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 881–890 of 1854 papers

TitleStatusHype
Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Video—0
Semantic-aware One-shot Face Re-enactment with Dense Correspondence Estimation—0
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image SegmentationCode1
Disentangled Feature Learning for Real-Time Neural Speech Coding—0
Multi-Directional Subspace Editing in Style-Space—0
VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement—0
Face Swapping as A Simple Arithmetic OperationCode1
Predicting Human Mobility via Self-supervised Disentanglement Learning—0
3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object ManipulationCode0
Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors—0
Show:102550
← PrevPage 89 of 186Next →

No leaderboard results yet.