Skip to content

Leo-FengPan/Awesome-Skeleton-based-Action-Recognition

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

48 Commits
 
 
 
 

Repository files navigation

Awesome Skeleton-based Action Recognition

Awesome PRs Welcome

We collect existing papers on skeleton-based action recognition published in prominent conferences and journals.

This paper list will be continuously updated at the end of each month.

Survey

  • Human Action Recognition from Various Data Modalities: A Review (TPAMI 2022) [paper]
  • Human action recognition and prediction: A survey (IJCV 2022) [paper]
  • Action recognition based on RGB and skeleton data sets: A survey (Neurocomputing 2022) [paper]
  • A Comparative Review of Recent Kinect-based Action Recognition Algorithms (TIP 2019) [paper]
  • ANUBIS: Review and Benchmark Skeleton-Based Action Recognition Methods with a New Dataset (2022 arXiv paper) [paper] [code]
  • A Survey on 3D Skeleton-Based Action Recognition Using Learning Method (2020 arXiv paper) [paper]

Papers

2023

CVPR

  • Learning Discriminative Representations for Skeleton Based Action Recognition [paper] [code]
  • Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition [paper] [code]
  • STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition [paper] [code]
  • HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions [paper] [code]
  • Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition [code]
  • 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition [paper]
  • Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features [paper]
  • Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling [paper]

ICLR

  • Graph Contrastive Learning for Skeleton-based Action Recognition [paper] [code]
  • Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations [paper] [code]

AAAI

  • Language Supervised Training for Skeleton-based Action Recognition [paper] [code]
  • Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations [paper] [code]
  • Anonymization for Skeleton Action Recognition [paper] [code]
  • Defending Black-box Skeleton-based Human Activity Classifiers [paper] [code]
  • Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning [paper] [code]
  • Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences [paper] [code]
  • Novel Motion Patterns Matter for Practical Skeleton-based Action Recognition [paper]

IJCAI

  • Part Aware Contrastive Learning for Self-Supervised Action Recognition [paper] [code]

ICIP

  • Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition [paper] [code]

TMM

  • Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions [paper] [code]
  • Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks [paper]

TNNLS

  • Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition [paper]

PR

  • Online Skeleton-based Action Recognition with Continual Spatio-Temporal Graph Convolutional Networks [paper] [code]
  • SpatioTemporal Focus for Skeleton-based Action Recognition [paper]

arXiv papers

  • Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition [paper] [code]
  • TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential [paper] [code]
  • Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [paper]
  • Action Capsules: Human Skeleton Action Recognition [paper]
  • Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN) [paper]
  • Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition [paper]
  • DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition [paper]
  • Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition [paper]
  • Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition [paper]
  • Attack is Good Augmentation: Towards Skeleton-Contrastive Representation Learning [paper]
  • Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization [paper]
  • Skeleton-based action analysis for ADHD diagnosis [paper]
  • Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis [paper]
  • Cross-view Action Recognition via Contrastive View-invariant Representation [paper]

2022

CVPR

  • InfoGCN: Representation Learning for Human Skeleton-based Action Recognition [paper] [code]
  • Revisiting Skeleton-based Action Recognition [paper] [code]

ECCV

  • CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation [paper] [code]
  • Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning [paper] [code]
  • Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning [paper] [code]
  • Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition [paper] [code]
  • Contrastive Positive Mining for Unsupervised 3D Action Representation Learning [paper]
  • Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition [paper]

AAAI

  • Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition [paper] [code]
  • Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition [paper] [code]
  • Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition [paper]

ACM MM

  • PYSKL: Towards Good Practices for Skeleton Action Recognition [paper] [code]
  • Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition [paper] [code]
  • Skeleton-based Action Recognition via Adaptive Cross-Form Learning [paper] [code]

CVPRW

  • Bootstrapped Representation Learning for Skeleton-Based Action Recognition [paper]

ECCVW

  • Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks [paper] [code]
  • PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition [paper] [code]
  • Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns [paper]

ACCV

  • Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition [paper]
  • Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition [paper]

