Activity Recognition 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	DSCNet (RGB + Pose)	96.7	No	-	-	Code
2	PoseC3D (RGB + Pose)	96.4	No	Revisiting Skeleton-based Action Recognition	2021-04-28	Code
3	π-ViT (RGB + Pose)	96.1	Yes	Just Add $π$! Pose Induced Video Transformers fo...	2023-11-30	Code
4	MMNet (RGB + Pose)	94.4	Yes	-	-	Code
5	EPP-Net (Parsing + Pose)	92.8	No	Explore Human Parsing Modality for Action Recogn...	2024-01-04	Code
6	STAR-Transformer (RGB + Pose)	92.7	No	STAR-Transformer: A Spatio-temporal Cross Attent...	2022-10-14	-
7	EPAM-Net	92.4	No	EPAM-Net: An Efficient Pose-driven Attention-gui...	2024-08-10	Code
8	ProtoGCN	92.2	No	Revealing Key Details to See Differences: A Nove...	2024-11-28	Code
9	MSA-GCN	92.2	No	-	-	-
10	π-ViT (RGB only)	91.9	Yes	Just Add $π$! Pose Induced Video Transformers fo...	2023-11-30	Code
11	JMDA (based on Skeleton MixFormer)	91.9	No	-	-	Code
12	LA-GCN	91.8	Yes	Language Knowledge-Assisted Representation Learn...	2023-05-21	Code
13	IPP-Net (Parsing + Pose)	91.7	No	Integrating Human Parsing and Pose Network for H...	2023-07-16	Code
14	Shap-Mix	91.7	No	Shap-Mix: Shapley Value Guided Mixing for Long-T...	2024-07-17	Code
15	MMCL	91.7	Yes	Multi-Modality Co-Learning for Efficient Skeleto...	2024-07-22	Code
16	TSGCNeXt	91.7	No	TSGCNeXt: Dynamic-Static Multi-Graph Convolution...	2023-04-23	Code
17	HD-GCN	91.6	No	Hierarchically Decomposed Graph Convolutional Ne...	2022-08-23	Code
18	BlockGCN	91.5	No	-	-	Code
19	Lit-llama	91.5	No	LLMs are Good Action Recognizers	2024-03-31	-
20	3DA (RGB + Pose)	91.4	No	Cross-Modal Learning with 3D Deformable Attentio...	2022-12-12	-
21	JPFormer(Pose)	91.4	No	-	-	Code
22	SkateFormer	91.4	No	SkateFormer: Skeletal-Temporal Transformer for H...	2024-03-14	Code
23	JPFormer	91.4	No	-	-	Code
24	MAMP	91.3	No	Masked Motion Predictors are Strong 3D Action Re...	2023-08-14	Code
25	Hyperformer	91.3	No	Hypergraph Transformer for Skeleton-based Action...	2022-11-17	Code
26	DG-STGCN	91.3	No	DG-STGCN: Dynamic Spatial-Temporal Modeling for ...	2022-10-12	Code
27	STEP-CATFormer	91.2	Yes	STEP CATFormer: Spatial-Temporal Effective Body-...	2023-12-06	Code
28	InfoGCN	91.2	No	-	-	Code
29	LST	91.1	Yes	Generative Action Description Prompts for Skelet...	2022-08-10	Code
30	Stream-GCN	91	No	Action Recognition with Multi-stream Motion Mode...	2023-06-13	-
31	SkeletonGCL (based on CTR-GCN)	91	No	Graph Contrastive Learning for Skeleton-based Ac...	2023-01-26	Code
32	DSTSA-GCN	90.97	No	DSTSA-GCN: Advancing Skeleton-Based Gesture Reco...	2025-01-21	Code
33	DSTSA-GCN	90.97	No	DSTSA-GCN: Advancing Skeleton-Based Gesture Reco...	2025-01-21	Code
34	TCA-GCN	90.8	No	Skeleton-based Action Recognition via Temporal-C...	2022-05-31	Code
35	ST-GCN++ [PYSKL, 3D Skeleton]	90.8	No	PYSKL: Towards Good Practices for Skeleton Actio...	2022-05-19	Code
36	VPN++ (RGB + Pose)	90.7	Yes	VPN++: Rethinking Video-Pose embeddings for unde...	2021-05-17	Code
37	PSUMNet	90.6	No	PSUMNet: Unified Modality Part Streams are All Y...	2022-08-11	Code
38	CTR-GCN	90.6	No	Channel-wise Topology Refinement Graph Convoluti...	2021-07-26	Code
39	DVANet (RGB only)	90.4	No	DVANet: Disentangling View and Action Features f...	2023-12-10	Code
40	STGAT	90.4	No	Spatial Temporal Graph Attention Network for Ske...	2022-08-18	Code
41	TSGCNeXT	90.3	No	TSGCNeXt: Dynamic-Static Multi-Graph Convolution...	2023-04-23	Code
42	PoseC3D (w. HRNet 2D Skeleton)	90.3	No	Revisiting Skeleton-based Action Recognition	2021-04-28	Code
