SOTAVerified

3D Action Recognition

Image: Rahmani et al

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 91 papers

TitleStatusHype
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action RecognitionCode0
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition—0
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton SequencesCode1
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition—0
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner—0
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
Learning Scene Flow With Skeleton Guidance For 3D Action Recognition—0
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization—0
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
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural ActivitiesCode0
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
Spatial-Temporal Transformer for 3D Point Cloud Sequences—0
Unsupervised View-Invariant Human Posture Representation—0
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning—0
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud VideosCode1
Show:102550
← PrevPage 1 of 4Next →
All datasetsAssembly101NTU RGB+D100 sleep nights of 8 caregivers

Benchmark Results

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