{"type":"ScholarlyArticle","title":"Towards Robust Deterministic and Probabilistic Modeling for Predictive Learning","authors":[{"name":"Xuesong Nie","slug":"xuesong-nie","given":"Xuesong","family":"Nie","affiliation":""},{"name":"Haoyuan Jin","slug":"haoyuan-jin","given":"Haoyuan","family":"Jin","affiliation":""},{"name":"Vijayakumar Bhagavatula","slug":"vijayakumar-bhagavatula","given":"Vijayakumar","family":"Bhagavatula","affiliation":""},{"name":"Xiaofeng Liu","slug":"xiaofeng-liu","given":"Xiaofeng","family":"Liu","affiliation":""}],"abstract":"Predictive modeling of unannotated spatiotemporal data presents inherent challenges, primarily due to the highly entangled visual dynamics in real-world scenes. To tackle these complexities, we introduce a novel insight through Disentangling Deterministic and Probabilistic (DDP) modeling. We note a key observation in spatiotemporal data where low-level details typically remain stable, whereas high-level motion frequently exhibits dynamic variations. The core motivation involves constructing two distinct pathways in the latent space: a deterministic path and a probabilistic path. The probabilistic path begins by defining the motion flow, which explicitly describes complex many-to-many motion patterns between patches, and models its probabilistic distribution using a motion diffuser. The deterministic path incorporates a spectral-aware enhancer to retain and amplify visual details in the frequency domain. These designs ensure visual consistency while also capturing intricate long-term motion dynamics. Extensive experiments demonstrate the superiority of DDP across diverse scenario evaluations.","doi":"10.24963/ijcai.2025/195","url":"https://ijcai.org/proceedings/2025/195","pdf":"https://ijcai.org/proceedings/2025/0195.pdf","markdown":"https://ijcai.org/proceedings/2025/195.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/195","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":195,"pages":{"first":1747,"last":1755},"keywords":["Computer Vision: CV: Video analysis and understanding","Computer Vision: CV: Motion and tracking","Machine Learning: ML: Self-supervised Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}