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 201–225 of 419 papers

TitleStatusHype
Skeleton-Based Action Recognition with Spatial-Structural Graph ConvolutionCode0
Skeleton-Based Action Recognition With Directed Graph Neural NetworksCode0
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional NetworksCode0
Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence CriterionCode0
Skeleton-Based Human Action Recognition with Noisy LabelsCode0
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference JointsCode0
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action RecognitionCode0
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action RecognitionCode0
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action RecognitionCode0
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action RecognitionCode0
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action RecognitionCode0
Structure-Aware Convolutional Neural NetworksCode0
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action RecognitionCode0
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action RecognitionCode0
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action RecognitionCode0
Tracking Emerges by Colorizing VideosCode0
UCF101: A Dataset of 101 Human Actions Classes From Videos in The WildCode0
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints InvarianceCode0
Unsupervised Motion Representation Learning with Capsule AutoencodersCode0
View Adaptive Neural Networks for High Performance Skeleton-based Human Action RecognitionCode0
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton DataCode0
View-Invariant Probabilistic Embedding for Human PoseCode0
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition—0
MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition—0
Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition—0
Show:102550
← PrevPage 9 of 17Next →

No leaderboard results yet.