SOTAVerified

Skeleton Based Action Recognition

Skeleton-based Action Recognition is a computer vision task that involves recognizing human actions from a sequence of 3D skeletal joint data captured from sensors such as Microsoft Kinect, Intel RealSense, and wearable devices. The goal of skeleton-based action recognition is to develop algorithms that can understand and classify human actions from skeleton data, which can be used in various applications such as human-computer interaction, sports analysis, and surveillance.

( Image credit: View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 391–400 of 419 papers

TitleStatusHype
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks—0
Deep Learning on Lie Groups for Skeleton-based Action Recognition—0
Jointly learning heterogeneous features for rgb-d activity recognition—0
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep NetworksCode0
PointNet: Deep Learning on Point Sets for 3D Classification and SegmentationCode1
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data—0
Temporal Convolutional Networks for Action Segmentation and DetectionCode1
Multi-region two-stream R-CNN for action detection—0
Semi-Supervised Classification with Graph Convolutional NetworksCode1
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition—0
Show:102550
← PrevPage 40 of 42Next →

No leaderboard results yet.