This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables and that improves the model expressivity through additional Normalizing Flows. A formal definition of the factors is proposed. This formalism leads to the derivation of sufficient conditions for the ground truth factors to be identifiable, and to the introduction of a novel theoretically grounded disentanglement constraint that can be directly and efficiently incorporated into our new framework. The experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
@article{arxiv.2408.05599,
title = {Sequential Representation Learning via Static-Dynamic Conditional Disentanglement},
author = {Mathieu Cyrille Simon and Pascal Frossard and Christophe De Vleeschouwer},
journal= {arXiv preprint arXiv:2408.05599},
year = {2024}
}