https://github.com/firework8/Awesome-Skeleton-based-Action-Recognition
A curated paper list of awesome skeleton-based action recognition.
https://github.com/firework8/Awesome-Skeleton-based-Action-Recognition
List: Awesome-Skeleton-based-Action-Recognition
action-recognition papers skeleton skeleton-based-action-recognition
Last synced: 2 months ago
JSON representation
A curated paper list of awesome skeleton-based action recognition.
- Host: GitHub
- URL: https://github.com/firework8/Awesome-Skeleton-based-Action-Recognition
- Owner: firework8
- License: mit
- Created: 2023-02-16T06:14:05.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2026-04-12T10:06:21.000Z (2 months ago)
- Last Synced: 2026-04-12T12:08:44.318Z (2 months ago)
- Topics: action-recognition, papers, skeleton, skeleton-based-action-recognition
- Homepage:
- Size: 487 KB
- Stars: 686
- Watchers: 20
- Forks: 73
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- ultimate-awesome - Awesome-Skeleton-based-Action-Recognition - A curated paper list of awesome skeleton-based action recognition. (Other Lists / Vue Lists)
- awesome-human-activity-recognition - Awesome Skeleton-based Action Recognition - GCN and transformer methods for skeleton HAR. (Related Awesome Lists / Surveys)
README
# Awesome Skeleton-based Action Recognition
[](https://github.com/sindresorhus/awesome)
[](http://makeapullrequest.com)
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.
## Table of Contents
- [Survey](#survey)
- [Papers](#papers)
- [2026](#2026)
- [2025](#2025)
- [2024](#2024)
- [2023](#2023)
- [2022](#2022)
- [2021](#2021)
- [2020](#2020)
- [2019](#2019)
- [2018](#2018)
- [2017](#2017)
- [2016](#2016)
- [2015](#2015)
- [2014](#2014)
- [Other Resources](#other-resources)
## Survey
- Human Action Recognition from Various Data Modalities: A Review (**TPAMI 2022**) [[paper](https://ieeexplore.ieee.org/abstract/document/9795869)]
- Human action recognition and prediction: A survey (**IJCV 2022**) [[paper](https://link.springer.com/article/10.1007/s11263-022-01594-9)]
- Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond (**IJCV 2026**) [[paper](https://link.springer.com/article/10.1007/s11263-025-02644-8)]
- A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions (**TNNLS 2025**) [[paper](https://ieeexplore.ieee.org/document/11282488)]
- Transformer for Skeleton-based action recognition: A review of recent advances (**Neurocomputing 2023**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231223002217)]
- Action recognition based on RGB and skeleton data sets: A survey (**Neurocomputing 2022**) [[paper](https://www.sciencedirect.com/science/article/pii/S0925231222011596)]
- A Comparative Review of Recent Kinect-based Action Recognition Algorithms (**TIP 2019**) [[paper](https://ieeexplore.ieee.org/abstract/document/8753686)]
- Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark (**2025 arXiv paper**) [[paper](https://www.researchgate.net/publication/394518696_Representation-Centric_Survey_of_Skeletal_Action_Recognition_and_the_ANUBIS_Benchmark)]
- 3D Skeleton-Based Action Recognition: A Review (**2025 arXiv paper**) [[paper](https://arxiv.org/abs/2506.00915)]
- The Journey of Action Recognition (**2025 arXiv paper**) [[paper](https://www.researchgate.net/profile/Lei-Wang-358/publication/387707420_The_Journey_of_Action_Recognition/links/677880dee74ca64e1f4b7bc9/The-Journey-of-Action-Recognition.pdf)]
- A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities (**2024 arXiv paper**) [[paper](https://arxiv.org/abs/2409.09678)]
## Papers
Statistics: 🔥 relatively highly cited | ⭐ code is available and star > 100
### 2026
**CVPR**
- SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2603.29692)] [[code](https://github.com/NingWang2049/skeletoncontext)]
- LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation [[paper](https://arxiv.org/abs/2603.24097)] [[code](https://github.com/HaoyuJi/LaDy)]
- Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation [[paper](https://arxiv.org/abs/2603.24134)] [[code](https://github.com/HaoyuJi/SpecScalpel)]
- OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition [[paper](https://arxiv.org/abs/2512.16727)]
**ICLR**
- Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation [[paper](https://openreview.net/forum?id=Vgh30npuN3)]
- Subspace Kernel Learning on Tensor Sequences [[paper](https://openreview.net/forum?id=kv22NbU2T2)]
**AAAI**
- FineTec: Fine-Grained Action Recognition under Temporal Corruption via Skeleton Decomposition and Sequence Completion [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/37838)] [[code](https://github.com/SmartDianLab/FineTec)]
- Learning Dynamics as Feedback: An Adaptive Entropy Flow Dynamics Framework for Long-tailed Human Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/39226)] [[code](https://github.com/ddddddy1221/AEED)]
- Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/37681)] [[code](https://github.com/LZYAndy/UMEG-Net)]
- SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/38852)]
- Decomposing Prompts, Composing Actions: A Multi-Granularity Prompting Approach for Incremental Action Learning [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/37326)]
**CVPRF**
- Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition [[paper](https://arxiv.org/abs/2511.09388)] [[code](https://github.com/cseeyangchen/Flora)]
**CVPRW**
- BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports [[paper](https://arxiv.org/abs/2502.21085)] [[code](https://github.com/Va6lue/BST-Badminton-Stroke-type-Transformer)]
- SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition [[paper](https://arxiv.org/abs/2604.03590)]
**ICPR**
- CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition [[paper](https://arxiv.org/abs/2509.00692)] [[code](https://github.com/Yusen-Peng/CascadeFormer)]
- SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2604.02222)]
**IJCV**
- DeST: A Decoupled Spatio-Temporal Framework for Action Segmentation [[paper](https://link.springer.com/article/10.1007/s11263-026-02797-0)] [[code](https://github.com/lyhisme/DeST)]
**TIP**
- Attack-Augmented Mixing-Contrastive Skeletal Representation Learning [[paper](https://ieeexplore.ieee.org/abstract/document/11372607)] [[code](https://github.com/1xbq1/A2MC)]
**TIFS**
- Bones of Contention: Exploring Query-Efficient Attacks Against Skeleton Recognition Systems [[paper](https://arxiv.org/abs/2501.16843)]
**TMM**
- Ranking-based Self-Supervised Representation Learning for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11353928)]
**TCSVT**
- STAR++: Region-aware Conditional Semantics via Interpretable Side Information for Zero-Shot Skeleton Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11339971)] [[code](https://github.com/cseeyangchen/STAR_pp)]
- Dynamic Prompting Spatial Temporal Actor Transformer for Fine-grained Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11328855)]
- Constant-invariant Information Guided Augmented Spatiotemporal Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11422982)]
**PR**
- RelPosGAR: Hierarchical relative position-aware interaction modeling for weakly supervised skeleton-based group activity recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320326002165)] [[code](https://github.com/li-lindong/RelPosGAR)]
- Frequency-Aware Spatio-Temporal Topology Learning for Skeleton-Based Human Activity Recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320326001093)]
- ST-VA-AR: Learning velocity-aware action representations with mixture of spatiotemporal attention [[paper](https://www.sciencedirect.com/science/article/pii/S0031320326001652)]
**Neurocomputing**
- FMFNet: A Faster Multimodal Fusion Network for action recognition via efficient modality compensation [[paper](https://www.sciencedirect.com/science/article/pii/S0925231226004881)]
**arXiv papers**
- Affinity Contrastive Learning for Skeleton-based Human Activity Understanding [[paper](https://arxiv.org/abs/2601.16694)] [[code](https://github.com/firework8/ACLNet)]
- BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition [[paper](https://arxiv.org/abs/2601.00369)] [[code](https://github.com/VinnyCSY/BHaRNet)]
- SkeFi: Cross-Modal Knowledge Transfer for Wireless Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2601.12432)] [[code](https://github.com/Huang0035/Skefi)]
- E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition [[paper](https://arxiv.org/abs/2603.02477)] [[code](https://github.com/ayodejimb/E2E-GNet)]
- Less is More: Decoder-Free Masked Modeling for Efficient Skeleton Representation Learning [[paper](https://arxiv.org/abs/2603.10648)] [[code](https://github.com/KAIST-VICLab/SLiM)]
- Variational Contrastive Learning for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2601.07666)]
- ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning [[paper](https://arxiv.org/abs/2602.06251)]
- Skarimva: Skeleton-based Action Recognition is a Multi-view Application [[paper](https://arxiv.org/abs/2602.23231)]
- Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models [[paper](https://arxiv.org/abs/2603.05963)]
- Point-Supervised Skeleton-Based Human Action Segmentation [[paper](https://arxiv.org/abs/2603.06201)]
- M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2603.09367)]
- Severe Domain Shift in Skeleton-Based Action Recognition: A Study of Uncertainty Failure in Real-World Gym Environments [[paper](https://arxiv.org/abs/2603.15574)]
- KGS-GCN: Enhancing Sparse Skeleton Sensing via Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Action Recognition [[paper](https://arxiv.org/abs/2603.16943)]
- Universal Skeleton Understanding via Differentiable Rendering and MLLMs [[paper](https://arxiv.org/abs/2603.18003)]
- S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition [[paper](https://arxiv.org/abs/2603.18062)]
- LLM Enhanced Action Recognition via Hierarchical Global-Local Skeleton-Language Model [[paper](https://arxiv.org/abs/2603.27103)]
