SOTAVerified

3D Action Recognition

Papers

Showing 2130 of 91 papers

TitleStatusHype
Real-time 3D human action recognition based on Hyperpoint sequenceCode1
Spatial-Temporal Transformer for 3D Point Cloud Sequences0
Unsupervised View-Invariant Human Posture Representation0
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning0
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud VideosCode1
BABEL: Bodies, Action and Behavior with English LabelsCode1
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model0
Revisiting Skeleton-based Action RecognitionCode1
Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction0
VI-Net: View-Invariant Quality of Human Movement Assessment0
Show:102550
← PrevPage 3 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HandFormer-B/21Actions Top-141.06Unverified
2TSMActions Top-135.27Unverified
3RGBPoseConv3DActions Top-133.61Unverified
4MS-G3DActions Top-128.7Unverified
5ISTA-NetActions Top-128.07Unverified
6CHASE(CTR-GCN)Actions Top-128.03Unverified
72s-AGCNActions Top-126.7Unverified
#ModelMetricClaimedVerifiedStatus
1KinetCross Subject Accuracy92.3Unverified
2PSTNet++Cross Subject Accuracy91.4Unverified
3PSTNetCross Subject Accuracy90.5Unverified
4P4TransformerCross Subject Accuracy90.2Unverified
53DV-PointNet++Cross Subject Accuracy88.8Unverified
#ModelMetricClaimedVerifiedStatus
1htf10%4Unverified