OpenCodePapers

zero-shot-skeletal-action-recognition-on-ntu-60

Action RecognitionSkeleton Based Action RecognitionZero Shot Skeletal Action Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracy (12 unseen classes)Accuracy (5 unseen classes)Random Split AccuracyModelNameReleaseDate
GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition✓ Link73.4387.98GenPrior2026-08-03
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition73.2PoseBridge2026-05-12
DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition✓ Link71.80DynaPURLS2025-12-12
SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition✓ Link64.489.6SkeletonContext2026-03-31
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition✓ Link57.4687.79FDSM2026-04-10
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition✓ Link56.0386.4988.88TDSM2024-11-16
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment✓ Link55.9980.2693.17PGFA2025-07-01
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition50.084.5SCALE2026-04-02
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition45.1081.4077.50STAR2024-04-11
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders✓ Link41.3882.3784.20SA-DVAE2024-07-18
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition✓ Link40.9979.23PURLS2024-06-19
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization✓ Link40.1877.9865.08SMIE2023-08-07
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition✓ Link33.3075.8164.19SynSE2021-01-27
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders✓ Link28.9676.8460.74CADA-VAE2018-12-05
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders✓ Link87.61SA-DVAE + augmented text2024-07-18
Check out how to contribute new results. Then edit this file on GitLab or GitHub.