{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:11Z","timestamp":1763192591989,"version":"3.45.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228547","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["ViPro-2: Unsupervised State Estimation via Integrated Dynamics for Guiding Video Prediction"],"prefix":"10.1109","author":[{"given":"Patrick","family":"Takenaka","sequence":"first","affiliation":[{"name":"Stuttgart Media University,Stuttgart,Germany"}]},{"given":"Johannes","family":"Maucher","sequence":"additional","affiliation":[{"name":"Stuttgart Media University,Stuttgart,Germany"}]},{"given":"Marco F.","family":"Huber","sequence":"additional","affiliation":[{"name":"University of Stuttgart and Fraunhofer IPA,Stuttgart,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71167-1_4"},{"author":"Radford","key":"ref3","article-title":"Improving Language Understanding by Generative Pre-Training"},{"volume-title":"Rebooting AI: Building Artificial Intelligence We Can Trust","year":"2019","author":"Marcus","key":"ref4"},{"article-title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","year":"2024","author":"Mirzadeh","key":"ref5"},{"article-title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","year":"2024","author":"Duan","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"ref8","article-title":"Unsupervised Learning for Physical Interaction through Video Prediction","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Finn","year":"2016"},{"article-title":"Learning Visual Predictive Models of Physics for Playing Billiards","year":"2016","author":"Fragkiadaki","key":"ref9"},{"key":"ref10","article-title":"A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Fraccaro","year":"2017"},{"article-title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","volume-title":"International Conference on Learning Representations","author":"Janner","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01493-5"},{"article-title":"Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video","volume-title":"International Conference on Learning Representations","author":"Jaques","key":"ref13"},{"article-title":"gradSim: Differentiable simulation for system identification and visuomotor control","volume-title":"International Conference on Learning Representations","author":"Murthy","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00014"},{"key":"ref16","first-page":"11 525","article-title":"Object-Centric Learning with Slot Attention","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Locatello","year":"2020"},{"article-title":"Conditional Object-Centric Learning from Video","volume-title":"International Conference on Learning Representations","author":"Kipf","key":"ref17"},{"key":"ref18","article-title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","author":"Elsayed","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"article-title":"PDE-Driven Spatiotemporal Disentanglement","volume-title":"International Conference on Learning Representations","author":"Don\u00e0","key":"ref24"},{"article-title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","volume-title":"Thirty-Seventh Conference on Neural Information Processing Systems","author":"Wu","key":"ref25"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228547.pdf?arnumber=11228547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:18Z","timestamp":1763192358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228547","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}