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 51–100 of 419 papers

TitleStatusHype
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action RecognitionCode1
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition—0
Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action DetectionCode0
Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation—0
An Improved Graph Pooling Network for Skeleton-Based Action Recognition—0
HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action RecognitionCode1
MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition—0
In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action RecognitionCode0
Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition—0
LLMs are Good Action Recognizers—0
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action RecognitionCode2
GCN-DevLSTM: Path Development for Skeleton-Based Action RecognitionCode1
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner—0
Skeleton-Based Human Action Recognition with Noisy LabelsCode0
SkateFormer: Skeletal-Temporal Transformer for Human Action RecognitionCode2
Taylor Videos for Action RecognitionCode1
Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition—0
AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture SearchCode0
Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition—0
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition—0
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action RecognitionCode2
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning—0
Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton SequenceCode0
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action RecognitionCode0
Navigating Open Set Scenarios for Skeleton-based Action RecognitionCode1
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action RecognitionCode0
Hulk: A Universal Knowledge Translator for Human-Centric TasksCode2
VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViGCode1
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the ArtCode1
SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System—0
InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action RecognitionCode1
Proving the Potential of Skeleton Based Action Recognition to Automate the Analysis of Manual Processes—0
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-SupervisionCode0
Exploring Self-supervised Skeleton-based Action Recognition in Occluded EnvironmentsCode1
SkeleTR: Towrads Skeleton-based Action Recognition in the Wild—0
Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action RecognitionCode1
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition—0
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action RecognitionCode1
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action RecognitionCode1
Balanced Representation Learning for Long-tailed Skeleton-based Action RecognitionCode0
Local Spherical Harmonics Improve Skeleton-Based Hand Action RecognitionCode0
Ske2Grid: Skeleton-to-Grid Representation Learning for Action RecognitionCode1
Masked Motion Predictors are Strong 3D Action Representation LearnersCode1
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and MaximizationCode1
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-trainingCode1
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionCode1
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning—0
Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition—0
Show:102550
← PrevPage 2 of 9Next →

No leaderboard results yet.