paper-with-me

홈 › Papers

PDE-Driven Spatiotemporal Disentanglement

2020-08-04 · ICLR 2021 1 · Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task based on a resolution method for partial differential equations: the separation of variables. This inspiration allows us to introduce a dynamical interpretation of spatiotemporal disentanglement. It induces a principled model based on learning disentangled spatial and temporal representations of a phenomenon to accurately predict future observations. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets.

📄 PDF Abstract BibTeX arXiv:2008.01352

Code (1)

JeremDona/spatiotemporal_variable_separation 공식 구현 pytorch

Tasks

Disentanglement

Similar Papers 제목 키워드 기반

From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition

2026-03-27 · Nazia Aslam, Abhisek Ray, Joakim Bruslund Haurum, Lukas Esterle 외 arxiv

Recent advances in large-scale video models have significantly improved video understanding across domains such as surveillance, healthcare, and entertainment. However, these models also amplify privacy risks by encoding…

Action Recognition

Disentangled Spatiotemporal Graph Generative Models

2022-02-28 · Yuanqi Du, Xiaojie Guo, Hengning Cao, Yanfang Ye 외

Spatiotemporal graph represents a crucial data structure where the nodes and edges are embedded in a geometric space and can evolve dynamically over time. Nowadays, spatiotemporal graph data is becoming increasingly popu…

DisentanglementFunctional ConnectivityGraph GenerationProtein Folding

SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition

2023-09-11 · Cong Wu, Xiao-Jun Wu, Josef Kittler, Tianyang Xu 외

Contrastive learning has achieved great success in skeleton-based action recognition. However, most existing approaches encode the skeleton sequences as entangled spatiotemporal representations and confine the contrasts …

Action RecognitionContrastive LearningDisentanglementRetrieval+3

Video Reenactment as Inductive Bias for Content-Motion Disentanglement

2021-01-30 · Juan F. Hernández Albarracín, Adín Ramírez Rivera

Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-d…

DisentanglementInductive BiasMotion Disentanglement

Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition

2021-09-07 · Ruwen Bai, Min Li, Bo Meng, Fengfa Li 외

Graph convolutional networks (GCNs) have emerged as dominant methods for skeleton-based action recognition. However, they still suffer from two problems, namely, neighborhood constraints and entangled spatiotemporal feat…

Action RecognitionDisentanglementSkeleton Based Action Recognition