43	MaskCLR	89.5	No	-	-	-
44	DualHead-Net	89.3	No	Learning Multi-Granular Spatio-Temporal Graph Ne...	2021-08-10	Code
45	Skeletal GNN	89.2	No	Learning Skeletal Graph Neural Networks for Hard...	2021-08-16	-
46	EfficientGCN-B4	89.1	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
47	ST-GCN [PYSKL, 2D Skeleton]	89	No	Spatial Temporal Graph Convolutional Networks fo...	2018-01-23	Code
48	ST-GCN [PYSKL, 3D Skeleton]	88.4	No	Spatial Temporal Graph Convolutional Networks fo...	2018-01-23	Code
49	MSSTNet	88.3	No	-	-	Code
50	PA-ResGCN-B19	88.3	No	Stronger, Faster and More Explainable: A Graph C...	2020-10-20	Code
51	EfficientGCN-B2	88	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
52	VPN	87.8	Yes	VPN: Learning Video-Pose Embedding for Activitie...	2020-07-06	Code
53	ViewCon (RGB)	87.5	No	-	-	Code
54	VA-CNN (ResNeXt-101)	86.9	No	-	-	-
55	VPN (RGB + Pose)	86.3	Yes	VPN: Learning Video-Pose Embedding for Activitie...	2020-07-06	Code
56	3s-HYSP	86.3	No	HYperbolic Self-Paced Learning for Self-Supervis...	2023-03-10	Code
57	S-TR (2-stream)	86.2	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
58	CoS-TR* (2-stream)	86.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
59	CoST-GCN* (2-stream)	85.5	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
60	AGCN (2-stream)	85.4	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
61	ST-GCN (2-stream)	85.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
62	EfficientGCN-B0	84.3	No	Constructing Stronger and Faster Baselines for S...	2021-06-29	Code
63	HYSP	82	No	HYperbolic Self-Paced Learning for Self-Supervis...	2023-03-10	Code
64	CoAGCN* (2-stream)	82	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
65	S-TR (1-stream)	81.8	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
66	CoS-TR* (1-stream)	81.7	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
67	CoST-GCN* (1-stream)	81.6	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
68	AGCN (1-stream)	80.7	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
69	3s-USDRL (DSTE) This work	79.3	No	USDRL: Unified Skeleton-Based Dense Representati...	2024-12-12	Code
70	CoAGCN* (1-stream)	79.1	No	Continual Spatio-Temporal Graph Convolutional Ne...	2022-03-21	Code
71	ST-GCN + AS-GCN w/DH-TCN	78.3	No	Vertex Feature Encoding and Hierarchical Tempora...	2019-12-20	-
72	Gimme Signals (AIS)	70.8	No	Gimme Signals: Discriminative signal encoding fo...	2020-03-13	Code
73	TSRJI	67.9	No	Skeleton Image Representation for 3D Action Reco...	2019-09-11	Code
74	Skelemotion + Yang et al. (skeleton only)	66.9	No	SkeleMotion: A New Representation of Skeleton Jo...	2019-07-30	Code
75	Body Pose Evolution Map	64.6	No	-	-	-

#1DSCNet (RGB + Pose)
96.7
Accuracy (Cross-Setup)
No paperCode
#2PoseC3D (RGB + Pose)SOTA
96.4
Accuracy (Cross-Setup)· 2021-04-28
Revisiting Skeleton-based Action Recognition Code
#3π-ViT (RGB + Pose)
96.1
Accuracy (Cross-Setup)· Extra Data· 2023-11-30
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living Code
#4MMNet (RGB + Pose)
94.4
Accuracy (Cross-Setup)· Extra Data
No paperCode
#5EPP-Net (Parsing + Pose)
92.8
Accuracy (Cross-Setup)· 2024-01-04
Explore Human Parsing Modality for Action Recognition Code
#6STAR-Transformer (RGB + Pose)
92.7
Accuracy (Cross-Setup)· 2022-10-14
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition
#7EPAM-Net
92.4
Accuracy (Cross-Setup)· 2024-08-10
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition Code
