{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:06:15Z","timestamp":1788991575832,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370259","type":"print"},{"value":"9783032370266","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\/978-3-032-37026-6_5","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:07:03Z","timestamp":1788988023000},"page":"73-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PercepTax: Benchmarking Physical Intelligence Through Cross-Property Reasoning in\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Jonathan","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingrui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luoxin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiezheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wufei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Cheng","family":"Chou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prakhar","family":"Kaushik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Armeni, I., et al.: 3d scene graph: a structure for unified semantics, 3d space, and camera (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00574","DOI":"10.1109\/ICCV.2019.00574"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: Scanqa: 3d question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Balazadeh, V., Ataei, M., Cheong, H., Khasahmadi, A.H., Krishnan, R.G.: Physics context builders: a modular framework for physical reasoning in vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7318\u20137328 (2025)","DOI":"10.1109\/ICCV51701.2025.00687"},{"key":"5_CR4","unstructured":"Cao, M., et al.: Physgame: uncovering physical commonsense violations in gameplay videos. arXiv preprint arXiv:2412.01800 (2024)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Chen, Z., Pan, L., Liu, Z.: Physx-3d: physical-grounded 3d asset generation. arXiv preprint arXiv:2507.12465 (2025)","DOI":"10.52202\/085713-3136"},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C., et al.: Spatialrgpt: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR7","unstructured":"Chow, W., Mao, J., Li, B., Seita, D., Guizilini, V., Wang, Y.: Physbench: benchmarking and enhancing vision-language models for physical world understanding. arXiv preprint arXiv:2501.16411 (2025)"},{"key":"5_CR8","unstructured":"Claude: Claude sonnet 4.5 (2025). https:\/\/www.anthropic.com\/claude\/sonnet. Accessed 30 June 2026"},{"key":"5_CR9","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":"5_CR10","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: Vlmevalkit: an open-source toolkit for evaluating large multi-modality models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 11198\u201311201 (2024)","DOI":"10.1145\/3664647.3685520"},{"key":"5_CR11","unstructured":"Epic Games: Unreal engine 5 (2021). https:\/\/www.unrealengine.com\/. version 5.x. Accessed 30 June 2026"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Fu, X., et al: Blink: multimodal large language models can see but not perceive. In: European Conference on Computer Vision, pp. 148\u2013166. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73337-6_9","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"5_CR13","volume-title":"The Ecological Approach to Visual Perception","author":"JJ Gibson","year":"1986","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception. Psychology Press, Hillsdale (1986)"},{"key":"5_CR14","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"issue":"1","key":"5_CR15","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1037\/xge0000129","volume":"145","author":"MR Greene","year":"2016","unstructured":"Greene, M.R., Baldassano, C., Esteva, A., Beck, D.M., Fei-Fei, L.: Visual scenes are categorized by function. J. Exp. Psychol. Gen. 145(1), 82 (2016)","journal-title":"J. Exp. Psychol. Gen."},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Groth, O., Fuchs, F.B., Posner, I., Vedaldi, A.: Shapestacks: learning vision-based physical intuition for generalised object stacking. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01246-5_43"},{"key":"5_CR17","first-page":"17427","volume":"34","author":"Y Hong","year":"2021","unstructured":"Hong, Y., Yi, L., Tenenbaum, J., Torralba, A., Gan, C.: PTR: a benchmark for part-based conceptual, relational, and physical reasoning. Adv. Neural. Inf. Process. Syst. 34, 17427\u201317440 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Huang, S.: Manipvqa: injecting robotic affordance and physically grounded information into multi-modal large language models. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7580\u20137587 (2024). https:\/\/doi.org\/10.1109\/IROS58592.2024.10801993","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van\u00a0der Maaten, L., Li, F.F., Zitnick, C.L., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"28798","DOI":"10.52202\/079017-0906","volume":"37","author":"J Kil","year":"2024","unstructured":"Kil, J., et al.: Mllm-compbench: a comparative reasoning benchmark for multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 28798\u201328827 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"7","key":"5_CR22","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v6: a large-scale dataset for detection, segmentation and classification. Int. J. Comput. Vision (IJCV) 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"5_CR24","unstructured":"Li, B., et al.: Seed-bench-2: Benchmarking multimodal large language models (2023). https:\/\/arxiv.org\/abs\/2311.17092"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Li, Z.: Super-clevr: a virtual benchmark to diagnose domain robustness in visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14963\u201314973 (2023)","DOI":"10.1109\/CVPR52729.2023.01437"},{"key":"5_CR26","unstructured":"Liu, H., et al.: Llava-next: improved reasoning, ocr, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/. Accessed 30 June 2026"},{"key":"5_CR27","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10882\u201310892 (2023)"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al: Mmbench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: 3dsrbench: a comprehensive 3d spatial reasoning benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6924\u20136934 (2025)","DOI":"10.1109\/ICCV51701.2025.00651"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: Spatialreasoner: towards explicit and generalizable 3d spatial reasoning. arXiv preprint arXiv:2504.20024 (2025)","DOI":"10.52202\/085713-4703"},{"key":"5_CR31","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol.\u00a01, pp. 281\u2013297. University of California Press (1967)"},{"key":"5_CR32","unstructured":"Mao, Y., Luo, W., Jing, J., Qiu, A., Mikolajczyk, K.: Hypo3d: exploring hypothetical reasoning in 3d. arXiv preprint arXiv:2502.00954 (2025)"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-vqa: a visual question answering benchmark requiring external knowledge. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"5_CR34","doi-asserted-by":"publisher","unstructured":"McInnes, L., Healy, J., Astels, S.: Hdbscan: hierarchical density based clustering. J. Open Source Softw.\u00a02, 205 (2017). https:\/\/doi.org\/10.21105\/joss.00205","DOI":"10.21105\/joss.00205"},{"key":"5_CR35","unstructured":"OpenAI: Gpt-5 system card (2025). https:\/\/openai.com\/index\/gpt-5-system-card. Accessed 30 June 2026"},{"key":"5_CR36","unstructured":"Oquab, M.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Qu, M., et al.: Rio: a benchmark for reasoning intention-oriented objects in open environments. Adv. Neural Inf. Process. Syst. 43041\u201343056 (2023)","DOI":"10.52202\/075280-1865"},{"key":"5_CR38","doi-asserted-by":"publisher","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-okvqa: augmented knowledge visual question answering. In: European Conference on Computer Vision (ECCV) Workshops. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1644"},{"key":"5_CR40","doi-asserted-by":"publisher","unstructured":"Tang, Y., Zhang, L., Zhang, S., Zhao, Y., Hao, X.: Roboafford: a dataset and benchmark for enhancing object and spatial affordance learning in robot manipulation. In: Proceedings of the 33rd ACM International Conference on Multimedia, MM \u201925, pp. 12706\u201312713. Association for Computing Machinery (2025). https:\/\/doi.org\/10.1145\/3746027.3758209","DOI":"10.1145\/3746027.3758209"},{"key":"5_CR41","unstructured":"Team, Q.: Qwen3 technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision & language models for visio-linguistic compositional reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"5_CR43","doi-asserted-by":"publisher","first-page":"87310","DOI":"10.52202\/079017-2771","volume":"37","author":"P Tong","year":"2024","unstructured":"Tong, P., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 87310\u201387356 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR44","unstructured":"Wang, J.: Affordance benchmark for mllms. arXiv preprint arXiv:2506.00893 (2025)"},{"key":"5_CR45","unstructured":"Wang, W.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Ma, W., Zhang, T., de\u00a0Melo, C.M., Chen, J., Yuille, A.: Spatial457: a diagnostic benchmark for 6d spatial reasoning of large mutimodal models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24669\u201324679 (2025)","DOI":"10.1109\/CVPR52734.2025.02297"},{"key":"5_CR47","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":"5_CR48","unstructured":"Yang, S., Zhang, C., Xu, Y., Gao, X., Zhang, L., Zhang, D.: Ram++: enhanced regional aggregation modeling for vision-language understanding. arXiv preprint arXiv:2403.05612 (2024)"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Yue, X.: Mmmu: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"issue":"7","key":"5_CR50","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.tics.2006.05.002","volume":"10","author":"A Yuille","year":"2006","unstructured":"Yuille, A., Kersten, D.: Vision as bayesian inference: analysis by synthesis? Trends Cogn. Sci. 10(7), 301\u2013308 (2006)","journal-title":"Trends Cogn. Sci."},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: Visual commonsense reasoning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00688"}],"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\/978-3-032-37026-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:07:12Z","timestamp":1788988032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37026-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370259","9783032370266"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37026-6_5","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":"10 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"}}]}}