WACV

  • Skeleton-DML: deep metric learning for skeleton-based one-shot action recognition [paper] [code]
  • Generative adversarial graph convolutional networks for human action synthesis [paper] [code]
  • Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [paper]

ICPR

  • Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network [paper]

TPAMI

  • Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition [paper] [code]
  • Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition [paper] [code]

IJCV

  • Action2video: Generating Videos of Human 3D Actions [paper]

TIP

  • Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition [paper] [code]
  • X-Invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition [paper]

TMM

  • Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition [paper]

TCSVT

  • Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition [paper] [code]

TNNLS

  • Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition [paper] [code]

Neurocomputing

  • Forward-reverse adaptive graph convolutional networks for skeleton-based action recognition [paper] [code]
  • AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement [paper]

arXiv papers

  • Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition [paper] [code]
  • HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment [paper] [code]
  • Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition [paper] [code]
  • Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition [paper] [code]
  • Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition [paper] [code]
  • ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting [paper] [code]
  • DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition [paper] [code]
  • MotionBERT: Unified Pretraining for Human Motion Analysis [paper] [code]
  • Hypergraph Transformer for Skeleton-based Action Recognition [paper] [code]
  • Skeleton-based Action Recognition Via Temporal-Channel Aggregation [paper]
  • A New Spatial Adjacency Matrix of Skeleton Data Based on Self-loop and Adaptive Weights [paper]
  • SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition [paper]
  • View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning [paper]
  • Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition [paper]

2021

CVPR

  • 3D Human Action Representation Learning via Cross-View Consistency Pursuit [paper] [code]
  • BASAR:Black-box Attack on Skeletal Action Recognition [paper] [code]
  • Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack [paper] [code]

ICCV

  • Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition [paper] [code]
  • AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition [paper] [code]
  • Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning [paper]
  • Self-supervised 3d skeleton action representation learning with motion consistency and continuity [paper]

NeurIPS

  • Unsupervised Motion Representation Learning with Capsule Autoencoders [paper]

AAAI

  • Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition [paper] [code]
  • Spatio-temporal difference descriptor for skeleton-based action recognition [paper]

ACM MM

  • Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [paper] [code]
  • Skeleton-Contrastive 3D Action Representation Learning [paper] [code]
  • STST: Spatial-temporal specialized transformer for skeleton-based action recognition [paper] [code]
  • Modeling the uncertainty for self-supervised 3d skeleton action representation learning [paper]

CVPRW

  • One-shot action recognition in challenging therapy scenarios [paper] [code]

BMVC

  • UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition [paper] [code]
  • Unsupervised human action recognition with skeletal graph Laplacian and self-supervised viewpoints invariance [paper] [code]

WACV

  • JOLO-GCN: mining joint-centered light-weight information for skeleton-based action recognition [paper]

ICPR

  • Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition [paper]

ICIP

  • Syntactically guided generative embeddings for zero-shot skeleton action recognition [paper] [code]

ICRA

  • Pose Refinement Graph Convolutional Network for Skeleton-basedAction Recognition [paper] [code]

TPAMI

  • Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction [paper]
  • Tensor Representations for Action Recognition [paper]

IJCV

  • Quo Vadis, Skeleton Action Recognition? [paper] [code]

TIP

  • Extremely Lightweight Skeleton-Based Action Recognition with ShiftGCN++ [paper] [code]
  • Structural knowledge distillation for efficient skeleton-based action recognition [paper] [code]
  • Hypergraph neural network for skeleton-based action recognition [paper]
  • Feedback Graph Convolutional Network for Skeleton-Based Action Recognition [paper]

TIFS

  • REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition [paper] [code]

TMM

  • Prototypical contrast and reverse prediction: Unsupervised skeleton based action recognition [paper] [code]
  • A Multi-Stream Graph Convolutional Networks-Hidden Conditional Random Field Model for Skeleton-Based Action Recognition [paper]
  • Multi-localized sensitive autoencoder-attention-lstm for skeleton-based action recognition [paper]
  • Laga-net: Local-and-global attention network for skeleton based action recognition [paper]

