Action Localization on NTU RGB+D 120

Metric: Accuracy (24 unseen classes) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Accuracy (24 unseen classes)▼	Extra Data	Paper	Date↕	Code
1	TDSM	65.06	No	TDSM: Triplet Diffusion for Skeleton-Text Matchi...	2024-11-16	Code
2	PGFA	59.42	No	Zero-shot Skeleton-based Action Recognition with...	2025-07-01	Code
3	PURLS	52.01	No	Part-aware Unified Representation of Language an...	2024-06-19	Code
4	SA-DVAE	46.12	No	SA-DVAE: Improving Zero-Shot Skeleton-Based Acti...	2024-07-18	Code
5	SMIE	45.3	No	Zero-shot Skeleton-based Action Recognition via ...	2023-08-07	Code
6	STAR	44.3	No	Fine-Grained Side Information Guided Dual-Prompt...	2024-04-11	-
7	SynSE	38.7	No	Syntactically Guided Generative Embeddings for Z...	2021-01-27	Code
8	CADA-VAE	35.77	No	Generalized Zero- and Few-Shot Learning via Alig...	2018-12-05	Code

#1TDSMSOTA
65.06
Accuracy (24 unseen classes)· 2024-11-16
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition Code
#2PGFA
59.42
Accuracy (24 unseen classes)· 2025-07-01
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment Code
#3PURLSSOTA
52.01
Accuracy (24 unseen classes)· 2024-06-19
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition Code
#4SA-DVAE
46.12
Accuracy (24 unseen classes)· 2024-07-18
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders Code
#5SMIESOTA
45.3
Accuracy (24 unseen classes)· 2023-08-07
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization Code
#6STAR
44.3
Accuracy (24 unseen classes)· 2024-04-11
Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition
#7SynSESOTA
38.7
Accuracy (24 unseen classes)· 2021-01-27
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition Code
#8CADA-VAESOTA
35.77
Accuracy (24 unseen classes)· 2018-12-05
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders Code