List your company
ResearchFormerly WizWand

Skeleton-based Action Recognition on NTU RGB+D (Cross-View)

98.2AccuracySkeletonAgent
93.5294.73595.9597.165Oct 11, 2019Oct 22, 2020Nov 3, 2021Nov 16, 2022Nov 28, 2023Dec 9, 2024Dec 22, 2025
Updated 8mo ago

Evaluation results

MethodLinks
SkeletonAgentEnsemble size=62025.1198.2——
SkeletonAgentEnsemble size=42025.1198——
SkateFormerPublication=ECCV 20242025.1197.8——
ProtoGCNPublication=CVPR 20252025.1197.8——
Hyper-GCNPublication=ICCV 20252025.1197.8——
SkeletonAgentEnsemble size=22025.1197.7——
DS-GCNPublication=AAAI 20242025.1197.5——
PYSKLPublication=ACM MM 20222025.1197.4——
HD-GCNPublication=ICCV 20232025.1197.2——
Skeleton MixFormerPublication=ACM MM 20232025.1197.2——
InfoGCNPublication=CVPR 20222025.1197.1——
UPSPublication=CVPR 20232025.1197——
GAPPublication=ICCV 20232025.1197——
BlockGCNPublication=CVPR 20242025.1197——
STFPublication=AAAI 20222025.1196.9——
CTR-GCN2023.0196.8——
CTR-GCNPublication=ICCV 20212025.1196.8——
FR-HeadPublication=CVPR 20232025.1196.8——
CTR-GCNParam. (M)=1.46, FLOPs (G)=7.88, Power (mJ)=36.252025.1296.8——
FR-HeadParam. (M)=1.3, FLOPs (G)=7.08, Power (mJ)=32.572025.1296.8——
Info-GCNParam. (M)=1.6, FLOPs (G)=7.36, Power (mJ)=33.862025.1296.7——
DeCoupleGCNYear=2020, # Ens=4, # Params (M)=13.72, GFlops=102.32021.0596.6——
MST-GCNPublication=AAAI 20212025.1196.6——
4s Shift-GCN2023.0196.5——
Shift-GCNFLOPs (G)=10, Power (mJ)=462025.1296.5——
MSTYear=2021, # Ens=22021.0596.4——
FGCN2020.0396.3——
AGE-EnsInput=S(B)&S(J+B)&V(J+B), # Ens=32021.0596.3——
AGE-EnsInput=S(J)&S(B)&S(J+B)&V(J+B), # Ens=42021.0596.3——
Action Capsules2023.0196.3——
MS-AAGCNNets=GCN2020.0396.2——
MS-AAGCNYear=2019, Architecture=GCN2020.0396.2——
MS-G3DYear=2020, # Ens=2, # Params (M)=6.44, GFlops=98.02021.0596.2——
MS-AAGCN2023.0196.2——
MS-G3DPublication=CVPR 20202025.1196.2——
MS-G3DParam. (M)=3.19, FLOPs (G)=48.88, Power (mJ)=239.512025.1296.2——
DGNNNets=GCN2020.0396.1——
DGNNYear=2019, Architecture=GCN2020.0396.1——
DGNN2020.0396.1——
DGNNParameter number (million)=26.242020.1096.1——
DGNNYear=2019, # Ens=4, # Params (M)=8.06, GFlops=71.12021.0596.1——
Efficient-Self-AttentionYear=2022, # Ens=42021.0596.1——
AGE-EnsInput=S(J+B)&V(J+B), # Ens=22021.0596.1——
JB-AAGCNNets=GCN2020.0396——
JB-AAGCNYear=2019, Architecture=GCN2020.0396——
PA-ResGCN-B19Inference speed (sequences/(second*GPU))=38.3, Parameter number (million)=3.642020.1096——
BSL-EnsInput=S(J)&S(B)&S(J+B)&V(J+B), # Ens=42021.0595.9——
Ours(Joint+Bone)2019.1195.7——
GCN-NAS(Joint&Bone)Nets=GCN2020.0395.7——