TCSVT

  • Fuzzy integral-based CNN classifier fusion for 3D skeleton action recognition [paper] [code]
  • A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition [paper]
  • Spatial temporal graph deconvolutional network for skeleton-based human action recognition [paper]
  • Symmetrical Enhanced Fusion Network for Skeleton-Based Action Recognition [paper]
  • Graph2Net: Perceptually-enriched graph learning for skeleton-based action recognition [paper]
  • A cross view learning approach for skeleton-based action recognition [paper]
  • Multi-stream interaction networks for human action recognition [paper]

PR

  • Arbitrary-view human action recognition via novel-view action generation [paper] [code]
  • Tripool: Graph triplet pooling for 3D skeleton-based action recognition [paper]
  • Action recognition using kinematics posture feature on 3D skeleton joint locations [paper]
  • Scene image and human skeleton-based dual-stream human action recognition [paper]

Neurocomputing

  • Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistance [paper]
  • Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition [paper]
  • Adaptive multi-view graph convolutional networks for skeleton-based action recognition [paper]
  • Rethinking the ST-GCNs for 3D skeleton-based human action recognition [paper]
  • Attention adjacency matrix based graph convolutional networks for skeleton-based action recognition [paper]

arXiv papers

  • Star: Sparse transformer-based action recognition [paper] [code]
  • Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [paper]
  • 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na¨ıve [paper]

2020

CVPR

  • Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [paper] [code]
  • Skeleton-Based Action Recognition with Shift Graph Convolutional Network [paper] [code]
  • Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [paper] [code]
  • PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition [paper] [code]
  • Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction [paper] [code]
  • Context aware graph convolution for skeleton-based action recognition [paper]

ECCV

  • Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition [paper] [code]
  • Unsupervised 3d human pose representation with viewpoint and pose disentanglement [paper] [code]
  • Adversarial Self-supervised Learning for Semi-supervised 3D Action Recognition [paper]

AAAI

  • Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching [paper] [code]
  • Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions [paper]
  • Part-Level Graph Convolutional Network for Skeleton-Based Action Recognition [paper]

ACM MM

  • Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition [paper] [code]
  • Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [paper] [code]
  • Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition [paper] [code]
  • MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition [paper] [code]
  • Group-Skeleton-Based Human Action Recognition in Complex Events [paper]
  • Mix dimension in poincaré geometry for 3d skeleton-based action recognition [paper]

ACCV

  • Decoupled spatial-temporal attention network for skeleton-based action-gesture recognition [paper]

TPAMI

  • Learning multi-view interactional skeleton graph for action recognition [paper] [code]
  • Multi-task deep learning for real-time 3D human pose estimation and action recognition [paper] [code]

TIP

  • Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks [paper] [code]

TMM

  • Hierarchical Soft Quantization for Skeleton-Based Human Action Recognition [paper]

TCSVT

  • Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition [paper] [code]

TNNLS

  • Adversarial attack on skeleton-based human action recognition [paper]

PR

  • Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network [paper]

2019

CVPR

  • Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition [paper] [code]
  • Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition [paper] [code]
  • Skeleton-Based Action Recognition with Directed Graph Neural Networks [paper] [code]
  • Bayesian Hierarchical Dynamic Model for Human Action Recognition [paper] [code]
  • An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition [paper]

ICCV

  • Bayesian graph convolution lstm for skeleton based action recognition [paper]
  • Making the invisible visible: Action recognition through walls and occlusions [paper]
  • Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition [paper]

AAAI

  • Graph CNNs with motif and variable temporal block for skeleton-based action recognition [paper] [code]

CVPRW

  • Three-stream convolutional neural network with multi-task and ensemble learning for 3d action recognition [paper]

WACV

  • Unsupervised feature learning of human actions as trajectories in pose embedding manifold [paper]

ICIP

  • Richly activated graph convolutional network for action recognition with incomplete skeletons [paper] [code]

ICME

  • Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention [paper]

TPAMI

  • NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding [paper] [code]
  • View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition [paper] [code]