### 2025
**CVPR**
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Liu_Revealing_Key_Details_to_See_Differences_A_Novel_Prototypical_Perspective_CVPR_2025_paper.pdf)] [[code](https://github.com/firework8/ProtoGCN)]
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? [[paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Xie_Are_Spatial-Temporal_Graph_Convolution_Networks_for_Human_Action_Recognition_Over-Parameterized_CVPR_2025_paper.pdf)] [[code](https://github.com/davelailai/Sparse-ST-GCN)]
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Chen_Neuron_Learning_Context-Aware_Evolving_Representations_for_Zero-Shot_Skeleton_Action_Recognition_CVPR_2025_paper.pdf)] [[code](https://github.com/cseeyangchen/Neuron)]
- Heterogeneous Skeleton-Based Action Representation Learning [[paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Wang_Heterogeneous_Skeleton-Based_Action_Representation_Learning_CVPR_2025_paper.pdf)]
- Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Zhu_Semantic-guided_Cross-Modal_Prompt_Learning_for_Skeleton-based_Zero-shot_Action_Recognition_CVPR_2025_paper.pdf)]
**ICCV**
- Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Zhou_Adaptive_Hyper-Graph_Convolution_Network_for_Skeleton-based_Human_Action_Recognition_with_ICCV_2025_paper.pdf)] [[code](https://github.com/6UOOON9/Hyper-GCN)]
- Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Wu_Frequency-Semantic_Enhanced_Variational_Autoencoder_for_Zero-Shot_Skeleton-based_Action_Recognition_ICCV_2025_paper.pdf)] [[code](https://github.com/wenhanwu95/FS-VAE)]
- Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Do_Bridging_the_Skeleton-Text_Modality_Gap_Diffusion-Powered_Modality_Alignment_for_Zero-shot_ICCV_2025_paper.pdf)] [[code](https://github.com/KAIST-VICLab/TDSM)]
- Bridging Class Imbalance and Partial Labeling via Spectral-Balanced Energy Propagation for Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Wang_Bridging_Class_Imbalance_and_Partial_Labeling_via_Spectral-Balanced_Energy_Propagation_ICCV_2025_paper.pdf)] [[code](https://github.com/ydanwang/SpeLER)]
- Privacy-centric Deep Motion Retargeting for Anonymization of Skeleton-Based Motion Visualization [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Carr_Privacy-centric_Deep_Motion_Retargeting_for_Anonymization_of_Skeleton-Based_Motion_Visualization_ICCV_2025_paper.pdf)] [[code](https://github.com/Thomasc33/Privacy-Retargeting)]
- Hierarchical-aware Orthogonal Disentanglement Framework for Fine-grained Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Chang_Hierarchical-aware_Orthogonal_Disentanglement_Framework_for_Fine-grained_Skeleton-based_Action_Recognition_ICCV_2025_paper.pdf)]
- Towards Efficient General Feature Prediction in Masked Skeleton Modeling [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Sun_Towards_Efficient_General_Feature_Prediction_in_Masked_Skeleton_Modeling_ICCV_2025_paper.pdf)]
- Sequential Keypoint Density Estimator: An Overlooked Baseline of Skeleton-based Video Anomaly Detection [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Delic_Sequential_keypoint_density_estimator_an_overlooked_baseline_of_skeleton-based_video_ICCV_2025_paper.pdf)]
- Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Gokay_Skeleton_Motion_Words_for_Unsupervised_Skeleton-Based_Temporal_Action_Segmentation_ICCV_2025_paper.pdf)]
- DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation [[paper](https://openaccess.thecvf.com/content/ICCV2025/papers/Tian_DuoCLR_Dual-Surrogate_Contrastive_Learning_for_Skeleton-based_Human_Action_Segmentation_ICCV_2025_paper.pdf)]
**NeurIPS**
- Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation [[paper](https://openreview.net/forum?id=wjXKFrUFzA)] [[code](https://github.com/Alchemist0754/Skeleton-Cache)]
- Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition [[paper](https://openreview.net/forum?id=u8SXX5ITE6)] [[code](https://github.com/capableofanything/SKETCH)]
- OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation [[paper](https://openreview.net/forum?id=LWuhOoHpo5)]
**ICLR**
- TASAR: Transfer-based Attack on Skeletal Action Recognition [[paper](https://arxiv.org/pdf/2409.02483)] [[code](https://github.com/qkicen/Skeleton-Robustness-Benchmark)]
**AAAI**
- USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32899)] [[code](https://github.com/wengwanjiang/USDRL)]
- SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32744)] [[code](https://github.com/thearkaprava/SKI-Models)]
- VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32894)]
- Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32201)]
- Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32324)]
- Stitch, Contrast, and Segment: Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/32792)]
**ACM MM**
- Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition [[paper](https://arxiv.org/abs/2507.21977)] [[code](https://github.com/momiji-bit/MMN)]
- Signal-SGN: A Spiking Graph Convolutional Network for Skeleton Action Recognition via Learning Temporal-Frequency Dynamics [[paper](https://dl.acm.org/doi/abs/10.1145/3746027.3755246)] [[code](https://github.com/zhengnaichuan2022/Signal-SGN)]
- Kinematic Enhanced Hypergraph Convolutional Network for Skeleton-based Human Action Recognition with LLM Training Guides [[paper](https://dl.acm.org/doi/abs/10.1145/3746027.3755538)]
- Skeleton Compression and Complementary Enhanced Fusion Under Branch-Stage Supervision for Human Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3746027.3755690)]
**ICCVW**
- Learning Robust Aligned Representations Across Multiple Visual Modalities in Human Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2025W/SAUAFG/papers/Lerch_Learning_Robust_Aligned_Representations_Across_Multiple_Visual_Modalities_in_Human_ICCVW_2025_paper.pdf)]
**BMVC**
- Multimodal Feature Collaboration and Fusion for Fine-grained Action Recognition [[paper](https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_284/paper.pdf)]
**WACV**
- Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition [[paper](https://arxiv.org/abs/2411.05692)] [[code](https://github.com/rayabhisek123/AutoregAd-HGformer)]
**ICIP**
- MFA-Net: Motion Field Adaptive Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11084688)]
- Stable-Invertible Graph Convolutional Networks for Label-Efficient Skeleton-Based Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11084667)]
**ICASSP**
- Auxiliary Tasks Benefit Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10887882)]
- Hybrid Spatial-Frequency Attention Network For Fine-Grained Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10890541)]
- SkeletonMix: A Mixup-Based Data Augmentation Framework for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10888125)]
- Dual Multi-Scale GCN with Deformable Temporal Kernel for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10890725)]
- Joint-Wise Distributed Perception Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10888560)]
- Multi-scale Graph Convolution with Corrective Contrastive Learning for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10890514)]
- Reenvisioning Skeleton-based Action Recognition Through the Lens of NLP [[paper](https://ieeexplore.ieee.org/abstract/document/10888571)]
- PASTD: Progressive Augmentation and Spatiotemporal Decoupling Contrastive Learning for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10890079)]
**IROS**
- Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition [[paper](https://arxiv.org/abs/2503.14960)] [[code](https://github.com/VinnyCSY/BHaRNet)]
- G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2509.07335)] [[code](https://github.com/CyanSea123/G3CN-Gaussian-Topology)]
- MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation [[paper](https://arxiv.org/abs/2508.12948)]
**TPAMI**
- Heatmap Pooling Network for Action Recognition from RGB Videos [[paper](https://ieeexplore.ieee.org/abstract/document/11278750)] [[code](https://github.com/liujf69/HPNet-Action)]
- Foundation Model for Skeleton-Based Human Action Understanding [[paper](https://ieeexplore.ieee.org/abstract/document/11130651)] [[code](https://github.com/wengwanjiang/FoundSkelModel)]
- Hulk: A Universal Knowledge Translator for Human-Centric Tasks [[paper](https://ieeexplore.ieee.org/abstract/document/10930828)] [[code](https://github.com/OpenGVLab/Hulk)]
- Self-Supervised Skeleton Representation Learning via Actionlet Contrast and Reconstruct [[paper](https://ieeexplore.ieee.org/abstract/document/11123705)] [[code](https://github.com/LanglandsLin/ActCLR)]
**IJCV**
- I2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation [[paper](https://link.springer.com/article/10.1007/s11263-025-02415-5)]
**TIP**
- Expressive Keypoints for Skeleton-Based Action Recognition via Progressive Skeleton Evolution [[paper](https://ieeexplore.ieee.org/document/11258079)] [[code](https://github.com/YijieYang23/PSE-GCN)]
- Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment [[paper](https://ieeexplore.ieee.org/abstract/document/11083680)] [[code](https://github.com/kaai520/PGFA)]
- Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation [[paper](https://ieeexplore.ieee.org/abstract/document/11220247)] [[code](https://github.com/HaoyuJi/TRG-Net)]
- Momentum Contrastive Teacher for Semi-Supervised Skeleton Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10820022)]
- Client-Unbiased Skeletal Action Recognizer in Federated Learning [[paper](https://ieeexplore.ieee.org/abstract/document/11079817)]
- Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples [[paper](https://ieeexplore.ieee.org/abstract/document/11235602)]
**TMM**
- Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10891636)] [[code](https://github.com/damnull/lagcn)]
- SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation [[paper](https://arxiv.org/pdf/2504.11749)] [[code](https://github.com/zzysteve/SkeletonX)]
