Soojie Kim
GET IN TOUCH
Soojie Kim
Awesome Skeleton-based Action Recognition
Date: 2026, Apr 24
Last update: 2026-04-26 08:31:56 UTC
| Index | Title | Venu | Year | Keyword | Paper | Code |
|---|---|---|---|---|---|---|
| 1 | SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition | CVPR | 2026 | zero-shot action recognition | Paper | Code |
| 2 | Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition | CVPRF | 2026 | zero-shot action recognition | Paper | Code |
| 3 | SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition | ICPR | 2026 | zero-shot action recognition | Paper | - |
| 4 | STAR++: Region-aware Conditional Semantics via Interpretable Side Information for Zero-Shot Skeleton Action Recognition | TCSVT | 2026 | zero-shot action recognition | Paper | Code |
| 5 | DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition | TPAMI | 2026 | zero-shot action recognition | Paper | Code |
| 6 | Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation | AAAI | 2026 | few-shot action recognition | Paper | Code |
| 7 | Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition | CVPR | 2025 | zero-shot action recognition | Paper | Code |
| 8 | Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition | CVPR | 2025 | zero-shot action recognition | Paper | - |
| 9 | Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition | ICCV | 2025 | zero-shot action recognition | Paper | Code |
| 10 | Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition | ICCV | 2025 | zero-shot action recognition | Paper | Code |
| 11 | Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation | NeurIPS | 2025 | zero-shot action recognition | Paper | Code |
| 12 | Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment | TIP | 2025 | zero-shot action recognition | Paper | Code |
| 13 | Multi-View Knowledge Guided Semantic Prototype Learning for Generalized Zero-Shot Action Recognition | TMM | 2025 | zero-shot action recognition | Paper | Code |
| 14 | An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition | TMM | 2025 | zero-shot action recognition | Paper | - |
| 15 | Prompt-Guided Prototype-Aware Commonality and Discrimination Learning for Zero-Shot Skeleton-Based Action Recognition | TMM | 2025 | zero-shot action recognition | Paper | - |
| 16 | Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment | PR | 2025 | zero-shot action recognition | Paper | Code |
| 17 | MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation | IROS | 2025 | semantic-aware action recognition | Paper | - |
| 18 | SAM-Net: Semantic-assisted multimodal network for action recognition in RGB-D videos | PR | 2025 | semantic-aware action recognition | Paper | - |
| 19 | Dstsa-gcn: Advancing skeleton-based gesture recognition with semantic-aware spatio-temporal topology modeling | Neurocomputing | 2025 | semantic-aware action recognition | Paper | Code |
| 20 | Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection | arXiv | 2025 | semantic-aware action recognition | Paper | - |
| 21 | Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition | TMM | 2025 | gcn-based action recognition | Paper | Code |
| 22 | Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition | CVPR | 2024 | zero-shot action recognition | Paper | Code |
| 23 | SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders | ECCV | 2024 | zero-shot action recognition | Paper | Code |
| 24 | Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition | ACM MM | 2024 | zero-shot action recognition | Paper | Code |
| 25 | CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner | ECCV | 2024 | one-shot action recognition | Paper | Code |
| 26 | One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching | TPAMI | 2024 | one-shot action recognition | Paper | - |
| 27 | A Novel Contrastive Diffusion Graph Convolutional Network for Few-Shot Skeleton-Based Action Recognition | ICASSP | 2024 | few-shot action recognition | Paper | - |
| 28 | Leveraging Enriched Skeleton Representation with Multi-relational Metrics for Few-shot Action Recognition | TMM | 2024 | few-shot action recognition | Paper | Code |
| 29 | Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition | AAAI | 2024 | semantic-aware action recognition | Paper | Code |
| 30 | Dynamic Semantic-based Spatial-Temporal Graph Convolution Network for Skeleton-based Human Action Recognition | TIP | 2024 | semantic-aware action recognition | Paper | Code |
| 31 | BlockGCN: Redefining Topology Awareness for Skeleton-Based Action Recognition | CVPR | 2024 | gcn-based action recognition | Paper | Code |
| 32 | DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition | TIP | 2024 | gcn-based action recognition | Paper | Code |
| 33 | SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition | ECCV | 2024 | transformer-based action recognition | Paper | Code |
| 34 | Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer | ACM MM | 2024 | transformer-based action recognition | Paper | Code |
| 35 | LLMs are Good Action Recognizers | CVPR | 2024 | action recognition | Paper | - |
| 36 | Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features | CVPR | 2023 | zero-shot action recognition | Paper | - |
| 37 | Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization | ACM MM | 2023 | zero-shot action recognition | Paper | Code |
| 38 | Multi-semantic fusion model for generalized zero-shot skeleton-based action recognition | ICIG | 2023 | zero-shot action recognition | Paper | Code |
| 39 | Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition | WACV | 2023 | one-shot action recognition | Paper | - |
| 40 | Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions | TMM | 2023 | one-shot action recognition | Paper | Code |
