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 401–419 of 419 papers

TitleStatusHype
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNCode0
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action RecognitionCode0
Improving Skeleton-based Action Recognition with Interactive Object InformationCode0
Idempotent Unsupervised Representation Learning for Skeleton-Based Action RecognitionCode0
Simple yet efficient real-time pose-based action recognitionCode0
Human Action Recognition by Representing 3D Skeletons as Points in a Lie GroupCode0
High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action RecognitionCode0
Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity RecognitionCode0
SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action RecognitionCode0
Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional NetworkCode0
DeepGRU: Deep Gesture Recognition UtilityCode0
Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton SequenceCode0
Action Recognition with Multi-stream Motion Modeling and Mutual Information MaximizationCode0
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action RecognitionCode0
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
Cross-modal Learning by Hallucinating Missing Modalities in RGB-D VisionCode0
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints InvarianceCode0
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action RecognitionCode0
Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringCode0
Show:102550
← PrevPage 9 of 9Next →

No leaderboard results yet.