SOTAVerified

Few Shot Action Recognition

Few-shot (FS) action recognition is a challenging com- puter vision problem, where the task is to classify an unlabelled query video into one of the action categories in the support set having limited samples per action class.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 76 papers

TitleStatusHype
Multi-level Second-order Few-shot LearningCode0
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition—0
3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve—0
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation—0
A New Split for Evaluating True Zero-Shot Action RecognitionCode0
Learning Graphs for Knowledge Transfer With Limited Labels—0
Few-Shot Action Recognition with Compromised Metric via Optimal Transport—0
CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition—0
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization—0
All About Knowledge Graphs for Actions—0
Show:102550
← PrevPage 7 of 8Next →

No leaderboard results yet.