paper-with-me

Papers

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement

2024-08-10 · Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer

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.

📄 PDF Abstract BibTeX arXiv:2408.05599

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementRepresentation Learning

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

FAVAE: SEQUENCE DISENTANGLEMENT USING IN- FORMATION BOTTLENECK PRINCIPLE

2019-05-01 · ICLR 2019 5 · Masanori Yamada, Kim Heecheol, Kosuke Miyoshi, Hiroshi Yamakawa

A state-of-the-art generative model, a ”factorized action variational autoencoder (FAVAE),” is presented for learning disentangled and interpretable representations from sequential data via the information bottleneck wit…

DisentanglementRepresentation Learning

Disentangled Recurrent Wasserstein Autoencoder

2021-01-19 · ICLR 2021 1 · Jun Han, Martin Renqiang Min, Ligong Han, Li Erran Li 외

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framew…

DisentanglementRepresentation LearningStyle TransferUnconditional Video Generation+1

FAVAE: Sequence Disentanglement using Information Bottleneck Principle

2019-02-22 · Masanori Yamada, Heecheol Kim, Kosuke Miyoshi, Hiroshi Yamakawa

We propose the factorized action variational autoencoder (FAVAE), a state-of-the-art generative model for learning disentangled and interpretable representations from sequential data via the information bottleneck withou…

DisentanglementRepresentation Learning

DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization

2025-07-18 · Marzieh Gheisari, Auguste Genovesio arxiv

Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. W…

Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

2025-10-20 · Tal Barami, Nimrod Berman, Ilan Naiman, Amos H. Hason 외 arxiv

Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors ove…