OpenCodePapers

zero-shot-skeletal-action-recognition-on-ntu-120

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 (10 unseen classes)Accuracy (24 unseen classes)Random Split AccuracyModelNameReleaseDate
GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition✓ Link90.4481.39GenPrior2026-08-03
DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition✓ Link89.06DynaPURLS2025-12-12
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition80.3PoseBridge2026-05-12
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment✓ Link79.9959.4271.38PGFA2025-07-01
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition✓ Link75.2466.52FDSM2026-04-10
SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition✓ Link74.260.1SkeletonContext2026-03-31
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition✓ Link74.1565.0669.47TDSM2024-11-16
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition73.654.9SCALE2026-04-02
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition✓ Link71.9552.01PURLS2024-06-19
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders✓ Link68.7746.1250.67SA-DVAE2024-07-18
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization✓ Link65.7445.3046.40SMIE2023-08-07
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition63.3044.30STAR2024-04-11
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition✓ Link62.6938.70SynSE2021-01-27
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders✓ Link59.5335.7745.14CADA-VAE2018-12-05
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders✓ Link57.16SA-DVAE + augmented text2024-07-18
Check out how to contribute new results. Then edit this file on GitLab or GitHub.