., Liu, X., Wang, W., Zhao, J.: VLMs as GeoGuessr masters: exceptional performance, hidden biases, and privacy risks. CoRR abs\/2502.11163 (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.11163","DOI":"10.48550\/arXiv.2502.11163"},{"key":"11_CR26","doi-asserted-by":"publisher","first-page":"2098","DOI":"10.1007\/s00426-020-01384-3","volume":"85","author":"K Kim","year":"2021","unstructured":"Kim, K., Bock, O.: Acquisition of landmark, route, and survey knowledge in a wayfinding task: in stages or in parallel? Psychol. Res. 85, 2098\u20132106 (2021)","journal-title":"Psychol. Res."},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ko, D., Lee, J.S., Kang, W., Roh, B., Kim, H.J.: Large language models are temporal and causal reasoners for video question answering. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Krishnan, A., et al.: Benchmarking egocentric visual-inertial SLAM at city scale. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02338"},{"key":"11_CR29","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. TMLR (2025)"},{"key":"11_CR30","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"11_CR31","unstructured":"Li, L., et al., Krishna, R.: Unfolding spatial cognition: evaluating multimodal models on visual simulations (2025). https:\/\/arxiv.org\/abs\/2506.04633"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-ChatGPT: towards detailed video understanding via large vision and language models. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. arXiv preprint arXiv:2308.09126 (2023)","DOI":"10.52202\/075280-2004"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Fergus, P.K., R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Newman, P., Ho, K.: SLAM-loop closing with visually salient features. In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, pp. 635\u2013642 (2005). https:\/\/doi.org\/10.1109\/ROBOT.2005.1570189","DOI":"10.1109\/ROBOT.2005.1570189"},{"key":"11_CR36","unstructured":"OpenAI: GPT-5 is here (2025). https:\/\/openai.com\/gpt-5. Accessed 29 June 2026"},{"key":"11_CR37","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. TMLR (2024)"},{"key":"11_CR38","doi-asserted-by":"publisher","unstructured":"Palgi, S., et al.: Head-direction cells as a neural compass in bats navigating outdoors on a remote oceanic island. Science 390(6770) (2025). https:\/\/doi.org\/10.1126\/science.adw6202","DOI":"10.1126\/science.adw6202"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"P\u0103tr\u0103ucean, V., et al.: Perception test: a diagnostic benchmark for multimodal video models. In: NeurIPS (2023). https:\/\/openreview.net\/forum?id=HYEGXFnPoq","DOI":"10.52202\/075280-1852"},{"key":"11_CR40","unstructured":"Ramakrishnan, S.K., Wijmans, E., Kraehenbuehl, P., Koltun, V.: Does spatial cognition emerge in frontier models? In: ICLR (2025). https:\/\/openreview.net\/forum?id=WK6K1FMEQ1"},{"key":"11_CR41","unstructured":"Rawal, R., et al.: CinePile: a long video question answering dataset and benchmark. arXiv preprint arXiv:2405.08813 (2024)"},{"key":"11_CR42","unstructured":"Roberts, J., L\u00fcddecke, T., Das, S., Han, K., Albanie, S.: GPT4Geo: how a language model sees the world\u2019s geography. In: NeurIPS Workshop on Foundation Models for Decision Making (2023)"},{"key":"11_CR43","doi-asserted-by":"publisher","unstructured":"Roberts, J., L\u00fcddecke, T., Sheikh, R., Han, K., Albanie, S.: Charting new territories: exploring the geographic and geospatial capabilities of multimodal LLMs. In: CVPR2024 Workshops. pp. 554\u2013563 (2024). https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00060","DOI":"10.1109\/CVPRW63382.2024.00060"},{"key":"11_CR44","doi-asserted-by":"publisher","unstructured":"Siegel, A.W., White, S.H.: The development of spatial representations of large-scale environments. In: Reese, H.W. (ed.) Advances in Child Development and Behavior, vol.\u00a010, pp. 9\u201355. JAI (1975). https:\/\/doi.org\/10.1016\/S0065-2407(08)60007-5, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0065240708600075","DOI":"10.1016\/S0065-2407(08)60007-5"},{"issue":"1","key":"11_CR45","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1121\/1.1913559","volume":"54","author":"JA Simmons","year":"1973","unstructured":"Simmons, J.A.: The resolution of target range by echolocating bats. J. Acoust. Soc. Am. 54(1), 157\u2013173 (1973)","journal-title":"J. Acoust. Soc. Am."},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Song, X., Chen, W., Liu, Y., Chen, W., Li, G., Lin, L.: Towards long-horizon vision-language navigation: platform, benchmark and method. