Awesome
<!-- [![GitHub Contributors](https://img.shields.io/github/contributors/Kali-Hac/Awesome-Skeleton-Based-Models?color=green&style=plastic)](https://github.com/Kali-Hac/Awesome-Skeleton-Based-Models/network/members) -->Awesome-Skeleton-Based-Models <!-- omit in toc -->
We collect existing skeleton-based models (369+ Papers & Codes) published in prominent conferences (CVPR, ICCV, ECCV, AAAI, IJCAI, ACMMM, ICLR, ICML, NeurIPS, etc) and journals (TPAMI, IJCV, TIP, TMM, TNNLS, PMLR, etc).
TODO <!-- omit in toc -->
- Paper List
- Skeleton-Based Action Recognition
- 3D Pose Estimation
- Skeleton-Based Person Re-Identification (New!)
- Skeleton-Based Gesture Recognition
- Skeleton-Based Gait Recognition
- Others (Skeleton-Based Motion Prediction, Interaction Recognition, etc)
Contents <!-- omit in toc -->
Skeleton-Based Action Recognition (2013-2022)
70 Datasets
Overview of 70 available datasets for action recognition and their statistics, provided by the paper of (TPAMI 2022) [arxiv] (Human Action Recognition from Various Data Modalities: A Review).
S: Skeleton, D: Depth, IR: Infrared, PC: Point Cloud, ES: Event Stream, Au: Audio, Ac: Acceleration, Gyr: Gyroscope, EMG: Electromyography. Bold shows the most-frequently used datasets in the literature.
<!-- ![datasets](./AR-datasets.jpg) -->
# Id | Dataset | Year | Modality | # Class | # Subject | # Sample | # View |
---|---|---|---|---|---|---|---|
1 | KTH | 2004 | RGB | 6 | 25 | 2,391 | 1 |
2 | Weizmann | 2005 | RGB | 10 | 9 | 90 | 1 |
3 | IXMAS | 2006 | RGB | 11 | 10 | 330 | 5 |
4 | HDM05 | 2007 | RGB,S | 130 | 5 | 2,337 | 1 |
5 | Hollywood | 2008 | RGB | 8 | — | 430 | — |
6 | Hollywood2 | 2009 | RGB | 12 | — | 3,669 | — |
7 | MSR-Action3D | 2010 | S,D | 20 | 10 | 567 | 1 |
8 | Olympic | 2010 | RGB | 16 | — | 783 | — |
9 | CAD-60 | 2011 | RGB,S,D | 12 | 4 | 60 | — |
10 | HMDB51 | 2011 | RGB | 51 | — | 6,766 | — |
11 | RGB-HuDaAct | 2011 | RGB,D | 13 | 30 | 1,189 | 1 |
12 | ACT4^{2} | 2012 | RGB,D | 14 | 24 | 6,844 | 4 |
13 | DHA | 2012 | RGB,D | 17 | 21 | 357 | 1 |
14 | MSRDailyActivity3D | 2012 | RGB,S,D | 16 | 10 | 320 | 1 |
15 | UCF101 | 2012 | RGB | 101 | — | 13,320 | — |
16 | UTKinect | 2012 | RGB,S,D | 10 | 10 | 200 | 1 |
17 | Berkeley MHAD | 2013 | RGB,S,D,Au,Ac | 12 | 12 | 660 | 4 |
18 | CAD-120 | 2013 | RGB,S,D | 10 | 4 | 120 | — |
19 | IAS-lab | 2013 | RGB,S,D,PC | 15 | 12 | 540 | 1 |
20 | J-HMDB | 2013 | RGB,S | 21 | — | 31,838 | — |
21 | MSRAction-Pair | 2013 | RGB,S,D | 12 | 10 | 360 | 1 |
22 | UCFKinect | 2013 | S | 16 | 16 | 1,280 | 1 |
23 | Multi-View TJU | 2014 | RGB,S,D | 20 | 22 | 7,040 | 2 |
24 | Northwestern-UCLA | 2014 | RGB,S,D | 10 | 10 | 1,475 | 3 |
25 | Sports-1M | 2014 | RGB | 487 | — | $1,113,158$ | — |
26 | UPCV | 2014 | S | 10 | 20 | 400 | 1 |
27 | UWA3D Multiview | 2014 | RGB,S,D | 30 | 10 | ~900 | 4 |
28 | ActivityNet | 2015 | RGB | 203 | — | 27,801 | — |
29 | SYSU 3D HOI | 2015 | RGB,S,D | 12 | 40 | 480 | 1 |
30 | THUMOS Challenge 15 | 2015 | RGB | 101 | — | 24,017 | — |
31 | TJU | 2015 | RGB,S,D | 15 | 20 | 1,200 | 1 |
32 | UTD-MHAD | 2015 | RGB,S,D,Ac,Gyr | 27 | 8 | 861 | 1 |
33 | UWA3D Multiview II | 2015 | RGB,S,D | 30 | 10 | 1,075 | 4 |
34 | M^{2}I | 2015 | RGB,S,D | 22 | 22 | ~1800 | 2 |
35 | Charades | 2016 | RGB | 157 | 267 | 9,848 | — |
36 | InfAR | 2016 | IR | 12 | 40 | 600 | 2 |
37 | NTU RGB+D | 2016 | RGB,S,D,IR | 60 | 40 | 56,880 | 80 |