#8ProtoGCN
92.2
Accuracy (Cross-Setup)· 2024-11-28
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition Code
#9MSA-GCN
92.2
Accuracy (Cross-Setup)
No paper
#10π-ViT (RGB only)
91.9
Accuracy (Cross-Setup)· Extra Data· 2023-11-30
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living Code
#11JMDA (based on Skeleton MixFormer)
91.9
Accuracy (Cross-Setup)
No paperCode
#12LA-GCN
91.8
Accuracy (Cross-Setup)· Extra Data· 2023-05-21
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition Code
#13IPP-Net (Parsing + Pose)
91.7
Accuracy (Cross-Setup)· 2023-07-16
Integrating Human Parsing and Pose Network for Human Action Recognition Code
#14Shap-Mix
91.7
Accuracy (Cross-Setup)· 2024-07-17
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition Code
#15MMCL
91.7
Accuracy (Cross-Setup)· Extra Data· 2024-07-22
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition Code
#16TSGCNeXt
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
#17HD-GCN
91.6
Accuracy (Cross-Setup)· 2022-08-23
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#18BlockGCN
91.5
Accuracy (Cross-Setup)
No paperCode
#19Lit-llama
91.5
Accuracy (Cross-Setup)· 2024-03-31
LLMs are Good Action Recognizers
#203DA (RGB + Pose)
91.4
Accuracy (Cross-Setup)· 2022-12-12
Cross-Modal Learning with 3D Deformable Attention for Action Recognition
#21JPFormer(Pose)
91.4
Accuracy (Cross-Setup)
No paperCode
#22SkateFormer
91.4
Accuracy (Cross-Setup)· 2024-03-14
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition Code
#23JPFormer
91.4
Accuracy (Cross-Setup)
No paperCode
#24MAMP
91.3
Accuracy (Cross-Setup)· 2023-08-14
Masked Motion Predictors are Strong 3D Action Representation Learners Code
#25Hyperformer
91.3
Accuracy (Cross-Setup)· 2022-11-17
Hypergraph Transformer for Skeleton-based Action Recognition Code
#26DG-STGCN
91.3
Accuracy (Cross-Setup)· 2022-10-12
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition Code
#27STEP-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
#28InfoGCN
91.2
Accuracy (Cross-Setup)
No paperCode
#29LST
91.1
Accuracy (Cross-Setup)· Extra Data· 2022-08-10
Generative Action Description Prompts for Skeleton-based Action Recognition Code
#30Stream-GCN
91
Accuracy (Cross-Setup)· 2023-06-13
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
#31SkeletonGCL (based on CTR-GCN)
91
Accuracy (Cross-Setup)· 2023-01-26
Graph Contrastive Learning for Skeleton-based Action Recognition Code
#32DSTSA-GCN
90.97
Accuracy (Cross-Setup)· 2025-01-21
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling Code
#33DSTSA-GCN
90.97
Accuracy (Cross-Setup)· 2025-01-21
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling Code
#34TCA-GCN
90.8
Accuracy (Cross-Setup)· 2022-05-31
Skeleton-based Action Recognition via Temporal-Channel Aggregation Code
#35ST-GCN++ [PYSKL, 3D Skeleton]
90.8
Accuracy (Cross-Setup)· 2022-05-19
PYSKL: Towards Good Practices for Skeleton Action Recognition Code
#36VPN++ (RGB + Pose)
90.7
Accuracy (Cross-Setup)· Extra Data· 2021-05-17
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living Code
#37PSUMNet
90.6
Accuracy (Cross-Setup)· 2022-08-11
PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition Code
#38CTR-GCN
90.6
Accuracy (Cross-Setup)· 2021-07-26
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition Code
#39DVANet (RGB only)
90.4
Accuracy (Cross-Setup)· 2023-12-10
DVANet: Disentangling View and Action Features for Multi-View Action Recognition Code