TIP

  • Sample Fusion Network: An End-to-End Data Augmentation Network for Skeleton-Based Human Action Recognition [paper] [code]
  • View-Invariant Human Action Recognition Based on a 3D Bio-Constrained Skeleton Model [paper] [code]
  • EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks [paper]

2018

CVPR

  • Recognizing Human Actions as the Evolution of Pose Estimation Maps [paper] [code]
  • Independently recurrent neural network (indrnn): Building a longer and deeper rnn [paper] [code]
  • 2d/3d pose estimation and action recognition using multitask deep learning [paper] [code]
  • Deep progressive reinforcement learning for skeleton-based action recognition [paper]

ECCV

  • Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack [paper]
  • Adding attentiveness to the neurons in recurrent neural networks [paper]

AAAI

  • Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition [paper [code]
  • Unsupervised representation learning with long-term dynamics for skeleton based action recognition [paper] [code]
  • Spatio-temporal graph convolution for skeleton based action recognition [paper]

ACM MM

  • Optimized Skeleton-based Action Recognition via Sparsified Graph Regression [paper]
  • A large-scale varying-view rgb-d action dataset for arbitrary-view human action recognition [paper]

IJCAI

  • Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation [paper] [code]
  • Memory Attention Networks for Skeleton-based Action Recognition [paper] [code]

BMVC

  • Part-based graph convolutional network for action recognition [paper] [code]
  • A fine-to-coarse convolutional neural network for 3D human action recognition [paper]

ICIP

  • Joints relation inference network for skeleton-based action recognition [paper]

TIP

  • Beyond joints: Learning representations from primitive geometries for skeleton-based action recognition and detection [paper] [code]

TCSVT

  • Skeleton-based action recognition with gated convolutional neural networks [paper]
  • Action recognition with spatio–temporal visual attention on skeleton image sequences [paper]

PR

  • Learning content and style: Joint action recognition and person identification from human skeletons [paper]

2017

CVPR

  • Deep Learning on Lie Groups for Skeleton-based Action Recognition [paper] [code]
  • Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks [paper]
  • Global Context-Aware Attention LSTM Networks for 3D Action Recognition [paper]
  • A new representation of skeleton sequences for 3d action recognition [paper]

ICCV

  • View adaptive recurrent neural networks for high performance human action recognition from skeleton data [paper] [code]
  • Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks [paper] [code]
  • Learning action recognition model from depth and skeleton videos [paper]

AAAI

  • An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data [paper]

CVPRW

  • Interpretable 3d human action analysis with temporal convolutional networks [paper] [code]

ACM MM Workshop

  • PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding [paper]

TIP

  • Skeleton-based human action recognition with global context-aware attention LSTM networks [paper]

PR

  • Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition [paper]
  • Enhanced skeleton visualization for view invariant human action recognition [paper]

2016

CVPR

  • NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis [paper] [code]
  • Rolling rotations for recognizing human actions from 3d skeletal data [paper]

ECCV

  • Temporal segment networks: Towards good practices for deep action recognition [paper] [code]
  • Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition [paper]

AAAI

  • Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks [paper]

ACM MM

  • Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks [paper]

TCSVT

  • Skeleton optical spectra-based action recognition using convolutional neural networks [paper]

2015

CVPR

  • Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition [paper]
  • Jointly learning heterogeneous features for RGB-D activity recognition [paper]

ICCV

  • Learning Spatiotemporal Features with 3D Convolutional Networks [paper] [code]

TPAMI

  • Multimodal Multipart Learning for Action Recognition in Depth Videos [paper]

2014

CVPR

  • Cross-view Action Modeling, Learning and Recognition [paper]
  • Human action recognition by representing 3d skeletons as points in a lie group [paper]

NeurIPS

  • Two-Stream Convolutional Networks for Action Recognition in Videos [paper]

Other Resources

With all the resources available on the github website, this paper list is comprehensive and recently updated.

Last update: May 15, 2023

Feel free to contact me if you find any interesting paper is missing.

About

A curated paper list of awesome skeleton-based action recognition.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published