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 1–50 of 419 papers

TitleStatusHype
MotionBERT: A Unified Perspective on Learning Human Motion RepresentationsCode3
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action RecognitionCode2
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action RecognitionCode2
SkateFormer: Skeletal-Temporal Transformer for Human Action RecognitionCode2
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action RecognitionCode2
Hulk: A Universal Knowledge Translator for Human-Centric TasksCode2
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature AlignmentCode1
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature AggregationCode1
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language RecognitionCode1
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket SportsCode1
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology ModelingCode1
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature DecorrelationCode1
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action RecognitionCode1
Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action SegmentationCode1
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionCode1
Multi-Modality Co-Learning for Efficient Skeleton-based Action RecognitionCode1
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational AutoencodersCode1
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed TransformerCode1
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action RecognitionCode1
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton SequencesCode1
Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNNCode1
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action RecognitionCode1
HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action RecognitionCode1
GCN-DevLSTM: Path Development for Skeleton-Based Action RecognitionCode1
Taylor Videos for Action RecognitionCode1
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
Navigating Open Set Scenarios for Skeleton-based Action RecognitionCode1
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
InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action RecognitionCode1
Exploring Self-supervised Skeleton-based Action Recognition in Occluded EnvironmentsCode1
Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action RecognitionCode1
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action RecognitionCode1
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action RecognitionCode1
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
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionCode1
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action RecognitionCode1
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology AwarenessCode1
Part Aware Contrastive Learning for Self-Supervised Action RecognitionCode1
Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture RecognitionCode1
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning PotentialCode1
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action RepresentationsCode1
Learning Discriminative Representations for Skeleton Based Action RecognitionCode1
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton SequencesCode1
Graph Contrastive Learning for Skeleton-based Action RecognitionCode1
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action RecognitionCode1
Show:102550
← PrevPage 1 of 9Next →

No leaderboard results yet.