#40STGAT
90.4
Accuracy (Cross-Setup)· 2022-08-18
Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition Code
#41TSGCNeXT
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
#42PoseC3D (w. HRNet 2D Skeleton)
90.3
Accuracy (Cross-Setup)· 2021-04-28
Revisiting Skeleton-based Action Recognition Code
#43MaskCLR
89.5
Accuracy (Cross-Setup)
No paper
#44DualHead-Net
89.3
Accuracy (Cross-Setup)· 2021-08-10
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition Code
#45Skeletal GNN
89.2
Accuracy (Cross-Setup)· 2021-08-16
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
#46EfficientGCN-B4
89.1
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#47ST-GCN [PYSKL, 2D Skeleton]SOTA
89
Accuracy (Cross-Setup)· 2018-01-23
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#48ST-GCN [PYSKL, 3D Skeleton]
88.4
Accuracy (Cross-Setup)· 2018-01-23
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition Code
#49MSSTNet
88.3
Accuracy (Cross-Setup)
No paperCode
#50PA-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
#51EfficientGCN-B2
88
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#52VPN
87.8
Accuracy (Cross-Setup)· Extra Data· 2020-07-06
VPN: Learning Video-Pose Embedding for Activities of Daily Living Code
#53ViewCon (RGB)
87.5
Accuracy (Cross-Setup)
No paperCode
#54VA-CNN (ResNeXt-101)
86.9
Accuracy (Cross-Setup)
No paper
#55VPN (RGB + Pose)
86.3
Accuracy (Cross-Setup)· Extra Data· 2020-07-06
VPN: Learning Video-Pose Embedding for Activities of Daily Living Code
#563s-HYSP
86.3
Accuracy (Cross-Setup)· 2023-03-10
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations Code
#57S-TR (2-stream)
86.2
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#58CoS-TR* (2-stream)
86.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#59CoST-GCN* (2-stream)
85.5
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#60AGCN (2-stream)
85.4
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#61ST-GCN (2-stream)
85.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#62EfficientGCN-B0
84.3
Accuracy (Cross-Setup)· 2021-06-29
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition Code
#63HYSP
82
Accuracy (Cross-Setup)· 2023-03-10
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations Code
#64CoAGCN* (2-stream)
82
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#65S-TR (1-stream)
81.8
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#66CoS-TR* (1-stream)
81.7
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#67CoST-GCN* (1-stream)
81.6
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#68AGCN (1-stream)
80.7
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#693s-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
#70CoAGCN* (1-stream)
79.1
Accuracy (Cross-Setup)· 2022-03-21
Continual Spatio-Temporal Graph Convolutional Networks Code
#71ST-GCN + AS-GCN w/DH-TCN
78.3
Accuracy (Cross-Setup)· 2019-12-20
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition
#72Gimme Signals (AIS)
70.8
Accuracy (Cross-Setup)· 2020-03-13
Gimme Signals: Discriminative signal encoding for multimodal activity recognition Code
#73TSRJI
67.9
Accuracy (Cross-Setup)· 2019-09-11
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints Code
#74Skelemotion + Yang et al. (skeleton only)
66.9
Accuracy (Cross-Setup)· 2019-07-30
SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition Code
#75Body Pose Evolution Map
64.6
Accuracy (Cross-Setup)
No paper