38 | YouTube-8M | 2016 | RGB | 4,800 | — | 8,264,650 | — |
39 | AVA | 2017 | RGB | 80 | — | 437 | — |
40 | DvsGesture | 2017 | ES | 17 | 29 | — | — |
41 | FCVID | 2017 | RGB | 239 | — | 91,233 | — |
42 | Kinetics-400 | 2017 | RGB | 400 | — | 306,245 | — |
43 | NEU-UB | 2017 | RGB,D | 6 | 20 | 600 | — |
44 | PKU-MMD | 2017 | RGB,S,D,IR | 51 | 66 | 1,076 | 3 |
45 | Something-Something-v1 | 2017 | RGB | 174 | — | 108,499 | — |
46 | UniMiB SHAR | 2017 | Ac | 17 | 30 | 11,771 | — |
47 | EPIC-KITCHENS-55 | 2018 | RGB,Au | — | 32 | 39,594 | Egocentric |
48 | Kinetics-600 | 2018 | RGB | 600 | — | 495,547 | — |
49 | RGB-D Varying-view | 2018 | RGB,S,D | 40 | 118 | 25,600 | 8+1(360$^{\circ}$) |
50 | DHP19 | 2019 | ES,S | 33 | 17 | — | 4 |
51 | Drive&Act | 2019 | RGB,S,D,IR | 83 | 15 | — | 6 |
52 | Hemangomez et al. | 2019 | Radar | 8 | 11 | 1,056 | — |
53 | Kinetics-700 | 2019 | RGB | 700 | — | 650,317 | — |
54 | Kitchen20 | 2019 | Au | 20 | — | 800 | — |
55 | MMAct | 2019 | RGB,S,Ac,Gyr,etc. | 37 | 20 | 36,764 | 4+Egocentric |
56 | Moments in Time | 2019 | RGB | 339 | — | ~1,000,000 | — |
57 | Wang et al. | 2019 | WiFi CSI | 6 | 1 | 1,394 | — |
58 | NTU RGB+D 120 | 2019 | RGB,S,D,IR | 120 | 106 | 114,480 | 155 |
59 | ETRI-Activity3D | 2020 | RGB,S,D | 55 | 100 | 112,620 | — |
60 | EV-Action | 2020 | RGB,S,D,EMG | 20 | 70 | 7,000 | 9 |
61 | IKEA ASM | 2020 | RGB,S,D | 33 | 48 | 16,764 | 3 |
62 | RareAct | 2020 | RGB | 122 | — | 905 | — |
63 | BABEL | 2021 | Mocap | 252 | — | 13,220 | — |
64 | HAA500 | 2021 | RGB | 500 | — | 10,000 | — |
65 | HOMAGE | 2021 | RGB,IR,Ac,Gyr,etc. | 75 | 27 | 1,752 | 2~5 |
66 | MultiSports | 2021 | RGB | 66 | — | 37,701 | — |
67 | UAV-Human | 2021 | RGB,S,D,IR,etc. | 155 | 119 | 67,428 | — |
68 | Ego4D | 2022 | RGB,Au,Ac,etc. | — | 923 | — | Egocentric |
69 | EPIC-KICHENS-100 | 2022 | RGB,Au,Ac | — | 45 | 89,979 | Egocentric |
70 | JRDB-Act | 2022 | RGB,PC | 26 | — | 3,625 | 360$^{\circ}$ |
Survey Papers
-
Human Action Recognition and Prediction: A Survey Recognition Algorithms (IJCV 2022) [paper]
-
Human Action Recognition from Various Data Modalities: A Review (TPAMI 2022) [arxiv]
-
A Comparative Review of Recent Kinect-based Action Recognition Algorithms (TIP 2019) [arxiv]
2022
-
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition (TPAMI 2022) [paper] [Github] (Not uploaded) [Gitee]
-
[Sym-GNN] Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction (TPAMI 2022) [paper] [Github] (Not uploaded)
-
[X-CAR] X-Invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition (TIP 2022) [paper]
-
[FGCN] Feedback Graph Convolutional Network for Skeleton-Based Action Recognition (TIP 2022) [paper]
-
[Multi-LiSAAL] Multi-Localized Sensitive Autoencoder-Attention-LSTM For Skeleton-based Action Recognition (TMM 2022) [paper]
-
[LAGA-Net] LAGA-Net: Local-and-Global Attention Network for Skeleton Based Action Recognition (TMM 2022) [paper]
-
[CIASA] Adversarial Attack on Skeleton-Based Human Action Recognition (TNNLS 2022) [paper]
-
[MTT] MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition (IEEE Signal Process. Lett. 2022) [paper]
-
[Graph2Net] Graph2Net: Perceptually-Enriched Graph Learning for Skeleton-Based Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2022) [paper] [Github]
-
A Cross View Learning Approach for Skeleton-Based Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2022) [paper]