- Multi-View Knowledge Guided Semantic Prototype Learning for Generalized Zero-Shot Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11194256)] [[code](https://github.com/EHZ9NIWI7/AMSF-GZSSAR)]
- Contrastive Feedback Vision-Language for 3D Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10855504)]
- An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10891402)]
- Prompt-Guided Prototype-Aware Commonality and Discrimination Learning for Zero-Shot Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11086379)]
- Action-Responsive Contrastive Network for Fine-Grained Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11147133)]
**TCSVT**
- TDSN-GCN: Transformerify Overall Structure Decaying Static Graph Embedding NAS-guided GCN for Skeleton Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/11176951)] [[code](https://github.com/vvhj/TDSN-GCN)]
- Asymmetric Context-guided Adaptive Alignment Network for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10843295)]
- Unsupervised Feature Enrichment and Fidelity Preservation Learning Framework for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10879058)]
- Robust 2D Skeleton Action Recognition via Decoupling and Distilling 3D Latent Features [[paper](https://ieeexplore.ieee.org/abstract/document/10972084)]
**PR**
- A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320325001815)] [[code](https://github.com/zhshj0110/CSRE)]
- Dual-decoder collaborative learning with multi-hybrid view augmentation for self-supervised 3D action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S003132032501012X)] [[code](https://github.com/Yingfei-Wu/DDC)]
- Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0031320325010039)] [[code](https://github.com/jidongkuang/DVTA)]
- SAM-Net: Semantic-assisted multimodal network for action recognition in RGB-D videos [[paper](https://www.sciencedirect.com/science/article/pii/S0031320325003851)]
- Skeleton-prompt: A cross-dataset transfer learning approach for skeleton action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S003132032500545X)]
- THTFormer: Topology-adaptive hypergraph transformer network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S003132032500785X)]
- Hierarchical kernel decoupling for graph convolution: Enhancing skeleton-based action recognition through structured representation [[paper](https://www.sciencedirect.com/science/article/pii/S0031320325013159)]
- RL-GTN: A reinforced divergence-optimized graph transformer network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320325013445)]
**Neurocomputing**
- A robust two-stage framework for human skeleton action recognition with GAIN and masked autoencoder [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225001055)] [[code](https://github.com/GD1201/A-two-stage-network-for-action-recognition)]
- EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225004539)] [[code](https://github.com/ahmed-nady/Multimodal-Action-Recognition)]
- Dstsa-gcn: Advancing skeleton-based gesture recognition with semantic-aware spatio-temporal topology modeling [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231225007386)] [[code](https://github.com/HuCui2022/DSTSA-GCN_Gesture)]
- High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225017503)] [[code](https://github.com/lizaowo/HPI-GCN)]
- MK-SGN: A spiking graph convolutional network with multimodal fusion and knowledge distillation for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225024683)] [[code](https://github.com/zhengnaichuan2022/MK-SGN)]
- SHoTGCN: Spatial high-order temporal GCN for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225003698)]
- Local and Global Spatial-Temporal Transformer for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225004928)]
- Exploring interaction: Inner-outer spatial–temporal transformer for skeleton-based mutual action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225006794)]
- Skeleton-based action recognition through dual-granularity feature fusion with self-adapting graph convolution and multi-scale temporal convolution [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225009336)]
- A dual-stream GCN-based action recognition framework using trustworthy fusion decision from different skeleton descriptors [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225021472)]
- Disentangled adaptive multi-dimensional dynamic graph convolutional network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225023653)]
- Integrating spatio-temporal modeling of RGB video with multi-stream skeleton representations for advanced human action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225024634)]
- Masked reconstruction model of latent space vector quantization for human skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231225027985)]
**arXiv papers**
- SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2511.22433)] [[code](https://github.com/firework8/SkeletonAgent)]
- Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2505.23012)] [[code](https://github.com/ShanakaRG/STJD-Spatio-Temporal-Joint-Density-Driven-Learning-for-Skeleton-Based-Action-Recognition)]
- UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2508.08944)] [[code](https://github.com/wenhanwu95/FreqMixFormer/tree/main/UniSTFormer)]
- MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition [[paper](https://arxiv.org/abs/2508.14889)] [[code](https://github.com/3Dwe-ai/ms-clr)]
- LSTC-MDA: A Unified Framework for Long-Short Term Temporal Convolution and Mixed Data Augmentation in Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2509.14619)] [[code](https://github.com/xiaobaoxia/LSTC-MDA)]
- DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2511.14179)] [[code](https://github.com/Ixiaohuihuihui/DoGCLR)]
- TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2512.11503)] [[code](https://github.com/ryannus2025-ai/TSkel-Mamba)]
- DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition [[paper](https://arxiv.org/abs/2512.11941)] [[code](https://github.com/Alchemist0754/DynaPURLS)]
- Evolving Skeletons: Motion Dynamics in Action Recognition [[paper](https://arxiv.org/abs/2501.02593)]
- HFGCN: Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2501.11007)]
- HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition [[paper](https://arxiv.org/abs/2502.05869)]
- SNN-Driven Multimodal Human Action Recognition via Event Camera and Skeleton Data Fusion [[paper](https://arxiv.org/abs/2502.13385)]
- CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusion [[paper](https://arxiv.org/abs/2504.21266)]
- Variational Graph Convolutional Neural Networks [[paper](https://arxiv.org/abs/2507.01699)]
- Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection [[paper](https://arxiv.org/abs/2509.11058)]
- Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton [[paper](https://arxiv.org/abs/2511.16860)]
- Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks [[paper](https://arxiv.org/abs/2511.17345)]
- Active Learning for GCN-based Action Recognition [[paper](https://arxiv.org/abs/2511.21625)]
- Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization [[paper](https://arxiv.org/abs/2512.16504)]
- Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition [[paper](https://arxiv.org/abs/2512.21064)]
- Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition [[paper](https://arxiv.org/abs/2512.21916)]
- Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2512.22214)]
### 2024
**CVPR**
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Zhou_BlockGCN_Redefine_Topology_Awareness_for_Skeleton-Based_Action_Recognition_CVPR_2024_paper.pdf)] [[code](https://github.com/ZhouYuxuanYX/BlockGCN)] [🔥] [⭐]
- Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily Living [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Reilly_Just_Add__Pose_Induced_Video_Transformers_for_Understanding_Activities_CVPR_2024_paper.pdf)] [[code](https://github.com/dominickrei/pi-vit)]
- Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Zhu_Part-aware_Unified_Representation_of_Language_and_Skeleton_for_Zero-shot_Action_CVPR_2024_paper.pdf)] [[code](https://github.com/azzh1/PURLS)]
- Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Wang_Skeleton-in-Context_Unified_Skeleton_Sequence_Modeling_with_In-Context_Learning_CVPR_2024_paper.pdf)] [[code](https://github.com/fanglaosi/Skeleton-in-Context)]
- LLMs are Good Action Recognizers [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Qu_LLMs_are_Good_Action_Recognizers_CVPR_2024_paper.pdf)] [🔥]
- MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning [[paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Abdelfattah_MaskCLR_Attention-Guided_Contrastive_Learning_for_Robust_Action_Representation_Learning_CVPR_2024_paper.pdf)]
**ECCV**
- SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/05796.pdf)] [[code](https://github.com/KAIST-VICLab/SkateFormer)] [🔥] [⭐]
- MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/03727.pdf)] [[code](https://github.com/LehongWu/MacDiff)]
- SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/02508.pdf)] [[code](https://github.com/pha123661/SA-DVAE)]
- On the Utility of 3D Hand Poses for Action Recognition [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/01025.pdf)] [[code](https://github.com/s-shamil/HandFormer)]
- Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/07657.pdf)] [[code](https://github.com/mgiant/MP-GCN)]
- VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/10768.pdf)] [[code](https://github.com/xuyankun/VSViG)]
- Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/07145.pdf)] [[code](https://github.com/HaoyuJi/LaSA)]
- Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/03717.pdf)]
- S-JEPA: A Joint Embedding Predictive Architecture for Skeletal Action Recognition [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/04755.pdf)]
- CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/03008.pdf)]
- Towards Physical World Backdoor Attacks against Skeleton Action Recognition [[paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/06445.pdf)]