| 41 | Parallel Attention Interaction Network for Few-Shot Skeleton-based Action Recognition | ICCV | 2023 | few-shot action recognition | Paper | Code |
| 42 | Skeletal Spatial-Temporal Semantics Guided Homogeneous-Heterogeneous Multimodal Network for Action Recognition | ACM MM | 2023 | semantic-aware action recognition | Paper | - |
| 43 | Generative Action Description Prompts for Skeleton-based Action Recognition | ICCV | 2023 | semantic-aware action recognition | Paper | Code |
| 44 | Temporal Decoupling Graph Convolutional Network for Skeleton-Based Gesture Recognition | TMM | 2023 | gcn-based action recognition | Paper | Code |
| 45 | Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition | ICCV | 2023 | gcn-based action recognition | Paper | Code |
| 46 | TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential | arXiv | 2023 | gcn-based action recognition | Paper | Code |
| 47 | STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition | WACV | 2023 | transformer-based action recognition | Paper | - |
| 48 | TemPose: a new skeleton-based transformer model designed for fine-grained motion recognition in badminton | CVPR | 2023 | transformer-based action recognition | Paper | - |
| 49 | 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition | CVPR | 2023 | transformer-based action recognition | Paper | - |
| 50 | Learning Discriminative Representations for Skeleton Based Action Recognition | CVPR | 2023 | action recognition | Paper | Code |
| 51 | Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition | CVPR | 2023 | action recognition | Paper | Code |
| 52 | MotionBERT: A Unified Perspective on Learning Human Motion Representations | ICCV | 2023 | action recognition | Paper | Code |
| 53 | Graph Contrastive Learning for Skeleton-based Action Recognition | ICLR | 2023 | action recognition | Paper | Code |
| 54 | Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition | WACV | 2022 | one-shot action recognition | Paper | Code |
| 55 | One-shot action recognition in challenging therapy scenarios | CVPRW | 2022 | one-shot action recognition | Paper | Code |
| 56 | Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition | ECCV | 2022 | few-shot action recognition | Paper | Code |
| 57 | Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition | ACCV | 2022 | few-shot action recognition | Paper | - |
| 58 | SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition | TIP | 2022 | few-shot action recognition | Paper | - |
| 59 | HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment | arXiv | 2022 | few-shot action recognition | Paper | Code |
| 60 | A spatial attentive and temporal dilated (SATD) GCN for skeleton-based action recognition | CAAI IT | 2022 | gcn-based action recognition | Paper | - |
| 61 | Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition | TPAMI | 2022 | gcn-based action recognition | Paper | Code |
| 62 | Skeleton-Based ST-GCN for Human Action Recognition With Extended Skeleton Graph and Partitioning Strategy | IEEE Access | 2022 | gcn-based action recognition | Paper | - |
| 63 | PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition | ECCV | 2022 | gcn-based action recognition | Paper | Code |
| 64 | InfoGCN: Representation Learning for Human Skeleton-based Action Recognition | CVPR | 2022 | gcn-based action recognition | Paper | Code |
| 65 | DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition | arXiv | 2022 | gcn-based action recognition | Paper | Code |
| 66 | Revisiting Skeleton-based Action Recognition | CVPR | 2022 | gcn-based action recognition | Paper | Code |
| 67 | Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition | arXiv | 2022 | transformer-based action recognition | Paper | Code |
| 68 | Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning | ECCV | 2022 | transformer-based action recognition | Paper | Code |
| 69 | Hypergraph Transformer for Skeleton-based Action Recognition | arXiv | 2022 | transformer-based action recognition | Paper | Code |
| 70 | Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition | AAAI | 2022 | action recognition | Paper | Code |
| 71 | Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition | AAAI | 2022 | action recognition | Paper | Code |
| 72 | PYSKL: Towards Good Practices for Skeleton Action Recognition | ACM MM | 2022 | action recognition | Paper | Code |
| 73 | SynSE - Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition | ICIP | 2021 | zero-shot action recognition | Paper | Code |
| 74 | 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve | arXiv | 2021 | few-shot action recognition | Paper | - |
| 75 | Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition | arXiv | 2021 | semantic-aware action recognition | Paper | - |
| 76 | Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction | TPAMI | 2021 | gcn-based action recognition | Paper | - |
| 77 | Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data | ICCV | 2021 | gcn-based action recognition | Paper | - |
| 78 | Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition | ICCV | 2021 | gcn-based action recognition | Paper | Code |
| 79 | Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition | AAAI | 2021 | gcn-based action recognition | Paper | Code |
| 80 | STAR: Sparse Transformer-based Action Recognition | arXiv | 2021 | transformer-based action recognition | Paper | Code |
| 81 | Spatial temporal transformer network for skeleton-based action recognition | ICPR | 2021 | transformer-based action recognition | Paper | Code |
| 82 | STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition | ACM MM | 2021 | transformer-based action recognition | Paper | Code |
