SOTAVerified

3D Action Recognition

Papers

Showing 125 of 91 papers

TitleStatusHype
A System for Real-Time Interactive Analysis of Deep Learning TrainingCode2
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton SequencesCode1
On the Utility of 3D Hand Poses for Action RecognitionCode1
Masked Motion Predictors are Strong 3D Action Representation LearnersCode1
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionCode1
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual DistillationCode1
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action RecognitionCode1
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action RecognitionCode1
PSTNet: Point Spatio-Temporal Convolution on Point Cloud SequencesCode1
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time SurfacesCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal DecompositionCode1
3DVNet: Multi-View Depth Prediction and Volumetric RefinementCode1
Real-time 3D human action recognition based on Hyperpoint sequenceCode1
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud VideosCode1
BABEL: Bodies, Action and Behavior with English LabelsCode1
Revisiting Skeleton-based Action RecognitionCode1
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksCode1
Reconstructing undersampled photoacoustic microscopy images using deep learningCode1
3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoCode1
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionCode1
Unsupervised Learning of Object Keypoints for Perception and ControlCode1
TSM: Temporal Shift Module for Efficient Video UnderstandingCode1
Grad-CAM++: Improved Visual Explanations for Deep Convolutional NetworksCode1
Show:102550
← PrevPage 1 of 4Next →

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