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

Showing 311320 of 1854 papers

TitleStatusHype
Audio-Driven Emotional Video PortraitsCode1
Disentangled Self-Supervision in Sequential RecommendersCode1
A Latent Transformer for Disentangled Face Editing in Images and VideosCode1
JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion RetargetingCode1
Language-Informed Visual Concept LearningCode1
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability PerspectiveCode1
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)Code1
CluCDD:Contrastive Dialogue Disentanglement via ClusteringCode1
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel PairsCode1
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANsCode1
Show:102550
← PrevPage 32 of 186Next →

No leaderboard results yet.