{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:28Z","timestamp":1784268568461,"version":"3.55.0"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441231,62472065,U23B2010"],"award-info":[{"award-number":["62441231,62472065,U23B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01149","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12360-12370","source":"Crossref","is-referenced-by-count":2,"title":["VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior"],"prefix":"10.1109","author":[{"given":"Xindi","family":"Yang","sequence":"first","affiliation":[{"name":"Monash University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baolu","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[{"name":"Oxford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqian","family":"Ma","sequence":"additional","affiliation":[{"name":"ZMO AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Jia","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref3","article-title":"Videophy: Evaluating physical commonsense for video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01472"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","volume-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref8","article-title":"How i warped your noise: a temporally-correlated noise prior for diffusion models","volume-title":"The Twelfth International Conference on Learning Representations. OpenReview","author":"Chang","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657513"},{"key":"ref11","article-title":"A survey on in-context learning","author":"Dong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Motion guidance: Diffusion-based image editing with differentiable motion estimators","author":"Geng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref14","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00076"},{"key":"ref19","article-title":"Fine-grained controllable video generation via object appearance and context","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref21","article-title":"How far is video generation from world model: A physical law perspective","author":"Kang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref25","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Videodirectorgpt: Consistent multi-scene video generation via 1lm-guided planning","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref28","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"ref30","first-page":"1","article-title":"Trailblazer: Trajectory control for diffusion-based video generation","volume-title":"SIGGRAPH Asia 2024 Conference Papers","author":"Kurt Ma","year":"2024"},{"key":"ref31","article-title":"Towards world simulator: Crafting physical commonsense-based benchmark for video generation","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Motioncraft: Physicsbased zero-shot video generation","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Montanaro"},{"key":"ref33","article-title":"Do generative video models learn physical principles from watching videos?","author":"Motamed","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0586"},{"key":"ref35","article-title":"Sg-i2v: Selfguided trajectory control in image-to-video generation","author":"Namekata","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2006.01000.x"},{"key":"ref37","first-page":"111","article-title":"Mofa-video: Controllable image animation via generative motion field adaptions in frozen image-to-video diffusion model","volume-title":"European Conference on Computer Vision","author":"Niu","year":"2024"},{"key":"ref38","volume-title":"Openai","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref40","article-title":"Freetraj: Tuning-free trajectory control in video diffusion models","author":"Qiu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461948"},{"key":"ref43","article-title":"Bora: Biomedical generalist video generation model","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref45","volume-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"ref46","article-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00249"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref52","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref55","article-title":"Pandora: Towards general world model with natural language actions and video states","author":"Xiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"ref57","article-title":"Hallucination is inevitable: An innate limitation of large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01754"},{"issue":"2","key":"ref59","first-page":"6","article-title":"Learning interactive real-world simulators","volume":"1","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_22"},{"key":"ref65","volume-title":"Llavanext: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref66","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446220.pdf?arnumber=11446220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T19:58:10Z","timestamp":1781121490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01149","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}