**NeurIPS**
- CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition [[paper](https://arxiv.org/pdf/2410.07153)] [[code](https://github.com/Necolizer/CHASE)]
- Recovering Complete Actions for Cross-dataset Skeleton Action Recognition [[paper](https://arxiv.org/pdf/2410.23641)] [[code](https://github.com/HanchaoLiu/Recover-and-Resample)]
**AAAI**
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/28440)] [[code](https://github.com/davelailai/DS-GCN)] [🔥]
- SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/28409)] [[code](https://github.com/cong-wu/SCD-Net)]
- Navigating Open Set Scenarios for Skeleton-based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/28247)] [[code](https://github.com/KPeng9510/OS-SAR)]
- Behavioral Recognition of Skeletal Data Based on Targeted Dual Fusion Strategy [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/28517)]
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/28590)]
**ACM MM**
- Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer [[paper](https://arxiv.org/pdf/2407.12322)] [[code](https://github.com/wenhanwu95/FreqMixFormer)]
- Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2407.15706)] [[code](https://github.com/liujf69/MMCL-Action)]
- Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition [[paper](https://arxiv.org/pdf/2404.07487)] [[code](https://github.com/cseeyangchen/STAR)]
**IJCAI**
- Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition [[paper](https://arxiv.org/pdf/2407.12312)] [[code](https://github.com/JHang2020/Shap-Mix)]
**CVPRW**
- Efficient Skeleton-Based Action Recognition for Real-Time Embedded Systems [[paper](https://openaccess.thecvf.com/content/CVPR2024W/MAI/papers/Noor_Efficient_Skeleton-Based_Action_Recognition_for_Real-Time_Embedded_Systems_CVPRW_2024_paper.pdf)]
**ECCVW**
- HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-031-91575-8_2)]
**ICPR**
- Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning [[paper](https://arxiv.org/pdf/2407.01397)] [[code](https://github.com/Sperimental3/CHARON)]
- Spatio-Temporal Domain-Aware Network for Skeleton-Based Action Representation Learning [[paper](https://link.springer.com/chapter/10.1007/978-3-031-78110-0_10)]
- EchoGCN: An Echo Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-031-78354-8_16)]
- Semi-structured Pruning of Graph Convolutional Networks for Skeleton-Based Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-031-78166-7_25)]
- Hybrid Human Action Anomaly Detection Based on Lightweight GNNs and Machine Learning [[paper](https://link.springer.com/chapter/10.1007/978-3-031-78110-0_14)]
**ICIP**
- Hierarchical Vertex-Wise Intensification Graph Convolution for Skeleton-Based Activity Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10647399)]
- Cross-Action Cross-Subject Skeleton Action Recognition Via Simultaneous Action-Subject Learning With Two-Step Feature Removal [[paper](https://ieeexplore.ieee.org/abstract/document/10647253)]
**ICASSP**
- Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision [[paper](https://arxiv.org/pdf/2309.12009.pdf)] [[code](https://github.com/desehuileng0o0/IKEM)]
- Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition [[paper](https://arxiv.org/pdf/2402.02210.pdf)]
- A Novel Contrastive Diffusion Graph Convolutional Network for Few-Shot Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10447668)]
**IROS**
- Skeleton-Based Human Action Recognition with Noisy Labels [[paper](https://arxiv.org/pdf/2403.09975)] [[code](https://github.com/xuyizdby/NoiseEraSAR)]
**ICMEW**
- HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2404.15719.pdf)] [[code](https://github.com/liujf69/ICMEW2024-Track10)]
**TPAMI**
- InfoGCN++: Learning Representation by Predicting the Future for Online Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10694798)] [[code](https://github.com/stnoah1/infogcn2)]
- One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching [[paper](https://ieeexplore.ieee.org/abstract/document/10428035)]
**IJCV**
- View-invariant Skeleton Action Representation Learning via Motion Retargeting [[paper](https://link.springer.com/article/10.1007/s11263-023-01967-8)] [[code](https://github.com/YangDi666/UNIK)]
**TIP**
- DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10478824)] [[code](https://github.com/WoominM/DeGCN_pytorch)] [🔥]
- SelfGCN: Graph Convolution Network With Self-Attention for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10618962)] [[code](https://github.com/SunPengP/SelfGCN)]
- Dynamic Semantic-based Spatial-Temporal Graph Convolution Network for Skeleton-based Human Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10758404)] [[code](https://github.com/davelailai/DS-STGCN)]
- Mutual Information Driven Equivariant Contrastive Learning for 3D Action Representation Learning [[paper](https://ieeexplore.ieee.org/abstract/document/10462918)]
- Multi-View Time-Series Hypergraph Neural Network for Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10517892)]
**TMM**
- Leveraging Enriched Skeleton Representation with Multi-relational Metrics for Few-shot Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10814069)] [[code](https://github.com/jinjinggu00/ESR-MM)]
- Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning [[paper](https://arxiv.org/pdf/2405.20606)]
- Adaptive Pitfall: Exploring the Effectiveness of Adaptation in Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10814651)]
- Localized Linear Temporal Dynamics for Self-supervised Skeleton Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10539295)]
- Hierarchical Aggregated Graph Neural Network for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10598383)]
- GCN-based Multi-modality Fusion Network for Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10814090)]
**TCSVT**
- SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10495051)] [[code](https://github.com/Eezekiel/SiT-MLP)]
- Asynchronous Joint-based Temporal Pooling for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10685538)] [[code](https://github.com/ShanakaRG/AJTP)]
- Glimpse and Zoom: Spatio-Temporal Focused Dynamic Network for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10415064)]
- Multi-scale Structural Graph Convolutional Network for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10464339)]
- Decoupled Knowledge Embedded Graph Convolutional Network for Skeleton-based Human Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10526294)]
- Global and Local Contrastive Learning for Self-supervised Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10551297)]
- Motion-Aware Mask Feature Reconstruction for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10562342)]
- Enhancing Skeleton-Based Action Recognition with Language Descriptions from Pre-trained Large Multimodal Models [[paper](https://ieeexplore.ieee.org/abstract/document/10742343)]
- DSDC-GCN: Decoupled Static-Dynamic Co-occurrence Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10742428)]
**TNNLS**
- Language-Guided 3-D Action Feature Learning Without Ground-Truth Sample Class Label [[paper](https://ieeexplore.ieee.org/abstract/document/10555120)] [[code](https://github.com/tangent-T/W3AMT)]
- GRA: Graph Representation Alignment for Semi-Supervised Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10398229)]
- Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10499829)]
**PR**
- Improving self-supervised action recognition from extremely augmented skeleton sequences [[paper](https://www.sciencedirect.com/science/article/pii/S0031320324000840)] [[code](https://github.com/Levigty/AimCLR-v2)]
- Spatiotemporal Progressive Inward-Outward Aggregation Network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S003132032400013X)]
- Understanding the vulnerability of skeleton-based Human Activity Recognition via black-box attack [[paper](https://www.sciencedirect.com/science/article/pii/S0031320324003157)]
**Neurocomputing**
- A motion-aware and temporal-enhanced Spatial–Temporal Graph Convolutional Network for skeleton-based human action segmentation [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224002534)] [[code](https://github.com/11yxk/openpack)]
- Skeleton-OOD: An end-to-end skeleton-based model for robust out-of-distribution human action detection [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224019295)] [[code](https://github.com/YilliaJing/Skeleton-OOD)]
- Independent Dual Graph Attention Convolutional Network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231224002674)]
- Representation modeling learning with multi-domain decoupling for unsupervised skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224002662)]
- Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224008579)]
- Modeling the skeleton-language uncertainty for 3D action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224011974)]
- Prompt-supervised dynamic attention graph convolutional network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224013948)]
- Language-guided temporal primitive modeling for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231224014073)]
**arXiv papers**
- AutoGCN-Toward Generic Human Activity Recognition With Neural Architecture Search [[paper](https://arxiv.org/abs/2402.01313)] [[code](https://github.com/DeepInMotion/AutoGCN)]
- Graph in Graph Neural Network [[paper](https://arxiv.org/abs/2407.00696)] [[code](https://github.com/wangjs96/Graph-in-Graph-Neural-Network)]
- Language Supervised Human Action Recognition with Salient Fusion: Construction Worker Action Recognition as a Use Case [[paper](https://arxiv.org/abs/2410.01962)] [[code](https://github.com/VCEET/ConstAct_HAR_SFU)]
- GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2403.15212)] [[code](https://github.com/DeepIntoStreams/GCN-DevLSTM)]
- Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition [[paper](https://arxiv.org/abs/2412.14833)] [[code](https://github.com/HaoHuang2003/SFHead)]
