{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:08:26Z","timestamp":1788894506865,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","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\/978-3-032-37035-8_17","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:53:10Z","timestamp":1788893590000},"page":"301-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics Question Scene Graph: Fine-Grained Evaluation of\u00a0Physical Plausibility in\u00a0Text-to-Video Generation"],"prefix":"10.1007","author":[{"given":"Atin","family":"Pothiraj","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-6169","authenticated-orcid":false,"given":"Jaemin","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-6536","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6689-505X","authenticated-orcid":false,"given":"Elias","family":"Stengel-Eskin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2965-5354","authenticated-orcid":false,"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"17_CR1","unstructured":"Ali, A., et\u00a0al.: World simulation with video foundation models for physical AI. arXiv preprint arXiv:2511.00062 (2025)"},{"key":"17_CR2","unstructured":"Artificial Analysis: Text to video model arena (2025). https:\/\/artificialanalysis.ai\/text-to-video\/arena?tab=leaderboard-text. Accessed Sept 1 2025"},{"key":"17_CR3","unstructured":"Bansal, H., Peng, C., Bitton, Y., Goldenberg, R., Grover, A., Chang, K.W.: Videophy-2: A challenging action-centric physical commonsense evaluation in video generation (2025)"},{"key":"17_CR4","unstructured":"Bao, F., et al.: Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models. arXiv preprint arXiv:2405.04233 (2024)"},{"key":"17_CR5","unstructured":"Blattmann, A., et al.: Stable video diffusion: Scaling latent video diffusion models to large datasets CoRR (2023)"},{"key":"17_CR6","unstructured":"Cho, J., et al.: Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation, p. ICLR (2024)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Choi, Y.: SVAD: From single image to 3D avatar via synthetic data generation with video diffusion and data augmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3137\u20133147 (2025)","DOI":"10.1109\/CVPRW67362.2025.00296"},{"key":"17_CR8","unstructured":"Chow, W., Mao, J., Li, B., Seita, D., Guizilini, V.C., Wang, Y.: Physbench: benchmarking and enhancing vision-language models for physical world understanding. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"17_CR9","unstructured":"Fu, X., et al.: Learning video generation for robotic manipulation with collaborative trajectory control, (2025). arXiv preprint arXiv:2506.01943"},{"key":"17_CR10","unstructured":"Gemini Team: 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":"17_CR11","doi-asserted-by":"crossref","unstructured":"Gillman, N., et al.: Force prompting: Video generation models can learn and generalize physics-based control signals. arXiv preprint arXiv:2505.19386 (2025)","DOI":"10.52202\/085713-3448"},{"key":"17_CR12","unstructured":"Google: Veo 3 (May 2025). https:\/\/aistudio.google.com\/models\/veo-3"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. NeurIPS 36, 66923\u201366939 (2023)","DOI":"10.52202\/075280-2923"},{"key":"17_CR14","unstructured":"Hao, Y., Chen, C., Mian, A.S., Xu, C., Liu, D.: Enhancing physical plausibility in video generation by reasoning the implausibility (2025). arXiv preprint arXiv:2509.24702"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"He, X., et\u00a0al.: Videoscore: Building automatic metrics to simulate fine-grained human feedback for video generation (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"17_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Klambauer, G., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS (2017)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Ho, J., et al.: Imagen video: High definition video generation with diffusion models (2022)","DOI":"10.52202\/068431-0628"},{"key":"17_CR19","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR20","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: Large-scale pretraining for text-to-video generation via transformers (2022)"},{"key":"17_CR21","unstructured":"Huang, Y., et al.: Phymotion: Structured 3D motion reward for physics-grounded human video generation (2026). arXiv preprint arXiv:2605.14269"},{"key":"17_CR22","unstructured":"Huang, Y., et al.: Planning with sketch-guided verification for physics-aware video generation (2025). arXiv preprint arXiv:2511.17450"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: Comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"17_CR24","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)","journal-title":"Behav. Brain Sci."},{"key":"17_CR25","unstructured":"Lee, D., Yoon, J., Cho, J., Bansal, M.: Self-correcting text-to-video generation with misalignment detection and localized refinement (2024). arXiv preprint arXiv:2411.15115"},{"key":"17_CR26","unstructured":"Li, C., Michel, O., Pan, X., Liu, S., Roberts, M., Xie, S.: Pisa experiments: Exploring physics post-training for video diffusion models by watching stuff drop. arXiv preprint arXiv:2503.09595 (2025)"},{"key":"17_CR27","unstructured":"Lin, W., et al.: Reasoning physical video generation with diffusion timestep tokens via reinforcement learning (2025). arXiv preprint arXiv:2504.15932"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., Ren, Z., Gupta, S., Wang, S.: Physgen: Rigid-body physics-grounded image-to-video generation. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Evalcrafter: Benchmarking and evaluating large video generation models (2023)","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"17_CR30","unstructured":"Ma\u00f1as, O., et al.: Improving text-to-image consistency via automatic prompt optimization. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=g12Gdl6aDL, featured Certification"},{"key":"17_CR31","unstructured":"Meng, F., et al.: Towards world simulator: Crafting physical commonsense-based benchmark for video generation. In: ICML (2025)"},{"key":"17_CR32","doi-asserted-by":"publisher","first-page":"123155","DOI":"10.52202\/079017-3914","volume":"37","author":"A Montanaro","year":"2024","unstructured":"Montanaro, A., Savant Aira, L., Aiello, E., Valsesia, D., Magli, E.: Motioncraft: physics-based zero-shot video generation. Adv. Neural. Inf. Process. Syst. 37, 123155\u2013123181 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Motamed, S., Culp, L., Swersky, K., Jaini, P., Geirhos, R.: Do generative video models understand physical principles? (2025)","DOI":"10.1109\/WACV61042.2026.00099"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Ni, H., et al.: Ti2v-zero: Zero-shot image conditioning for text-to-video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9015\u20139025 (2024)","DOI":"10.1109\/CVPR52733.2024.00861"},{"key":"17_CR35","unstructured":"OpenAI: Video generation models as world simulators (2024). https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/"},{"key":"17_CR36","unstructured":"OpenAI: GPT-5 model (2025). https:\/\/openai.com\/gpt-5\/"},{"key":"17_CR37","unstructured":"OpenAI: Sora 2 (October 2025). https:\/\/openai.com\/index\/sora-2\/"},{"key":"17_CR38","unstructured":"Qin, Y., et\u00a0al.: Worldsimbench: Towards video generation models as world simulators. In: Forty-second International Conference on Machine Learning (2025)"},{"key":"17_CR39","unstructured":"Ross, C., Hall, M., Romero-Soriano, A., Williams, A.: What makes a good metric? evaluating automatic metrics for text-to-image consistency. In: First Conference on Language Modeling (2024). https:\/\/openreview.net\/forum?id=LFfktMPAci"},{"key":"17_CR40","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans (2016). https:\/\/arxiv.org\/abs\/1606.03498"},{"key":"17_CR41","unstructured":"Soni, A., et al.: Videoagent: Self-improving video generation for embodied planning. In: Workshop on Reinforcement Learning Beyond Rewards@ Reinforcement Learning Conference, p. 2025 (2025)"},{"issue":"1","key":"17_CR42","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":"17_CR43","unstructured":"Spelke, E.S., Gutheil, G., Van\u00a0de Walle, G.: The development of object perception. Visual Cognition (1995)"},{"key":"17_CR44","unstructured":"Tan, X., et al.: Physmotion: Physics-grounded dynamics from a single image. arXiv preprint arXiv:2411.17189 (2024)"},{"key":"17_CR45","unstructured":"Team Wan: Wan: Open and advanced large-scale video generative models (2025)"},{"key":"17_CR46","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1162\/tacl_a_00685","volume":"12","author":"L Tjuatja","year":"2024","unstructured":"Tjuatja, L., Chen, V., Wu, T., Talwalkwar, A., Neubig, G.: Do LLMs exhibit human-like response biases? a case study in survey design. Trans. Assoc. Comput. Linguist. 12, 1011\u20131026 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"17_CR47","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards Accurate Generative Models of Video: A New Metric & Challenges (2019). https:\/\/arxiv.org\/abs\/1812.01717"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Physctrl: Generative physics for controllable and physics-grounded video generation. arXiv preprint arXiv:2509.20358 (2025)","DOI":"10.52202\/085713-5598"},{"key":"17_CR49","unstructured":"Wang, P., Wang, W., Li, Q.: Physcorr: Dual-reward dpo for physics-constrained text-to-video generation with automated preference selection. arXiv preprint arXiv:2511.03997 (2025)"},{"key":"17_CR50","unstructured":"Wang, Z., et al.: Epic: Efficient video camera control learning with precise anchor-video guidance. arXiv preprint arXiv:2505.21876 (2025)"},{"key":"17_CR51","unstructured":"Wang, Z., Lin, H., Yoon, J., Cho, J., Zhang, Y., Bansal, M.: Anchorweave: World-consistent video generation with retrieved local spatial memories (2026). arXiv preprint arXiv:2602.14941"},{"key":"17_CR52","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: Text-to-video diffusion models with an expert transformer. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"17_CR53","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: Text-to-video diffusion models with an expert transformer. In: The Thirteenth International Conference on Learning Representations (2024)"},{"issue":"12","key":"17_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3802588","volume":"58","author":"Z Yin","year":"2026","unstructured":"Yin, Z., et al.: A survey: spatiotemporal consistency in video generation. ACM Comput. Surv. 58(12), 1\u201341 (2026)","journal-title":"ACM Comput. Surv."},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Vlm4d: towards spatiotemporal awareness in vision language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8600\u20138612 (2025)","DOI":"10.1109\/ICCV51701.2025.00805"}],"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\/978-3-032-37035-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:53:16Z","timestamp":1788893596000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_17","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":"9 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"}}]}}