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 101–125 of 419 papers

TitleStatusHype
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action RecognitionCode1
Learning Discriminative Representations for Skeleton Based Action RecognitionCode1
Logsig-RNN: a novel network for robust and efficient skeleton-based action recognitionCode1
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton SequencesCode1
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action RecognitionCode1
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action RecognitionCode1
Masked Motion Predictors are Strong 3D Action Representation LearnersCode1
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action RecognitionCode1
Make Skeleton-based Action Recognition Model Smaller, Faster and BetterCode1
Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture RecognitionCode1
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action RecognitionCode1
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational AutoencodersCode1
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionCode1
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning PotentialCode1
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
Multi-Modality Co-Learning for Efficient Skeleton-based Action RecognitionCode1
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action RecognitionCode1
Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action RecognitionCode1
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed TransformerCode1
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket SportsCode1
Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action DetectionCode0
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and DetectionCode0
Non-Local Graph Convolutional Networks for Skeleton-Based Action RecognitionCode0
ADG-Pose: Automated Dataset Generation for Real-World Human Pose EstimationCode0
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action RecognitionCode0
Show:102550
← PrevPage 5 of 17Next →

No leaderboard results yet.