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 1–10 of 76 papers

TitleStatusHype
Temporal Alignment-Free Video Matching for Few-shot Action RecognitionCode1
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action RecognitionCode1
D^2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action RecognitionCode1
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action RecognitionCode1
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language KnowledgeCode1
CLIP-guided Prototype Modulating for Few-shot Action RecognitionCode1
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action RecognitionCode1
TempCLR: Temporal Alignment Representation with Contrastive LearningCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
Show:102550
← PrevPage 1 of 8Next →

No leaderboard results yet.