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01128"},{"key":"11_CR47","unstructured":"SpiegelShai, E., Peer, S., Shvartzman, B., Demri, A., Avni, O.: Visual positioning system. U.S. Patent Application US20200401617A1 (2019)"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"11_CR49","unstructured":"Team, G.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities (2025). https:\/\/arxiv.org\/abs\/2507.06261"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Tolman, E.C.: Cognitive maps in rats and men. Psychol. Rev. 55 (4), 189\u2013208 (1948). https:\/\/api.semanticscholar.org\/CorpusID:42496633","DOI":"10.1037\/h0061626"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Vafa, K., Chen, J.Y., Rambachan, A., Kleinberg, J., Mullainathan, S.: Evaluating the world model implicit in a generative model. In: NeurIPS (2024). https:\/\/openreview.net\/forum?id=aVK4JFpegy","DOI":"10.52202\/079017-0846"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Valmeekam, K., Marquez, M., Olmo, A., Sreedharan, S., Kambhampati, S.: PlanBench: an extensible benchmark for evaluating large language models on planning and reasoning about change. In: NeurIPS. Curran Associates Inc. (2023)","DOI":"10.52202\/075280-1693"},{"key":"11_CR53","unstructured":"Venkataramanan, S., Rizve, M.N., Carreira, J., Asano, Y.M., Avrithis, Y.: Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video. In: ICLR (2024)"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Q., Do, M.Q., Agarwal, N., Lee, K., Sun, C.: Vamos: versatile action models for video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: LVBench: an extreme long video understanding benchmark. In: ICCV, pp. 22958\u201322967 (2025)","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"11_CR56","unstructured":"Wang, Y., et al.: InternVideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"11_CR57","unstructured":"Wang, Y., Yang, Y., Ren, M.: LifelongMemory: Leveraging LLMs for answering queries in long-form egocentric videos. arXiv preprint arXiv:2312.05269 (2024)"},{"key":"11_CR58","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1080\/13875860902906496","volume":"9","author":"JM Wiener","year":"2009","unstructured":"Wiener, J.M., Buchner, S.J., Holscher, C.: Taxonomy of human wayfinding tasks: a knowledge-based approach. Spat. Cogn. Comput. 9, 152\u2013165 (2009). https:\/\/doi.org\/10.1080\/13875860902906496","journal-title":"Spat. Cogn. Comput."},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: Next-QA: next phase of question-answering to explaining temporal actions. In: CVPR, pp. 9777\u20139786 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Xu, Y., Pan, Y., Liu, Z., Wang, H.: FLAME: learning to navigate with multimodal LLM in urban environments. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 9005\u20139013 (2025)","DOI":"10.1609\/aaai.v39i9.32974"},{"key":"11_CR61","unstructured":"Xue, L., et\u00a0al.: xGen-MM (BLIP-3): a family of open large multimodal models. arXiv preprint arXiv:2408.08872 (2024)"},{"key":"11_CR62","doi-asserted-by":"publisher","unstructured":"Yang, A., et al.: Evaluating and enhancing spatial cognition abilities of large language models. Int. J. Geograph. Inf. Sci. (2025). https:\/\/doi.org\/10.1080\/13658816.2025.2490701","DOI":"10.1080\/13658816.2025.2490701"},{"key":"11_CR63","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_CR64","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. In: ICLR (2020). https:\/\/openreview.net\/forum?id=HkxYzANYDB"},{"key":"11_CR65","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"11_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"11_CR67","doi-asserted-by":"crossref","unstructured":"Zhukov, D., Alayrac, J.B., Cinbis, R.G., Fouhey, D., Laptev, I., Sivic, J.: Cross-task weakly supervised learning from instructional videos. In: CVPR, pp. 3537\u20133545 (2019)","DOI":"10.1109\/CVPR.2019.00365"},{"key":"11_CR68","doi-asserted-by":"publisher","unstructured":"\u00f6zye\u015fil, O., Voroninski, V., Basri, R., Singer, A.: A survey of structure from motion. Acta Numer. 26, 305\u2013364 (2017). https:\/\/doi.org\/10.1017\/S096249291700006X","DOI":"10.1017\/S096249291700006X"}],"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\/978-3-032-37020-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:23:55Z","timestamp":1789039435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_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":"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"}}]}}