-
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition (ACM Trans. Multim. Comput. Commun. Appl. 2022) [paper] [Github]
-
Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition (ACM Trans. Multim. Comput. Commun. Appl. 2022) [paper]
-
[SparseShift-GCN] SparseShift-GCN: High precision skeleton-based action recognition (Pattern Recognit. Lett. 2022) [paper]
-
[FR-AGCN] Forward-reverse adaptive graph convolutional networks for skeleton-based action recognition (Neurocomputing 2022) [paper] [Github]
-
[ED-GCN] Enhanced discriminative graph convolutional network with adaptive temporal modelling for skeleton-based action recognition (Comput. Vis. Image Underst. 2022) [paper]
2021
-
Quo Vadis, Skeleton Action Recognition ? (IJCV 2021) [paper] [Github]
-
[CTR-GCN] Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition (ICCV 2021) [paper] [Github]
-
Spatio-Temporal Difference Descriptor for Skeleton-Based Action Recognition (AAAI 2021) [paper]
-
[AdaSGN] AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition (ICCV 2021) [paper] [Github]
-
Self-supervised 3D Skeleton Action Representation Learning with Motion Consistency and Continuity (ICCV 2021) [paper]
-
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning (ICCV 2021) [paper]
-
3D Human Action Representation Learning via Cross-View Consistency Pursuit (CVPR 2021) [arxiv][Github]
-
[MST-GCN] Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021) [paper] [Github]
-
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition (ACMMM 2021) [paper] [Github] (Not uploaded)
-
Modeling the Uncertainty for Self-supervised 3D Skeleton Action Representation Learning (ACMMM 2021) [paper]
-
Skeleton-Contrastive 3D Action Representation Learning (ACMMM 2021) [paper] [Github] (Not uploaded)
-
[STST] STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition (ACMMM 2021) [paper] [Github] (Not uploaded)
-
[CP-STN] Spatial Temporal Enhanced Contrastive and Pretext Learning for Skeleton-based Action Representation (PMLR 2021) [paper]
-
Tripool: Graph triplet pooling for 3D skeleton-based action recognition (Pattern Recognit. 2021) [paper]
-
Structural Knowledge Distillation for Efficient Skeleton-Based Action Recognition (TIP 2021) [paper] [Github]
-
[ShiftGCN++] Extremely Lightweight Skeleton-Based Action Recognition With ShiftGCN++ (TIP 2021) [paper] [Github]
-
[Hyper-GNN] Hypergraph Neural Network for Skeleton-Based Action Recognition (TIP 2021) [paper]
-
[GCN-HCRF] A Multi-Stream Graph Convolutional Networks-Hidden Conditional Random Field Model for Skeleton-Based Action Recognition (TMM 2021) [paper]
-
Hierarchical Soft Quantization for Skeleton-Based Human Action Recognition (TMM 2021) [paper]
-
Pose Refinement Graph Convolutional Network for Skeleton-Based Action Recognition ({IEEE} Robotics Autom. Lett. 2021) [paper] [Github]
-
[FDGCN] Skeleton-Based Action Recognition With Focusing-Diffusion Graph Convolutional Networks (IEEE Signal Process. Lett. 2021) [paper]
-
[ST-GDN] Spatial Temporal Graph Deconvolutional Network for Skeleton-Based Human Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2021) [paper]
-
Fuzzy Integral-Based {CNN} Classifier Fusion for 3D Skeleton Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2021) [paper] [Github]
-
[SEFN] Symmetrical Enhanced Fusion Network for Skeleton-Based Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2021) [paper]