- Active Generation Network of Human Skeleton for Action Recognition [[paper](https://arxiv.org/abs/2401.17086)] [[code](https://github.com/imustwangxin/active-generation-network)]
- STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences [[paper](https://arxiv.org/abs/2407.10935)] [[code](https://github.com/TaatiTeam/STARS)]
- Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2409.17951)] [[code](https://github.com/YinxPeng/HA-CM-main)]
- Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2411.12560)]
- Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [[paper](https://arxiv.org/abs/2401.00921)]
- Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2404.02624)]
- Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos [[paper](https://arxiv.org/abs/2404.07645)]
- An Improved Graph Pooling Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2404.16359)]
- Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation [[paper](https://arxiv.org/abs/2410.06353)]
- SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders [[paper](https://arxiv.org/abs/2411.19544)]
### 2023
**CVPR**
- Learning Discriminative Representations for Skeleton Based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Learning_Discriminative_Representations_for_Skeleton_Based_Action_Recognition_CVPR_2023_paper.pdf)] [[code](https://github.com/zhysora/FR-Head)] [🔥] [⭐]
- Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Neural_Koopman_Pooling_Control-Inspired_Temporal_Dynamics_Encoding_for_Skeleton-Based_Action_CVPR_2023_paper.pdf)] [[code](https://github.com/Infinitywxh/Neural_Koopman_pooling)]
- Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Actionlet-Dependent_Contrastive_Learning_for_Unsupervised_Skeleton-Based_Action_Recognition_CVPR_2023_paper.pdf)] [[code](https://github.com/LanglandsLin/ActCLR)] [🔥]
- HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Shah_HaLP_Hallucinating_Latent_Positives_for_Skeleton-Based_Self-Supervised_Learning_of_Actions_CVPR_2023_paper.pdf)] [[code](https://github.com/anshulbshah/HaLP)]
- 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_3Mformer_Multi-Order_Multi-Mode_Transformer_for_Skeletal_Action_Recognition_CVPR_2023_paper.pdf)] [🔥]
- Unified Pose Sequence Modeling [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Foo_Unified_Pose_Sequence_Modeling_CVPR_2023_paper.pdf)]
- Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Hachiuma_Unified_Keypoint-Based_Action_Recognition_Framework_via_Structured_Keypoint_Pooling_CVPR_2023_paper.pdf)]
- Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Sato_Prompt-Guided_Zero-Shot_Anomaly_Action_Recognition_Using_Pretrained_Deep_Skeleton_Features_CVPR_2023_paper.pdf)]
**ICCV**
- Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Hierarchically_Decomposed_Graph_Convolutional_Networks_for_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf)] [[code](https://github.com/Jho-Yonsei/HD-GCN)] [🔥] [⭐]
- Generative Action Description Prompts for Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_Generative_Action_Description_Prompts_for_Skeleton-based_Action_Recognition_ICCV_2023_paper.pdf)] [[code](https://github.com/MartinXM/GAP)] [⭐]
- Masked Motion Predictors are Strong 3D Action Representation Learners [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Mao_Masked_Motion_Predictors_are_Strong_3D_Action_Representation_Learners_ICCV_2023_paper.pdf)] [[code](https://github.com/maoyunyao/MAMP)]
- MotionBERT: A Unified Perspective on Learning Human Motion Representations [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_MotionBERT_A_Unified_Perspective_on_Learning_Human_Motion_Representations_ICCV_2023_paper.pdf)] [[code](https://github.com/Walter0807/MotionBERT)] [🔥] [⭐]
- Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Modeling_the_Relative_Visual_Tempo_for_Self-supervised_Skeleton-based_Action_Recognition_ICCV_2023_paper.pdf)] [[code](https://github.com/Zhuysheng/RVTCLR)]
- Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Hard_No-Box_Adversarial_Attack_on_Skeleton-Based_Human_Action_Recognition_with_ICCV_2023_paper.pdf)] [[code](https://github.com/luyg45/HardNoBoxAttack)]
- LAC - Latent Action Composition for Skeleton-based Action Segmentation [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_LAC_-_Latent_Action_Composition_for_Skeleton-based_Action_Segmentation_ICCV_2023_paper.pdf)] [[code](https://github.com/walker1126/Latent_Action_Composition)]
- Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Leveraging_Spatio-Temporal_Dependency_for_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf)]
- SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_SkeletonMAE_Graph-based_Masked_Autoencoder_for_Skeleton_Sequence_Pre-training_ICCV_2023_paper.pdf)]
- Parallel Attention Interaction Network for Few-Shot Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Parallel_Attention_Interaction_Network_for_Few-Shot_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf)]
- FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_FSAR_Federated_Skeleton-based_Action_Recognition_with_Adaptive_Topology_Structure_and_ICCV_2023_paper.pdf)]
- SkeleTR: Towards Skeleton-based Action Recognition in the Wild [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Duan_SkeleTR_Towards_Skeleton-based_Action_Recognition_in_the_Wild_ICCV_2023_paper.pdf)]
- Cross-Modal Learning with 3D Deformable Attention for Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Cross-Modal_Learning_with_3D_Deformable_Attention_for_Action_Recognition_ICCV_2023_paper.pdf)]
**ICML**
- Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition [[paper](http://proceedings.mlr.press/v202/cai23c/cai23c.pdf)] [[code](https://github.com/OSVAI/Ske2Grid)]
**ICLR**
- Graph Contrastive Learning for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2301.10900.pdf)] [[code](https://github.com/OliverHxh/SkeletonGCL)] [⭐]
- Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations [[paper](https://arxiv.org/pdf/2303.06242.pdf)] [[code](https://github.com/paolomandica/HYSP)]
**AAAI**
- Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25451)] [[code](https://github.com/JHang2020/HiCLR)]
- Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25495)] [[code](https://github.com/YujieOuO/PSTL)]
- Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25439)] [[code](https://github.com/line/Skeleton-Temporal-Action-Localization)]
- Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25127)] [[code](https://github.com/HuiGuanLab/HiCo)]
- Anonymization for Skeleton Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/26754)] [[code](https://github.com/ml-postech/Skeleton-anonymization)]
- Defending Black-box Skeleton-based Human Activity Classifiers [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25352)] [[code](https://github.com/realcrane/Defending-Black-box-Skeleton-based-Human-Activity-Classifiers)]
- Novel Motion Patterns Matter for Practical Skeleton-based Action Recognition [[paper](https://humanperception.github.io/documents/AAAI2023.pdf)]
- Self-Supervised Learning for Multilevel Skeleton-Based Forgery Detection via Temporal-Causal Consistency of Actions [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/25163)]
**ACM MM**
- Skeleton MixFormer: Multivariate Topology Representation for Skeleton-based Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3611900)] [[code](https://github.com/ElricXin/Skeleton-MixFormer)]
- Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3611774)] [[code](https://github.com/JHang2020/PCM3)]
- Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3612449)] [[code](https://github.com/HuiGuanLab/UmURL)]
- Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3611888)] [[code](https://github.com/YujieOuO/SMIE)]
- Self-Relational Graph Convolution Network for Skeleton-Based Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3612280)]
- Skeletal Spatial-Temporal Semantics Guided Homogeneous-Heterogeneous Multimodal Network for Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3612560)]
- Occluded Skeleton-Based Human Action Recognition with Dual Inhibition Training [[paper](https://dl.acm.org/doi/abs/10.1145/3581783.3612170)]
**IJCAI**
- Part Aware Contrastive Learning for Self-Supervised Action Recognition [[paper](https://www.ijcai.org/proceedings/2023/0095.pdf)] [[code](https://github.com/GitHubOfHyl97/SkeAttnCLR)]
- Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization [[paper](https://www.ijcai.org/proceedings/2023/0184.pdf)]
**ICCVW**
- A Lightweight Skeleton-Based 3D-CNN for Real-Time Fall Detection and Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2023W/JRDB/papers/Noor_A_Lightweight_Skeleton-Based_3D-CNN_for_Real-Time_Fall_Detection_and_Action_ICCVW_2023_paper.pdf)]
**BMVC**
- STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2312.03288.pdf)] [[code](https://github.com/maclong01/STEP-CATFormer)]
**WACV**
- Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/WACV2023/papers/Zhu_Adaptive_Local-Component-Aware_Graph_Convolutional_Network_for_One-Shot_Skeleton-Based_Action_Recognition_WACV_2023_paper.pdf)]
- STAR-Transformer: A Spatio-Temporal Cross Attention Transformer for Human Action Recognition [[paper](https://openaccess.thecvf.com/content/WACV2023/html/Ahn_STAR-Transformer_A_Spatio-Temporal_Cross_Attention_Transformer_for_Human_Action_Recognition_WACV_2023_paper.html)]
**ICIP**
- Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/ftp/arxiv/papers/2302/2302.12967.pdf)]
- Part Aware Graph Convolution Network with Temporal Enhancement for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10222714)]
- Skeleton Action Recognition Based on Spatio-Temporal Features [[paper](https://ieeexplore.ieee.org/abstract/document/10223086)]
**ICME**
- DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action Recognition [[paper](https://arxiv.org/pdf/2308.12501.pdf)]
- Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2302.08689)]
