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

Showing 401419 of 419 papers

TitleStatusHype
Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringCode0
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data0
NTU RGB+D: A Large Scale Dataset for 3D Human Activity AnalysisCode0
Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks0
Pose for Action - Action for Pose0
Structural-RNN: Deep Learning on Spatio-Temporal GraphsCode0
Hierarchical recurrent neural network for skeleton based action recognition0
Modeling Video Evolution for Action Recognition0
Joint Action Recognition and Pose Estimation From Video0
Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition0
Finding Action TubesCode0
10,000+ Times Accelerated Robust Subset Selection (ARSS)0
Skeletal quads: Human action recognition using joint quadruples0
Large-Scale Video Classification with Convolutional Neural NetworksCode1
Human Action Recognition by Representing 3D Skeletons as Points in a Lie GroupCode0
Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Anticipation0
UCF101: A Dataset of 101 Human Actions Classes From Videos in The WildCode0
Learning Human Activities and Object Affordances from RGB-D Videos0
View invariant human action recognition using histograms of 3D joints0
Show:102550
← PrevPage 9 of 9Next →

No leaderboard results yet.