{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:07:00Z","timestamp":1789124820432,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372604","type":"print"},{"value":"9783032372611","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\/978-3-032-37261-1_32","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:17:50Z","timestamp":1789121870000},"page":"565-582","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatial Amsan: A Benchmark for\u00a0Perception-Grounded Spatial Reasoning and\u00a0Action Evaluation in\u00a0Egocentric Manipulation"],"prefix":"10.1007","author":[{"given":"Changsoo","family":"Jung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Fitzgerald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan","family":"Seefried","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariah","family":"Bradford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathaniel","family":"Blanchard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"32_CR2","unstructured":"Anthropic: System card: Claude opus 4 & claude sonnet 4. Tech. rep., Anthropic (2025). https:\/\/www.anthropic.com\/claude-4-system-card. Accessed 05 Mar 2026"},{"key":"32_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"32_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"32_CR5","unstructured":"Bear, D., et al.: Physion: evaluating physical prediction from vision in humans and machines. In: Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track (2021)"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: SpatialRGPT: grounded spatial reasoning in vision-language models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 37 (2024)","DOI":"10.52202\/079017-4293"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the EPIC-KITCHENS dataset. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 753\u2013771 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"32_CR9","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"32_CR10","unstructured":"Girdhar, R., Ramanan, D.: CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"32_CR11","unstructured":"Google: Gemini 3 flash: Our fastest, most efficient thinking model. Google Blog (2025). https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3-flash\/. Accessed 05 Mar 2026"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5843\u20135851 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"32_CR13","unstructured":"Jiang, Y., et al.: VIMA: robot manipulation with multimodal prompts. In: Proceedings of the International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 202, pp. 14975\u201315022 (2023)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Kamath, A., Hessel, J., Chang, K.W.: What\u2019s \u201cup\u201d with vision-language models? investigating their struggle with spatial reasoning. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 9161\u20139175 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"32_CR15","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"32_CR16","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"32_CR18","unstructured":"Li, X., et al.: Videochat-r1: enhancing spatio-temporal perception via reinforcement fine-tuning. arXiv preprint arXiv:2504.06958 (2025)"},{"key":"32_CR19","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1162\/tacl_a_00566","volume":"11","author":"F Liu","year":"2023","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguistics 11, 635\u2013651 (2023)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 46212\u201346244 (2023)","DOI":"10.52202\/075280-2004"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Mirzaee, R., Rajaby Faghihi, H., Ning, Q., Kordjamshidi, P.: SPARTQA: a textual question answering benchmark for spatial reasoning. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 4582\u20134598 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.364"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Mittal, H., Agarwal, N., Lo, S.Y., Lee, K.: Can\u2019t make an omelette without breaking some eggs: plausible action anticipation using large video-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18580\u201318590 (2024)","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"32_CR23","unstructured":"OpenAI: Gpt-5 system card. Tech. rep., OpenAI (2025). https:\/\/arxiv.org\/abs\/2601.03267. Accessed 05 Mar 2026"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Padmakumar, A., et al.: TEACh: task-driven embodied agents that chat. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 2017\u20132025 (2022)","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Pothiraj, A., Stengel-Eskin, E., Cho, J., Bansal, M.: Capture: evaluating spatial reasoning in vision language models via occluded object counting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8001\u20138010 (2025)","DOI":"10.1109\/ICCV51701.2025.00750"},{"key":"32_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"9","key":"32_CR27","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1109\/TPAMI.2021.3083839","volume":"44","author":"R Riochet","year":"2022","unstructured":"Riochet, R., et al.: IntPhys 2019: a benchmark for visual intuitive physics understanding. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5016\u20135025 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhang, Q., Lipani, A.: StepGame: a new benchmark for robust multi-hop spatial reasoning in texts. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 11321\u201311329 (2022)","DOI":"10.1609\/aaai.v36i10.21383"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Shridhar, M., et al.: ALFRED: a benchmark for interpreting grounded instructions for everyday tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10737\u201310746 (2020)","DOI":"10.1109\/CVPR42600.2020.01075"},{"issue":"1","key":"32_CR31","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1207\/s15516709cog1401_3","volume":"14","author":"ES Spelke","year":"1990","unstructured":"Spelke, E.S.: Principles of object perception. Cogn. Sci. 14(1), 29\u201356 (1990)","journal-title":"Cogn. Sci."},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Tang, H., Kreiman, G.: Recognition of occluded objects. In: Computational and Cognitive Neuroscience of Vision, pp. 41\u201358. Springer (2016)","DOI":"10.1007\/978-981-10-0213-7_3"},{"key":"32_CR33","doi-asserted-by":"publisher","first-page":"75392","DOI":"10.52202\/079017-2400","volume":"37","author":"J Wang","year":"2024","unstructured":"Wang, J., et al.: Is a picture worth a thousand words? delving into spatial reasoning for vision language models. Adv. Neural. Inf. Process. Syst. 37, 75392\u201375421 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR34","unstructured":"Wang, W., Gao, Z., Gu, L., Pu, H., Cui, L.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"32_CR35","unstructured":"Xu, P., Wang, S., Zhu, Y., Li, J., Qi, G., Zhang, Y.: SpatialBench: benchmarking multimodal large language models for spatial cognition. arXiv preprint arXiv:2511.21471 (2025)"},{"key":"32_CR36","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: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"32_CR37","unstructured":"Yang, S., Yang, J., Huang, P., Brown, E., et\u00a0al.: Cambrian-s: towards spatial supersensing in video. arXiv preprint arXiv:2511.04670 (2025)"},{"key":"32_CR38","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"32_CR39","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-37261-1_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:18:03Z","timestamp":1789121883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37261-1_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372604","9783032372611"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37261-1_32","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":"12 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"}}]}}