SOTAVerified

Disentanglement

This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 261–270 of 1854 papers

TitleStatusHype
Neural Emotion Director: Speech-preserving semantic control of facial expressions in "in-the-wild" videosCode1
Towards Principled Disentanglement for Domain GeneralizationCode1
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
Optimizing Latent Space Directions For GAN-based Local Image EditingCode1
Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GANCode1
Self-supervised Re-renderable Facial Albedo Reconstruction from Single ImageCode1
Unsupervised Learning of Compositional Energy ConceptsCode1
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesCode1
Generative Adversarial Graph Convolutional Networks for Human Action SynthesisCode1
Structural Characterization for Dialogue DisentanglementCode1
Show:102550
← PrevPage 27 of 186Next →

No leaderboard results yet.