Action Detection on NTU RGB+D 120

Metric: Accuracy (Cross-Setup) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy (Cross-Setup)▼	Extra Data	Paper	Date↕	Code
1	ProtoGCN	92.2	No	Revealing Key Details to See Differences: A Nove...	2024-11-28	Code
2	MSA-GCN	92.2	No	-	-	-
3	JMDA (based on Skeleton MixFormer)	91.9	No	-	-	Code
4	LA-GCN	91.8	Yes	Language Knowledge-Assisted Representation Learn...	2023-05-21	Code
5	Shap-Mix	91.7	No	Shap-Mix: Shapley Value Guided Mixing for Long-T...	2024-07-17	Code
6	MMCL	91.7	Yes	Multi-Modality Co-Learning for Efficient Skeleto...	2024-07-22	Code
7	TSGCNeXt	91.7	No	TSGCNeXt: Dynamic-Static Multi-Graph Convolution...	2023-04-23	Code
8	HD-GCN	91.6	No	Hierarchically Decomposed Graph Convolutional Ne...	2022-08-23	Code
9	BlockGCN	91.5	No	-	-	Code
10	Lit-llama	91.5	No	LLMs are Good Action Recognizers	2024-03-31	-
11	SkateFormer	91.4	No	SkateFormer: Skeletal-Temporal Transformer for H...	2024-03-14	Code
12	JPFormer	91.4	No	-	-	Code
13	MAMP	91.3	No	Masked Motion Predictors are Strong 3D Action Re...	2023-08-14	Code
14	Hyperformer	91.3	No	Hypergraph Transformer for Skeleton-based Action...	2022-11-17	Code
15	DG-STGCN	91.3	No	DG-STGCN: Dynamic Spatial-Temporal Modeling for ...	2022-10-12	Code
16	STEP-CATFormer	91.2	Yes	STEP CATFormer: Spatial-Temporal Effective Body-...	2023-12-06	Code
17	InfoGCN	91.2	No	-	-	Code
18	LST	91.1	Yes	Generative Action Description Prompts for Skelet...	2022-08-10	Code
19	Stream-GCN	91	No	Action Recognition with Multi-stream Motion Mode...	2023-06-13	-
20	SkeletonGCL (based on CTR-GCN)	91	No	Graph Contrastive Learning for Skeleton-based Ac...	2023-01-26	Code
21	DSTSA-GCN	90.97	No	DSTSA-GCN: Advancing Skeleton-Based Gesture Reco...	2025-01-21	Code
22	TCA-GCN	90.8	No	Skeleton-based Action Recognition via Temporal-C...	2022-05-31	Code
23	ST-GCN++ [PYSKL, 3D Skeleton]	90.8	No	PYSKL: Towards Good Practices for Skeleton Actio...	2022-05-19	Code
24	PSUMNet	90.6	No	PSUMNet: Unified Modality Part Streams are All Y...	2022-08-11	Code
25	CTR-GCN	90.6	No	Channel-wise Topology Refinement Graph Convoluti...	2021-07-26	Code
26	STGAT	90.4	No	Spatial Temporal Graph Attention Network for Ske...	2022-08-18	Code
27	TSGCNeXT	90.3	No	TSGCNeXt: Dynamic-Static Multi-Graph Convolution...	2023-04-23	Code
28	PoseC3D (w. HRNet 2D Skeleton)	90.3	No	Revisiting Skeleton-based Action Recognition	2021-04-28	Code
29	MaskCLR	89.5	No	-	-	-
30	DualHead-Net	89.3	No	Learning Multi-Granular Spatio-Temporal Graph Ne...	2021-08-10	Code
31	Skeletal GNN	89.2	No	Learning Skeletal Graph Neural Networks for Hard...	2021-08-16	-
32	EfficientGCN-B4	89.1	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
33	ST-GCN [PYSKL, 2D Skeleton]	89	No	Spatial Temporal Graph Convolutional Networks fo...	2018-01-23	Code
34	ST-GCN [PYSKL, 3D Skeleton]	88.4	No	Spatial Temporal Graph Convolutional Networks fo...	2018-01-23	Code
35	MSSTNet	88.3	No	-	-	Code
36	PA-ResGCN-B19	88.3	No	Stronger, Faster and More Explainable: A Graph C...	2020-10-20	Code
37	EfficientGCN-B2	88	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
38	VPN	87.8	Yes	VPN: Learning Video-Pose Embedding for Activitie...	2020-07-06	Code
39	VA-CNN (ResNeXt-101)	86.9	No	-	-	-
40	3s-HYSP	86.3	No	HYperbolic Self-Paced Learning for Self-Supervis...	2023-03-10	Code
41	S-TR (2-stream)	86.2	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
42	CoS-TR* (2-stream)	86.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
43	CoST-GCN* (2-stream)	85.5	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
44	AGCN (2-stream)	85.4	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
45	ST-GCN (2-stream)	85.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
46	EfficientGCN-B0	84.3	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
47	HYSP	82	No	HYperbolic Self-Paced Learning for Self-Supervis...	2023-03-10	Code
48	CoAGCN* (2-stream)	82	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
49	S-TR (1-stream)	81.8	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
50	CoS-TR* (1-stream)	81.7	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
51	CoST-GCN* (1-stream)	81.6	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
52	AGCN (1-stream)	80.7	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
53	3s-USDRL (DSTE) This work	79.3	No	USDRL: Unified Skeleton-Based Dense Representati...	2024-12-12	Code
54	CoAGCN* (1-stream)	79.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code

#1ProtoGCNSOTA
92.2
Accuracy (Cross-Setup)· 2024-11-28
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition Code
#2MSA-GCN
92.2
Accuracy (Cross-Setup)
No paper
#3JMDA (based on Skeleton MixFormer)
91.9
Accuracy (Cross-Setup)
No paperCode
#4LA-GCNSOTA
91.8
Accuracy (Cross-Setup)· Extra Data· 2023-05-21
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition Code
#5Shap-Mix
91.7
Accuracy (Cross-Setup)· 2024-07-17
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition Code
#6MMCL