GCN-NAS(Joint&Bone)Year=2019, Architecture=GCN2020.0395.7——
NAS-GCNParameter number (million)=6.572020.1095.7——
BSL-EnsInput=S(J+B)&V(J+B), # Ens=22021.0595.7——
BSL-EnsInput=S(B)&S(J+B)&V(J+B), # Ens=32021.0595.7——
PA-ResGCN-N51Inference speed (sequences/(second*GPU))=54.8, Parameter number (million)=1.142020.1095.6——
AGE-EnsInput=S(J)&V(J), # Ens=22021.0595.5——
AGE-EnsInput=S(B)&V(B), # Ens=22021.0595.5——
2s-AGCNNets=GCN, Evaluation Protocol=self-evaluated2020.0395.3——
2s-AGCNYear=2019, Architecture=GCN, Implementation=Trained by authors2020.0395.399.4—
AdaSGNYear=2021, # Ens=42021.0595.3——
AGE-SInput=Joint+Bone, # Ens=12021.0595.2——
2S-AGCNConference=CVPR20192019.1195.1——
2s-AGCN2020.0395.1——
2s-AGCNInference speed (sequences/(second*GPU))=22.3, Parameter number (million)=6.942020.1095.1——
2s-AGCNYear=2019, # Ens=4, # Params (M)=6.72, GFlops=37.22021.0595.1——
Ta-CNNYear=2022, # Ens=22021.0595.1——
BSL-SInput=Joint+Bone, # Ens=12021.0595.1——
2s-AGCNPublication=CVPR 20192025.1195.1——
2S-AGCNParam. (M)=3.48, FLOPs (G)=37.32, Power (mJ)=182.872025.1295.1——
AGC-LSTMNets=GCN+LSTM2020.0395——
AGC-LSTM(Joint&Part)Year=2019, Architecture=GCN+LSTM2020.0395——
AGC-LSTM2020.0395——
VA-fusionParameter number (million)=24.602020.1095——
AGC-LSTMParameter number (million)=22.892020.1095——
PL-GCNParameter number (million)=20.702020.1095——
AGC-LSTMYear=2019, # Ens=22021.0595——
2s AGC-LSTM2023.0195——
ResGCN-B19 (Basic)Inference speed (sequences/(second*GPU))=44.0, Parameter number (million)=3.262020.1094.8——
AGE-SInput=Bone, # Ens=12021.0594.8——
AGE-VInput=Bone, # Ens=12021.0594.8——
BSL-EnsInput=S(J)&V(J), # Ens=22021.0594.7——
BSL-EnsInput=S(B)&V(B), # Ens=22021.0594.7——
SGNYear=2020, # Ens=1, # Params (M)=0.69, GFlops=15.42021.0594.5——
AGE-SInput=Joint, # Ens=12021.0594.5——
AGE-VInput=Joint, # Ens=12021.0594.5——
Signal-SGN++ (4 ensemble)Param. (M)=1.72, FLOPs (G)=6.44, SOPs (G)=1.252, Power (mJ)=1.4762025.1294.5——
GR-GCNConference=ACMM20192019.1194.3——
GR-GCN2020.1094.3——
AS-GCNConference=CVPR20192019.1194.2——
AS-GCNNets=GCN2020.0394.2——
AS-GCNYear=2019, Architecture=GCN2020.0394.2——
AS-GCN2020.0394.2——
AS-GCNParameter number (million)=6.992020.1094.2——
AS-GCNYear=2019, # Ens=1, # Params (M)=7.17, GFlops=35.52021.0594.2——
AS-GCN2023.0194.2——
Bs-AGCNNets=GCN, Evaluation Protocol=self-evaluated2020.0394.1——
Bs-AGCNYear=2019, Architecture=GCN, Implementation=Trained by authors2020.0394.199.23—
AGE-VInput=Joint+Bone, # Ens=12021.0594——
dense-IndRNN-augAugmentation=true2019.1093.97——
BSL-SInput=Joint, # Ens=12021.0593.7——
3SCNN2023.0193.7——