| 83 | IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition | arXiv | 2021 | transformer-based action recognition | Paper | - |
| 84 | 3D Human Action Representation Learning via Cross-View Consistency Pursuit | CVPR | 2021 | action recognition | Paper | Code |
| 85 | Memory Attention Networks for Skeleton-Based Action Recognition | TNNLS | 2021 | action recognition | Paper | Code |
| 86 | ActionCLIP: A New Paradigm for Video Action Recognition | arXiv | 2021 | action recognition | Paper | Code |
| 87 | Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition | CVPR | 2020 | semantic-aware action recognition | Paper | Code |
| 88 | Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition | ECCV | 2020 | gcn-based action recognition | Paper | Code |
| 89 | Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching | AAAI | 2020 | gcn-based action recognition | Paper | Code |
| 90 | Skeleton-Based Action Recognition with Shift Graph Convolutional Network | CVPR | 2020 | gcn-based action recognition | Paper | Code |
| 91 | Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition | CVPR | 2020 | gcn-based action recognition | Paper | Code |
| 92 | Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition | ACM MM | 2020 | gcn-based action recognition | Paper | Code |
| 93 | Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition | ACM MM | 2020 | gcn-based action recognition | Paper | Code |
| 94 | Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks | TIP | 2020 | gcn-based action recognition | Paper | Code |
| 95 | Self-Attention Network for Skeleton-based Human Action Recognition | WACV | 2020 | transformer-based action recognition | Paper | - |
| 96 | Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action-Gesture Recognition | ACCV | 2020 | transformer-based action recognition | Paper | Code |
| 97 | PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition | CVPR | 2020 | action recognition | Paper | Code |
| 98 | Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction | CVPR | 2020 | action recognition | Paper | Code |
| 99 | Action2Motion: Conditioned Generation of 3D Human Motions | ACM MM | 2020 | action recognition | Paper | Code |
| 100 | Multi-Task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition | TPAMI | 2020 | action recognition | Paper | Code |
| 101 | Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition | CVPR | 2019 | gcn-based action recognition | Paper | Code |
| 102 | Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition | CVPR | 2019 | gcn-based action recognition | Paper | Code |
| 103 | Skeleton-Based Action Recognition with Directed Graph Neural Networks | CVPR | 2019 | gcn-based action recognition | Paper | Code |
| 104 | An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition | CVPR | 2019 | gcn-based action recognition | Paper | - |
| 105 | NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding | TPAMI | 2019 | action recognition | Paper | Code |
| 106 | View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition | TPAMI | 2019 | action recognition | Paper | Code |
| 107 | Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition | AAAI | 2018 | gcn-based action recognition | Paper | Code |
| 108 | Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning | ECCV | 2018 | gcn-based action recognition | Paper | - |
| 109 | Independently Recurrent Neural Network (IndRNN): Building a Longer and Deeper RNN | CVPR | 2018 | action recognition | Paper | Code |
| 110 | 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning | CVPR | 2018 | action recognition | Paper | Code |
| 111 | Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition | CVPR | 2018 | action recognition | Paper | - |
| 112 | Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation | IJCAI | 2018 | action recognition | Paper | Code |
| 113 | Global Context-Aware Attention LSTM Networks for 3D Action Recognition | CVPR | 2017 | action recognition | Paper | - |
| 114 | A New Representation of Skeleton Sequences for 3D Action Recognition | CVPR | 2017 | action recognition | Paper | - |
| 115 | View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data | ICCV | 2017 | action recognition | Paper | Code |
| 116 | An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data | AAAI | 2017 | action recognition | Paper | - |
| 117 | Interpretable 3D Human Action Analysis with Temporal Convolutional Networks | CVPRW | 2017 | action recognition | Paper | Code |
| 118 | Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks | TIP | 2017 | action recognition | Paper | - |
| 119 | Enhanced skeleton visualization for view invariant human action recognition | PR | 2017 | action recognition | Paper | - |
| 120 | NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis | CVPR | 2016 | action recognition | Paper | Code |
| 121 | Temporal segment networks: Towards good practices for deep action recognition | ECCV | 2016 | action recognition | Paper | Code |
| 122 | Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition | ECCV | 2016 | action recognition | Paper | - |
| 123 | Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks | AAAI | 2016 | action recognition | Paper | - |
| 124 | Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition | CVPR | 2015 | action recognition | Paper | - |
| 125 | Jointly learning heterogeneous features for RGB-D activity recognition | CVPR | 2015 | action recognition | Paper | - |
| 126 | Learning Spatiotemporal Features with 3D Convolutional Networks | ICCV | 2015 | action recognition | Paper | Code |
| 127 | Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group | CVPR | 2014 | action recognition | Paper | - |
| 128 | Two-Stream Convolutional Networks for Action Recognition in Videos | NeurIPS | 2014 | action recognition | Paper | - |