SOTAVerified

Multi-label zero-shot learning

The goal of multi-label classification task is to predict a set of labels in an image. As an extension of zero-shot learning (ZSL), multi-label zero-shot learning (ML-ZSL) is developed to identify multiple seen and unseen labels in an image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 27 papers

TitleStatusHype
ML-Decoder: Scalable and Versatile Classification HeadCode1
Discriminative Region-based Multi-Label Zero-Shot LearningCode1
Contrastive Language-Image Pre-training for the Italian LanguageCode1
Semantic Diversity Learning for Zero-Shot Multi-label ClassificationCode1
Generative Multi-Label Zero-Shot LearningCode1
Interaction Compass: Multi-Label Zero-Shot Learning of Human-Object Interactions via Spatial RelationsCode1
A Shared Multi-Attention Framework for Multi-Label Zero-Shot LearningCode1
Zero-shot Learning for Audio-based Music Classification and TaggingCode0
Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection—0
Multi-Label Zero-Shot Learning with Structured Knowledge GraphsCode0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.