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 426–450 of 1854 papers

TitleStatusHype
Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation—0
Select and Reorder: A Novel Approach for Neural Sign Language Production—0
Reuse out-of-year data to enhance land cover mappingvia feature disentanglement and contrastive learning—0
Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement—0
MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation—0
Tripod: Three Complementary Inductive Biases for Disentangled Representation LearningCode1
3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow—0
Move Anything with Layered Scene Diffusion—0
Multi-modal Document Presentation Attack Detection With Forensics Trace Disentanglement—0
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement—0
Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement—0
Reference-Based 3D-Aware Image Editing with Triplanes—0
EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis—0
Disentangling Hippocampal Shape Variations: A Study of Neurological Disorders Using Mesh Variational Autoencoder with Contrastive LearningCode0
Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation—0
DSFNet: Learning Disentangled Scenario Factorization for Multi-Scenario Route Ranking—0
A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation—0
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self AugmentationCode1
Review-Based Hyperbolic Cross-Domain RecommendationCode0
Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics—0
WordRobe: Text-Guided Generation of Textured 3D Garments—0
Activity-Biometrics: Person Identification from Daily ActivitiesCode0
Can Large Language Models (or Humans) Disentangle Text?Code0
X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention—0
Defying Imbalanced Forgetting in Class Incremental Learning—0
Show:102550
← PrevPage 18 of 75Next →

No leaderboard results yet.