**WACVW**
- Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art [[paper](https://openaccess.thecvf.com/content/WACV2024W/CV4Smalls/papers/Hatamimajoumerd_Challenges_in_Video-Based_Infant_Action_Recognition_A_Critical_Examination_of_WACVW_2024_paper.pdf)]
**ICMEW**
- SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition [[paper](https://arxiv.org/pdf/2209.02399.pdf)]
**ICASSP**
- Body Prior Guided Graph Convolutional Neural Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10096690)] [[code](https://github.com/519542630/BPG-GCN)]
**ICIG**
- Multi-semantic fusion model for generalized zero-shot skeleton-based action recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-031-46305-1_6)] [[code](https://github.com/EHZ9NIWI7/MSF-GZSSAR)]
**IROS**
- Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition [[paper](https://arxiv.org/pdf/2307.07469.pdf)] [[code](https://github.com/Necolizer/ISTA-Net)]
**TPAMI**
- Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization [[paper](https://arxiv.org/pdf/2304.08799.pdf)]
**TIP**
- DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10348505/)]
**TMM**
- Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10113233)] [[code](https://github.com/liujf69/TD-GCN-Gesture)] [🔥] [⭐]
- Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions [[paper](https://ieeexplore.ieee.org/abstract/document/10011561)] [[code](https://github.com/KPeng9510/Trans4SOAR)]
- Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks [[paper](https://arxiv.org/pdf/2301.11495.pdf)]
- Learning Representations by Contrastive Spatio-temporal Clustering for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10227565)]
- Skeleton-Based Gesture Recognition With Learnable Paths and Signature Features [[paper](https://ieeexplore.ieee.org/abstract/document/10261439)]
- Skeleton-Based Action Recognition with Select-Assemble-Normalize Graph Convolutional Networks [[paper](https://ieeexplore.ieee.org/abstract/document/10265127)]
- Joints-Centered Spatial-Temporal Features Fused Skeleton Convolution Network for Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10287687)]
**TCSVT**
- Motion Complement and Temporal Multifocusing for Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10015806)] [[code](https://github.com/cong-wu/MCMT-Net)]
- TranSkeleton: Hierarchical Spatial-Temporal Transformer for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10029908)]
**TNNLS**
- Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2302.02316.pdf)]
- Learning Heterogeneous Spatial–Temporal Context for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10081331)]
- Self-Adaptive Graph With Nonlocal Attention Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/10250900)]
**PR**
- Continual spatio-temporal graph convolutional networks [[paper](https://www.sciencedirect.com/science/article/pii/S0031320323002285)] [[code](https://github.com/LukasHedegaard/continual-skeletons)]
- Relation-mining self-attention network for skeleton-based human action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320323001553)] [[code](https://github.com/GedamuA/RSA-Net)]
- SpatioTemporal focus for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320322007105)]
- Multi-grained clip focus for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320323008853)]
**Neurocomputing**
- SPAR: An efficient self-attention network using Switching Partition Strategy for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S092523122301038X)] [[code](https://github.com/Goldfish0106/SPAR-Network)]
- Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231223003211)]
- Spatio-temporal segments attention for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231222013716)]
- STDM-transformer: Space-time dual multi-scale transformer network for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231223010263)]
**arXiv papers**
- TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential [[paper](https://arxiv.org/abs/2304.11631)] [[code](https://github.com/vvhj/TSGCNeXt)]
- Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2308.14024)] [[code](https://github.com/firework8/BRL)]
- Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition [[paper](https://arxiv.org/abs/2307.07791)] [[code](https://github.com/Levigty/ACL)]
- Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments [[paper](https://arxiv.org/abs/2309.12029)] [[code](https://github.com/cyfml/OPSTL)]
- Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2302.02327)] [[code](https://github.com/1xbq1/PSP-Learning)]
- Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN) [[paper](https://arxiv.org/abs/2301.13360)]
- Cross-view Action Recognition via Contrastive View-invariant Representation [[paper](https://arxiv.org/abs/2305.01733)]
- Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2302.13434)]
- Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [[paper](https://arxiv.org/abs/2301.03949)]
- Skeleton-based action analysis for ADHD diagnosis [[paper](https://arxiv.org/abs/2304.09751)]
- Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating [[paper](https://arxiv.org/abs/2307.02730)]
### 2022
**CVPR**
- InfoGCN: Representation Learning for Human Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Chi_InfoGCN_Representation_Learning_for_Human_Skeleton-Based_Action_Recognition_CVPR_2022_paper.pdf)] [[code](https://github.com/stnoah1/infogcn)] [🔥] [⭐]
- Revisiting Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Duan_Revisiting_Skeleton-Based_Action_Recognition_CVPR_2022_paper.pdf)] [[code](https://github.com/kennymckormick/pyskl)] [🔥] [⭐]
**ECCV**
- CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation [[paper](https://arxiv.org/pdf/2208.12448.pdf)] [[code](https://github.com/maoyunyao/CMD)]
- Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning [[paper](https://arxiv.org/pdf/2207.09644.pdf)] [[code](https://github.com/yuxiaochen1103/Hi-TRS)]
- Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition [[paper](https://arxiv.org/pdf/2207.09767.pdf)] [[code](https://github.com/canbaoburen/CoDT)]
- Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning [[paper](https://arxiv.org/pdf/2207.06101.pdf)] [[code](https://github.com/Boeun-Kim/GL-Transformer)]
- IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition [[paper](https://arxiv.org/pdf/2207.12100.pdf)]
- Contrastive Positive Mining for Unsupervised 3D Action Representation Learning [[paper](https://arxiv.org/pdf/2208.03497.pdf)]
- Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition [[paper](https://openreview.net/pdf?id=qIlLNOJsKxJ)]
- Uncertainty-DTW for Time Series and Sequences [[paper](https://arxiv.org/pdf/2211.00005.pdf)]
**AAAI**
- Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/19957)] [[code](https://github.com/Levigty/AimCLR)] [🔥]
- Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/20191)] [[code](https://github.com/hikvision-research/skelact)] [🔥] [⭐]
- Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/19998)]
**ACM MM**
- PYSKL: Towards Good Practices for Skeleton Action Recognition [[paper](https://arxiv.org/pdf/2205.09443.pdf)] [[code](https://github.com/kennymckormick/pyskl)] [🔥] [⭐]
- Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition [[paper](https://arxiv.org/pdf/2209.02986.pdf)] [[code](https://github.com/ideal-idea/SAP)]
- Skeleton-based Action Recognition via Adaptive Cross-Form Learning [[paper](https://arxiv.org/pdf/2206.15085.pdf)] [[code](https://github.com/stoa-xh91/ACFL)]
- Self-Supervised Representation Learning for Skeleton-Based Group Activity Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3503161.3547822)] [[code](https://github.com/xiaochehe/SSL_Skeleton_GAR)]
- Global-Local Cross-View Fisher Discrimination for View-Invariant Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3503161.3548280)]
**CVPRW**
- Bootstrapped Representation Learning for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2022W/L3D-IVU/papers/Moliner_Bootstrapped_Representation_Learning_for_Skeleton-Based_Action_Recognition_CVPRW_2022_paper.pdf)]
**ECCVW**
- Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks [[paper](https://arxiv.org/pdf/2209.09393.pdf)] [[code](https://github.com/kennymckormick/ARAS-Dataset)]
- PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition [[paper](https://arxiv.org/pdf/2208.05775.pdf)] [[code](https://github.com/skelemoa/psumnet)]
- Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns [[paper](https://arxiv.org/pdf/2205.14405.pdf)]
**ACCV**
- Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content/ACCV2022/papers/Gao_Focal_and_Global_Spatial-Temporal_Transformer_for_Skeleton-based_Action_Recognition_ACCV_2022_paper.pdf)]
- Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition [[paper](https://openaccess.thecvf.com/content/ACCV2022/papers/Wang_Temporal-Viewpoint_Transportation_Plan_for_Skeletal_Few-shot_Action_Recognition_ACCV_2022_paper.pdf)]
**WACV**
- Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition [[paper](https://openaccess.thecvf.com/content/WACV2022/papers/Memmesheimer_Skeleton-DML_Deep_Metric_Learning_for_Skeleton-Based_One-Shot_Action_Recognition_WACV_2022_paper.pdf)] [[code](https://github.com/raphaelmemmesheimer/skeleton-dml)]
- Generative Adversarial Graph Convolutional Networks for Human Action Synthesis [[paper](https://openaccess.thecvf.com/content/WACV2022/papers/Degardin_Generative_Adversarial_Graph_Convolutional_Networks_for_Human_Action_Synthesis_WACV_2022_paper.pdf)] [[code](https://github.com/DegardinBruno/Kinetic-GAN)]
**ICPR**
- Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network [[paper](https://arxiv.org/pdf/2207.05493.pdf)]
**TPAMI**
- Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2106.15125.pdf)] [[code](https://gitee.com/yfsong0709/EfficientGCNv1)] [🔥]
- Motif-GCNs With Local and Non-Local Temporal Blocks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9763364)] [[code](https://github.com/wenyh1616/SAMotif-GCN)]
- Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9954217)] [[code](https://github.com/1xbq1/MAC-Learning)]
**IJCV**
- Action2video: Generating Videos of Human 3D Actions [[paper](https://link.springer.com/article/10.1007/s11263-021-01550-z)]
**TIP**
- Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2111.11051.pdf)] [[code](https://github.com/Picasso-Wang/CRRL)]
- Multilevel Spatial–Temporal Excited Graph Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9997556)] [[code](https://github.com/Zhuysheng/ML-STGNet)]
- SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9975251)]
- X-Invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9782720)]
**TMM**
- Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition [[paper](https://arxiv.org/pdf/2110.14994.pdf)]
- Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition [[paper](https://arxiv.org/ftp/arxiv/papers/2202/2202.04075.pdf)]
**TCSVT**
- Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition [[paper](https://arxiv.org/pdf/2208.06174.pdf)] [[code](https://github.com/mgiant/2P-GCN)]
- Zoom Transformer for Skeleton-Based Group Activity Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9845486)] [[code](https://github.com/Kebii/Zoom-Transformer)]
- Motion Guided Attention Learning for Self-Supervised 3D Human Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9841515)]
- Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9931755)]
- View-Normalized and Subject-Independent Skeleton Generation for Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9940286)]
**TNNLS**
- Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition [[paper](https://arxiv.org/pdf/2105.01563.pdf)] [[code](https://github.com/ZhenyueQin/Angular-Skeleton-Encoding)]
**Neurocomputing**
- Forward-reverse adaptive graph convolutional networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231221018920)] [[code](https://github.com/Nanasaki-Ai/FR-AGCN)]
- AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement [[paper](https://arxiv.org/pdf/2208.03444.pdf)]
- Hierarchical graph attention network with pseudo-metapath for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231222007421)]
- Skeleton-based similar action recognition through integrating the salient image feature into a center-connected graph convolutional network [[paper](https://www.sciencedirect.com/science/article/pii/S0925231222009560)]
- PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231222008049)]
**arXiv papers**
- Hypergraph Transformer for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2211.09590)] [[code](https://github.com/ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition)] [⭐]
- DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2210.05895)] [[code](https://github.com/kennymckormick/pyskl)]
- Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2201.02849)] [[code](https://github.com/heleiqiu/STTFormer)]
- Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition [[paper](https://arxiv.org/abs/2207.03065)] [[code](https://github.com/czhaneva/SkeleMixCLR)]
- HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment [[paper](https://arxiv.org/abs/2202.07308)] [[code](https://github.com/Morris88826/HAA4D)]
- Skeleton-based Action Recognition Via Temporal-Channel Aggregation [[paper](https://arxiv.org/abs/2205.15936)]
- A New Spatial Adjacency Matrix of Skeleton Data Based on Self-loop and Adaptive Weights [[paper](https://arxiv.org/abs/2206.14344)]
### 2021
**CVPR**
- 3D Human Action Representation Learning via Cross-View Consistency Pursuit [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_3D_Human_Action_Representation_Learning_via_Cross-View_Consistency_Pursuit_CVPR_2021_paper.pdf)] [[code](https://github.com/LinguoLi/CrosSCLR)] [🔥]
- BASAR:Black-box Attack on Skeletal Action Recognition [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Diao_BASARBlack-Box_Attack_on_Skeletal_Action_Recognition_CVPR_2021_paper.pdf)] [[code](https://github.com/realcrane/BASAR-Black-box-Attack-on-Skeletal-Action-Recognition)]
- Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Understanding_the_Robustness_of_Skeleton-Based_Action_Recognition_Under_Adversarial_Attack_CVPR_2021_paper.pdf)] [[code](https://github.com/realcrane/Understanding-the-Robustness-of-Skeleton-based-Action-Recognition-under-Adversarial-Attack)]
**ICCV**
- Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_Channel-Wise_Topology_Refinement_Graph_Convolution_for_Skeleton-Based_Action_Recognition_ICCV_2021_paper.pdf)] [[code](https://github.com/Uason-Chen/CTR-GCN)] [🔥] [⭐]
- AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Shi_AdaSGN_Adapting_Joint_Number_and_Model_Size_for_Efficient_Skeleton-Based_ICCV_2021_paper.pdf)] [[code](https://github.com/lshiwjx/AdaSGN)]
- Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Skeleton_Cloud_Colorization_for_Unsupervised_3D_Action_Representation_Learning_ICCV_2021_paper.pdf)]
- Self-supervised 3D Skeleton Action Representation Learning with Motion Consistency and Continuity [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Su_Self-Supervised_3D_Skeleton_Action_Representation_Learning_With_Motion_Consistency_and_ICCV_2021_paper.pdf)]
- Geometric Deep Neural Network Using Rigid and Non-Rigid Transformations for Human Action Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Friji_Geometric_Deep_Neural_Network_Using_Rigid_and_Non-Rigid_Transformations_for_ICCV_2021_paper.pdf)]
- GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Nguyen_GeomNet_A_Neural_Network_Based_on_Riemannian_Geometries_of_SPD_ICCV_2021_paper.pdf)]
**NeurIPS**
- Unsupervised Motion Representation Learning with Capsule Autoencoders [[paper](https://proceedings.neurips.cc/paper/2021/file/19ca14e7ea6328a42e0eb13d585e4c22-Paper.pdf)] [[code](https://github.com/ZiweiXU/CapsuleMotion)]
**AAAI**
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16197)] [[code](https://github.com/czhaneva/MST-GCN)] [🔥]
- Spatio-Temporal Difference Descriptor for Skeleton-Based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16210)]
**ACM MM**
- Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2108.04536.pdf)] [[code](https://github.com/tailin1009/DualHead-Network)]
- STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition [[paper](https://dl.acm.org/doi/abs/10.1145/3474085.3475473)] [[code](https://github.com/HanzoZY/STST)]
- Skeleton-Contrastive 3D Action Representation Learning [[paper](https://arxiv.org/pdf/2108.03656.pdf)] [[code](https://github.com/fmthoker/skeleton-contrast)]
- Modeling the Uncertainty for Self-supervised 3D Skeleton Action Representation Learning [[paper](https://dl.acm.org/doi/abs/10.1145/3474085.3475248)]
**CVPRW**
- One-shot action recognition in challenging therapy scenarios [[paper](https://openaccess.thecvf.com/content/CVPR2021W/LLID/papers/Sabater_One-Shot_Action_Recognition_in_Challenging_Therapy_Scenarios_CVPRW_2021_paper.pdf)] [[code](https://github.com/AlbertoSabater/Skeleton-based-One-shot-Action-Recognition)]
**BMVC**
- UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2107.08580.pdf)] [[code](https://github.com/YangDi666/UNIK)]
- Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance [[paper](https://arxiv.org/pdf/2204.10312.pdf)] [[code](https://github.com/IIT-PAVIS/UHAR_Skeletal_Laplacian)]
- LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition [[paper](https://arxiv.org/abs/2111.00823)]
**WACV**
- JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content/WACV2021/papers/Cai_JOLO-GCN_Mining_Joint-Centered_Light-Weight_Information_for_Skeleton-Based_Action_Recognition_WACV_2021_paper.pdf)]
**ICPR**
- Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2112.03328.pdf)]
**ICPRW**
- Spatial Temporal Transformer Network for Skeleton-Based Action Recognition [[paper](https://arxiv.org/pdf/2012.06399.pdf)] [[code](https://github.com/Chiaraplizz/ST-TR)] [🔥] [⭐]
**ICIP**
- Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition [[paper](https://arxiv.org/pdf/2101.11530.pdf)] [[code](https://github.com/skelemoa/synse-zsl)]
**ICME**
- Graph Convolutional Hourglass Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9428355)]
**ICRA**
- Pose Refinement Graph Convolutional Network for Skeleton-basedAction Recognition [[paper](https://arxiv.org/pdf/2010.07367.pdf)] [[code](https://github.com/sj-li/PR-GCN)]
**TPAMI**
- Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction [[paper](https://arxiv.org/pdf/1910.02212.pdf)] [🔥]
- Tensor Representations for Action Recognition [[paper](https://arxiv.org/pdf/2012.14371.pdf)]
**IJCV**
- Quo Vadis, Skeleton Action Recognition? [[paper](https://arxiv.org/pdf/2007.02072.pdf)] [[code](https://skeleton.iiit.ac.in)]
**TIP**
- Extremely Lightweight Skeleton-Based Action Recognition with ShiftGCN++ [[paper](https://ieeexplore.ieee.org/abstract/document/9515708)] [[code](https://github.com/kchengiva/Shift-GCN-plus)]
- Structural Knowledge Distillation for Efficient Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9351789)] [[code](https://github.com/xiaochehe/SKD)]
- Feedback Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9626596)]
- Hypergraph Neural Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9329123)]
**TIFS**
- REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition [[paper](https://arxiv.org/pdf/2105.06711.pdf)]
**TMM**
- Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9623511)] [[code](https://github.com/LZU-SIAT/PCRP)]
- Interaction Relational Network for Mutual Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9319533)] [[code](https://github.com/mauriciolp/inter-rel-net)]
- LAGA-Net: Local-and-Global Attention Network for Skeleton Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9447926)]
- A Multi-Stream Graph Convolutional Networks-Hidden Conditional Random Field Model for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9000721)]
- Multi-Localized Sensitive Autoencoder-Attention-LSTM For Skeleton-based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9392333)]
