Video Understanding through the Disentanglement of Appearance and Motion
-
Updated
Oct 18, 2018 - Python
Video Understanding through the Disentanglement of Appearance and Motion
Learning Object Representations by Mixing Scenes, MSc thesis, University of Bern, Switzerland
Applying VAE and DGM families to JATS personality survey database in PyTorch
Vector-Quantised Variational Autoencoder for privacy-preserving speech recognition
BERT EncoderDecoderModel to reproduce a sentence with learned disentangled represntation
Learning alternative disentangled representations using weak labels
Code that reproduces results for the paper "Adversarial learning for modeling human motion" -
DELA - Disentanglement Learning Archive
It's a repo for figuring out ways how to get automatic text summaries to Auto-ML models that perform regression (get compressed and factorized latent representation). Ideally it should be even able to answer questions on properties of that model.
Experiments on Disentangled Representation Learning using Variational autoencoding algorithms
Unofficial Knet.jl implementation of paper "Image-to-image Translation via Hierarchical Style Disentanglement" (CVPR 2021 Oral).
Correlated Ellipses dataset for measuring disentanglement when the factors of variation are correlated. See our paper "Hyperprior Induced Unsupervised Disentanglement of Latent Representations" (AAAI 2019)
List of Generative Models (mostly VAE based, for now)
PyTorch version of disentanglement lib
Temporal Attention Bottleneck for VAE is informative? (ICML 2023)
Semi-Supervised Learning by Disentangling and Self-Ensembling over Stochastic Latent Space. MICCAI 2019.
unofficial backup service for mpi3d_real dataset
Code/supplement for the paper "Approaching an unknown communication system by latent space exploration and causal inference"
A multimodal dynamical variational autoencoder for audiovisual speech representation learning
Add a description, image, and links to the disentangled-representations topic page so that developers can more easily learn about it.
To associate your repository with the disentangled-representations topic, visit your repo's landing page and select "manage topics."