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 111–120 of 419 papers

TitleStatusHype
Simplifying Graph Convolutional NetworksCode1
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionCode1
Graph Attention NetworksCode1
Quo Vadis, Action Recognition? A New Model and the Kinetics DatasetCode1
Skeleton-based Action Recognition with Convolutional Neural NetworksCode1
PointNet: Deep Learning on Point Sets for 3D Classification and SegmentationCode1
Temporal Convolutional Networks for Action Segmentation and DetectionCode1
Semi-Supervised Classification with Graph Convolutional NetworksCode1
Large-Scale Video Classification with Convolutional Neural NetworksCode1
Show:102550
← PrevPage 12 of 42Next →

No leaderboard results yet.