paper-with-me

홈 › Papers

A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

2017-10-16 · NeurIPS 2017 12 · Marco Fraccaro, Simon Kamronn, Ulrich Paquet, Ole Winther

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework for unsupervised learning of sequential data that disentangles two latent representations: an object's representation, coming from a recognition model, and a latent state describing its dynamics. As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate high dimensional frames at each time step. The model is trained end-to-end on videos of a variety of simulated physical systems, and outperforms competing methods in generative and missing data imputation tasks.

📄 PDF Abstract BibTeX arXiv:1710.05741

Code (1)

simonkamronn/kvae 공식 구현 tf

Tasks

Imputation

Similar Papers 제목 키워드 기반

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

2020-07-21 · ICLR 2021 1 · David Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov 외

We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that representations can be disentangled if all but a …

DisentanglementRepresentation Learning

DISENTANGLED STATE SPACE MODELS: UNSUPERVISED LEARNING OF DYNAMICS ACROSS HETEROGENEOUS ENVIRONMENTS

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · Ðorđe Miladinović, Waleed Gondal, Bernhard Schölkopf, Joachim M. Buhmann 외

Sequential data often originates from diverse environments. Across them exist both shared regularities and environment specifics. To learn robust cross-environment descriptions of sequences we introduce disentangled stat…

PredictionState Space Models

Disentangled State Space Representations

2019-06-07 · Đorđe Miladinović, Muhammad Waleed Gondal, Bernhard Schölkopf, Joachim M. Buhmann 외

Sequential data often originates from diverse domains across which statistical regularities and domain specifics exist. To specifically learn cross-domain sequence representations, we introduce disentangled state space m…

regressionState Space ModelsTransfer Learning

Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry

2018-06-16 · Xianglei Xing, Ruiqi Gao, Tian Han, Song-Chun Zhu 외

We present a deformable generator model to disentangle the appearance and geometric information for both image and video data in a purely unsupervised manner. The appearance generator network models the information relat…

DisentanglementTransfer Learning

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

2025-11-05 · Jongseo Lee, Wooil Lee, Gyeong-Moon Park, Seong Tae Kim 외 arxiv

Effective explanations of video action recognition models should disentangle how movements unfold over time from the surrounding spatial context. However, existing methods based on saliency produce entangled explanations…

Action Recognition