-
[RA-GCN] Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition (IEEE Trans. Circuits Syst. Video Technol. 2021) [paper] [Github]
-
Dual-Stream Structured Graph Convolution Network for Skeleton-Based Action Recognition (ACM Trans. Multim. Comput. Commun. Appl. 2021) [paper]
-
Action recognition using kinematics posture feature on 3D skeleton joint locations (Pattern Recognit. Lett. 2021) [paper]
-
Scene image and human skeleton-based dual-stream human action recognition (Pattern Recognit. Lett. 2021) [paper]
-
Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistance (Neurocomputing 2021) [paper]
-
[VE-GCN] Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition (Neurocomputing 2021) [paper]
-
[AMV-GCNs] Adaptive multi-view graph convolutional networks for skeleton-based action recognition (Neurocomputing 2021) [paper]
-
Rethinking the ST-GCNs for 3D skeleton-based human action recognition (Neurocomputing 2021) [paper] [Github]
-
[AAM-GCN] Attention adjacency matrix based graph convolutional networks for skeleton-based action recognition (Neurocomputing 2021) [paper]
-
[ST-TR] Skeleton-based action recognition via spatial and temporal transformer networks (Comput. Vis. Image Underst. 2021) [paper] [Github]
-
[AS-CAL] Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition (Inf. Sci. 2021) [paper] [Github]
2020
-
(Mainly from [Github], adding latest status)
-
[MV-IGNET] Learning Multi-View Interactional Skeleton Graph for Action Recognition (TPAMI 2020) [paper][Github]
-
[MS-AAGCN] Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks (TIP 2020) [paper]
-
[P&C FW-AEC] PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition (CVPR 2020) [paper]
-
[CA-GC] Context Aware Graph Convolution for Skeleton-Based Action Recognition (CVPR 2020) [paper]
-
[Shift-GCN] Skeleton-Based Action Recognition With Shift Graph Convolutional Network (CVPR 2020) [paper][Github]
-
[DMGNN] Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction (CVPR 2020) [paper]
-
[SGN] Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (CVPR 2020) [arxiv][Github]
-
[MS-G3D] Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition (CVPR 2020) [arxiv] [Github]
-
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition (ECCV 2020) [arxiv]
-
Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement (ECCV 2020) [arxiv] [Github]
-
[DecoupleGCN-DropGraph] Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition (ECCV 2020) [arxiv] [Github]
-
Ms2l: Multi-task self-supervised learning for skeleton based action recognition (ACMMM 2020) [arxiv]
-
[Dynamic GCN] Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition (ACM-MM 2020)[arxiv]
-
[GCN-NAS] Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching (AAAI 2020) [arxiv] [Github]
-
[PA-ResGCN] Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition (ACM-MM 2020) [arxiv] [Github]
-
[Poincare-GCN] Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition (ACM-MM 2020) [arxiv]
-
[STIGCN] Spatio-Temporal Inception Graph Convolutional for Skeleton-Based Action Recognition (ACM-MM 2020) [arxiv]
-
[JOLO-GCN] JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition (WACV 2021) [arxiv]
-
[ST-TR-AGCN] Spatial Temporal Transformer Network for Skeleton-based Action Recognition (Under submission at Computer Vision and Image Understanding (CVIU)) [arxiv] [Github]
-