- Dear-Net: Learning Diversities for Skeleton-Based Early Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9667321)]
- Efficient Spatio-Temporal Contrastive Learning for Skeleton-Based 3-D Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9612062)]
- GA-Net: A Guidance Aware Network for Skeleton-Based Early Activity Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9661424)]
**TCSVT**
- Fuzzy Integral-Based CNN Classifier Fusion for 3D Skeleton Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9177170)] [[code](https://github.com/theavicaster/fuzzy-integral-cnn-fusion-3d-har)]
- A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9597501)] [[code](https://github.com/iesymiao/CD-GCN)]
- Multi-Stream Interaction Networks for Human Action Recognition [[paper](https://ieeexplore.ieee.org/document/9492107)]
- A Cross View Learning Approach for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9496611)]
- Symmetrical Enhanced Fusion Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9319717)]
- Graph2Net: Perceptually-enriched graph learning for skeleton-based action recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9446181)]
**TNNLS**
- Memory Attention Networks for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9378801)] [[code](https://github.com/memory-attention-networks/MANs)] [🔥]
**PR**
- Tripool: Graph triplet pooling for 3D skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320321001084)]
- Action recognition using kinematics posture feature on 3D skeleton joint locations [[paper](https://www.sciencedirect.com/science/article/pii/S0167865521000751)]
- Scene image and human skeleton-based dual-stream human action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0167865521001902)]
- Dyadic relational graph convolutional networks for skeleton-based human interaction recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0031320321001072)]
- Arbitrary-view human action recognition via novel-view action generation [[paper](https://www.sciencedirect.com/science/article/pii/S0031320321002302)]
**Neurocomputing**
- Rethinking the ST-GCNs for 3D skeleton-based human action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231221007153)]
- Attention adjacency matrix based graph convolutional networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231221002101)]
- Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistance [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220317094)]
- Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231221013928)]
- Adaptive multi-view graph convolutional networks for skeleton-based action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220317690)]
- Knowledge embedded GCN for skeleton-based two-person interaction recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220317732)]
- Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220317720)]
**arXiv papers**
- STAR: Sparse Transformer-based Action Recognition [[paper](https://arxiv.org/abs/2107.07089)] [[code](https://github.com/imj2185/STAR)]
- Self-attention based anchor proposal for skeleton-based action recognition [[paper](https://arxiv.org/abs/2112.09413)] [[code](https://github.com/ideal-idea/SAP)]
- Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [[paper](https://arxiv.org/abs/2111.03993)]
- 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na¨ıve [[paper](https://arxiv.org/abs/2112.12668)]
### 2020
**CVPR**
- Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Liu_Disentangling_and_Unifying_Graph_Convolutions_for_Skeleton-Based_Action_Recognition_CVPR_2020_paper.pdf)] [[code](https://github.com/kenziyuliu/ms-g3d)] [🔥] [⭐]
- Skeleton-Based Action Recognition with Shift Graph Convolutional Network [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Cheng_Skeleton-Based_Action_Recognition_With_Shift_Graph_Convolutional_Network_CVPR_2020_paper.pdf)] [[code](https://github.com/kchengiva/Shift-GCN)] [🔥] [⭐]
- Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zhang_Semantics-Guided_Neural_Networks_for_Efficient_Skeleton-Based_Human_Action_Recognition_CVPR_2020_paper.pdf)] [[code](https://github.com/microsoft/SGN)] [🔥] [⭐]
- PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Su_PREDICT__CLUSTER_Unsupervised_Skeleton_Based_Action_Recognition_CVPR_2020_paper.pdf)] [[code](https://github.com/shlizee/Predict-Cluster)] [⭐]
- Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Li_Dynamic_Multiscale_Graph_Neural_Networks_for_3D_Skeleton_Based_Human_CVPR_2020_paper.pdf)] [[code](https://github.com/limaosen0/DMGNN)] [🔥] [⭐]
- Context Aware Graph Convolution for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zhang_Context_Aware_Graph_Convolution_for_Skeleton-Based_Action_Recognition_CVPR_2020_paper.pdf)]
**ECCV**
- Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-030-58586-0_32)] [[code](https://github.com/kchengiva/DecoupleGCN-DropGraph)] [🔥]
- Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement [[paper](https://link.springer.com/chapter/10.1007/978-3-030-58529-7_7)] [[code](https://github.com/NIEQiang001/unsupervised-human-pose)]
- DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-030-58565-5_45)]
- Adversarial Self-supervised Learning for Semi-supervised 3D Action Recognition [[paper](https://link.springer.com/chapter/10.1007/978-3-030-58571-6_3)]
**AAAI**
- Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/5652)] [[code](https://github.com/xiaoiker/GCN-NAS)] [🔥] [⭐]
- Part-Level Graph Convolutional Network for Skeleton-Based Action Recognition [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/6759)]
- Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/6911)]
**ACM MM**
- Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2010.09978.pdf)] [[code](https://gitee.com/yfsong0709/ResGCNv1)] [🔥]
- Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2007.14690.pdf)] [[code](https://github.com/hikvision-research/skelact)] [⭐]
- Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://arxiv.org/pdf/2011.13322.pdf)] [[code](https://github.com/yellowtownhz/STIGCN)]
- MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition [[paper](https://arxiv.org/pdf/2010.05599.pdf)] [[code](https://github.com/LanglandsLin/MS2L)]
- Action2Motion: Conditioned Generation of 3D Human Motions [[paper](https://arxiv.org/pdf/2007.15240.pdf)] [[code](https://github.com/EricGuo5513/action-to-motion)] [⭐]
- Group-Skeleton-Based Human Action Recognition in Complex Events [[paper](https://arxiv.org/ftp/arxiv/papers/2011/2011.13273.pdf)]
- Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2007.15678.pdf)]
**NIPSW**
- Contrastive Self-Supervised Learning for Skeleton Action Recognition [[paper](http://proceedings.mlr.press/v148/gao21a/gao21a.pdf)]
**ACCV**
- Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action-Gesture Recognition [[paper](https://openaccess.thecvf.com/content/ACCV2020/papers/Shi_Decoupled_Spatial-Temporal_Attention_Network_for_Skeleton-Based_Action-Gesture_Recognition_ACCV_2020_paper.pdf)]
**TPAMI**
- Learning Multi-View Interactional Skeleton Graph for Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9234715)] [[code](https://github.com/niais/mv-ignet)]
- Multi-Task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9007695)] [[code](https://github.com/dluvizon/deephar)] [⭐]
**TIP**
- Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks [[paper](https://arxiv.org/pdf/1912.06971.pdf)] [[code](https://github.com/lshiwjx/2s-AGCN)] [🔥] [⭐]
**TMM**
- Hierarchical Soft Quantization for Skeleton-Based Human Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/9076822)]
- Deep Manifold-to-Manifold Transforming Network for Skeleton-Based Action Recognition [[paper](https://ieeexplore.ieee.org/abstract/document/8960323)]
**TCSVT**
- Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition [[paper](https://arxiv.org/pdf/2008.03791.pdf)] [[code](https://github.com/wqk666999/RA-GCNv2)]
**TNNLS**
- Adversarial Attack on Skeleton-Based Human Action Recognition [[paper](https://arxiv.org/pdf/1909.06500.pdf)]
**TOMM**
- A Benchmark Dataset and Comparison Study for Multi-modal Human Action Analytics [[paper](http://39.96.165.147/Pub%20Files/2020/ssj_tomm20.pdf)]
**PR**
- Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network [[paper](https://www.sciencedirect.com/science/article/pii/S0031320320303149)]
**Neurocomputing**
- Exploring a rich spatial–temporal dependent relational model for skeleton-based action recognition by bidirectional LSTM-CNN [[paper](https://www.sciencedirect.com/science/article/pii/S0925231220311760)]
- HDS-SP: A novel descriptor for skeleton-based human action recognition [[paper](https://www.sciencedirect.com/science/article/pii/S0925231219316509)]
### 2019
**CVPR**
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_Two-Stream_Adaptive_Graph_Convolutional_Networks_for_Skeleton-Based_Action_Recognition_CVPR_2019_paper.pdf)] [[code](https://github.com/lshiwjx/2s-AGCN)] [🔥] [⭐]
- Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Actional-Structural_Graph_Convolutional_Networks_for_Skeleton-Based_Action_Recognition_CVPR_2019_paper.pdf)] [[code](https://github.com/limaosen0/AS-GCN)] [🔥] [⭐]
- Skeleton-Based Action Recognition with Directed Graph Neural Networks [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_Skeleton-Based_Action_Recognition_With_Directed_Graph_Neural_Networks_CVPR_2019_paper.pdf)] [[code](https://github.com/kenziyuliu/DGNN-PyTorch)] [🔥] [⭐]
- Bayesian Hierarchical Dynamic Model for Human Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Bayesian_Hierarchical_Dynamic_Model_for_Human_Action_Recognition_CVPR_2019_paper.pdf)] [[code](https://github.com/rort1989/HDM)]
- An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Si_An_Attention_Enhanced_Graph_Convolutional_LSTM_Network_for_Skeleton-Based_Action_CVPR_2019_paper.pdf)] [🔥]
**ICCV**
- Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition [[paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhao_Bayesian_Graph_Convolution_LSTM_for_Skeleton_Based