91.7
Accuracy (Cross-Setup)· Extra Data· 2024-07-22
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition Code
#7TSGCNeXtSOTA
91.7
Accuracy (Cross-Setup)· 2023-04-23
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential Code
#8HD-GCNSOTA
91.6
Accuracy (Cross-Setup)· 2022-08-23
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#9BlockGCN
91.5
Accuracy (Cross-Setup)
No paperCode
#10Lit-llama
91.5
Accuracy (Cross-Setup)· 2024-03-31
LLMs are Good Action Recognizers
#11SkateFormer
91.4
Accuracy (Cross-Setup)· 2024-03-14
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition Code
#12JPFormer
91.4
Accuracy (Cross-Setup)
No paperCode
#13MAMP
91.3
Accuracy (Cross-Setup)· 2023-08-14
Masked Motion Predictors are Strong 3D Action Representation Learners Code
#14Hyperformer
91.3
Accuracy (Cross-Setup)· 2022-11-17
Hypergraph Transformer for Skeleton-based Action Recognition Code
#15DG-STGCN
91.3
Accuracy (Cross-Setup)· 2022-10-12
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition Code
#16STEP-CATFormer
91.2
Accuracy (Cross-Setup)· Extra Data· 2023-12-06
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition Code
#17InfoGCN
91.2
Accuracy (Cross-Setup)
No paperCode
#18LSTSOTA
91.1
Accuracy (Cross-Setup)· Extra Data· 2022-08-10
Generative Action Description Prompts for Skeleton-based Action Recognition Code
#19Stream-GCN
91
Accuracy (Cross-Setup)· 2023-06-13
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
#20SkeletonGCL (based on CTR-GCN)
91
Accuracy (Cross-Setup)· 2023-01-26
Graph Contrastive Learning for Skeleton-based Action Recognition Code
#21DSTSA-GCN
90.97
Accuracy (Cross-Setup)· 2025-01-21
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling Code
#22TCA-GCN
90.8
Accuracy (Cross-Setup)· 2022-05-31
Skeleton-based Action Recognition via Temporal-Channel Aggregation Code
#23ST-GCN++ [PYSKL, 3D Skeleton]SOTA
90.8
Accuracy (Cross-Setup)· 2022-05-19
PYSKL: Towards Good Practices for Skeleton Action Recognition Code
#24PSUMNet
90.6
Accuracy (Cross-Setup)· 2022-08-11
PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition Code
#25CTR-GCNSOTA
90.6
Accuracy (Cross-Setup)· 2021-07-26
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition Code
#26STGAT
90.4
Accuracy (Cross-Setup)· 2022-08-18
Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition Code
#27TSGCNeXT
90.3
Accuracy (Cross-Setup)· 2023-04-23
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential Code
#28PoseC3D (w. HRNet 2D Skeleton)SOTA
90.3
Accuracy (Cross-Setup)· 2021-04-28
Revisiting Skeleton-based Action Recognition Code
#29MaskCLR
89.5
Accuracy (Cross-Setup)
No paper
#30DualHead-Net
89.3
Accuracy (Cross-Setup)· 2021-08-10
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition Code
#31Skeletal GNN
89.2
Accuracy (Cross-Setup)· 2021-08-16
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
#32EfficientGCN-B4
89.1
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#33ST-GCN [PYSKL, 2D Skeleton]SOTA
89
Accuracy (Cross-Setup)· 2018-01-23
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#34ST-GCN [PYSKL, 3D Skeleton]
88.4
Accuracy (Cross-Setup)· 2018-01-23
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#35MSSTNet
88.3
Accuracy (Cross-Setup)
No paperCode
#36PA-ResGCN-B19
88.3
Accuracy (Cross-Setup)· 2020-10-20
Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition Code
#37EfficientGCN-B2
88
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#38VPN
87.8
Accuracy (Cross-Setup)· Extra Data· 2020-07-06
VPN: Learning Video-Pose Embedding for Activities of Daily Living Code
#39VA-CNN (ResNeXt-101)
86.9
Accuracy (Cross-Setup)
No paper
#403s-HYSP
86.3
Accuracy (Cross-Setup)· 2023-03-10
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations Code
#41S-TR (2-stream)
86.2
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#42CoS-TR* (2-stream)
86.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#43CoST-GCN* (2-stream)
85.5
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#44AGCN (2-stream)
85.4
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#45ST-GCN (2-stream)
85.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#46EfficientGCN-B0
84.3
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#47HYSP
82
Accuracy (Cross-Setup)· 2023-03-10
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations Code
#48CoAGCN* (2-stream)
82
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#49S-TR (1-stream)
81.8
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#50CoS-TR* (1-stream)
81.7
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#51CoST-GCN* (1-stream)
81.6
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#52AGCN (1-stream)
80.7
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#533s-USDRL (DSTE) This work
79.3
Accuracy (Cross-Setup)· 2024-12-12
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation Code
#54CoAGCN* (1-stream)
79.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code