HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Zero Shot Skeletal Action Recognition On Ntu 1

Metrics

Accuracy (10 unseen classes)
Accuracy (24 unseen classes)

Results

Performance results of various models on this benchmark

Paper Title
TDSM74.1565.06TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition
PURLS71.9552.01Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
SA-DVAE68.7746.12SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
SMIE65.7445.30Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
STAR63.3044.30Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition
SynSE62.6938.70Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
CADA-VAE59.5335.77Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
SA-DVAE + augmented text--SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
0 of 8 row(s) selected.