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 1–25 of 76 papers

TitleStatusHype
Temporal-Relational CrossTransformers for Few-Shot Action RecognitionCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action RecognitionCode1
Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence ClassificationCode1
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action RecognitionCode1
CLIP-guided Prototype Modulating for Few-shot Action RecognitionCode1
Home Action Genome: Cooperative Compositional Action UnderstandingCode1
Object-Region Video TransformersCode1
TempCLR: Temporal Alignment Representation with Contrastive LearningCode1
Temporal Alignment-Free Video Matching for Few-shot Action RecognitionCode1
Revisiting spatio-temporal layouts for compositional action recognitionCode1
Action Genome: Actions as Composition of Spatio-temporal Scene GraphsCode1
Spatio-temporal Relation Modeling for Few-shot Action RecognitionCode1
TA2N: Two-Stage Action Alignment Network for Few-shot Action RecognitionCode1
D^2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action RecognitionCode1
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video RecognitionCode1
Hybrid Relation Guided Set Matching for Few-shot Action RecognitionCode1
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action RecognitionCode1
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
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CPM^2C)Code0
SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action RecognitionCode0
Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)Code0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.