[PCRP] Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition [arxiv] [Github]
2019
- NTU-RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (TPAMI 2019) [arxiv] [Homepage] [Github]
- [VA-NN] View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition (TPAMI 2019) [arxiv] [Github]
- Bayesian Graph Convolutional LSTM for Skeleton Based Action Recognition (ICCV 2019) [arxiv]
- [2s-SDGCN] Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (ICCV Workshop 2019) [paper]
- [DGNN] Skeleton-Based Action Recognition With Directed Graph Neural Networks (CVPR 2019) [paper] [unofficial PyTorch implementation]
- [2s-AGCN] Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019) [paper] [Github]
- [AS-GCN] Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition (CVPR 2019) [arxiv] [Github]
- [AGC-LSTM] An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (CVPR 2019) [arxiv]
- Optimized Skeleton-based Action Recognition via Sparsified Graph Regression (ACMMM 2019) [paper]
- [Motif-STGCN] Graph CNNs with Motif and Variable Temporal Block for Skeleton-based Action Recognition (AAAI 2019) [arxiv] [Github]
- Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons (ICIP 2019) [arxiv] [Github]
- [TSRJI] Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints (SIBGRAPI) [arxiv] [Github]
- [SkeleMotion] SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition (AVSS) [arxiv] [Github]
2018
- Beyond Joints: Learning Representations from Primitive Geometries for Skeleton-based Action Recognition and Detection (TIP 2018) [paper] [Github]
- [DPRL] Deep progressive reinforcement learning for skeleton-based action recognition (CVPR 2018) [paper]
- [SR-TSL] Skeleton based action recognition with spatial reasoning and temporal stack learning (ECCV 2018) [arxiv]
- [HCN] Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation (IJCAI 2018) [arxiv] [Reimplementation]
- [MAN] Memory attention networks for skeleton-based action recognition (IJCAI 2018) [arxiv] [Github]
- [ST-GCN] Spatial temporal graph convolutional networks for skeleton-based action recognition (AAAI 2018) [arxiv] [Github]
- Unsupervised representation learning with long-term dynamics for skeleton based action recognition (AAAI 2018) [arxiv] [Github]
- Spatio-temporal graph convolution for skeleton based action recognition (AAAI 2018) [arxiv]
- Part-based Graph Convolutional Network for Action Recognition (BMVC 2018) [arxiv] [Github]
- A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition (BMVC 2018) [arxiv]
- A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition (ACMMM 2018) [arxiv]
- Unsupervised feature learning of human actions as trajectories in pose embedding manifold (WACV 2018) [arxiv]
2017
- Jointly learning heterogeneous features for RGB-D activity recognition (TPAMI 2017) [paper]
- [Visualization CNN] Enhanced skeleton visualization for view invariant human action recognition (Pattern Recognition 2017) [paper]
- Global context-aware attention lstm networks for 3d action recognition (CVPR 2017) [paper]
- [Two-stream RNN] Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks (CVPR 2017) [arxiv] [Github]
- [C-CNN + MTLN] A new representation of skeleton sequences for 3d action recognition (CVPR 2017) [arxiv]
- [Ensemble TS-LSTM] Ensemble deep learning for skeleton-based action recognition using temporal sliding lstm networks (ICCV 2017) [paper] [Github]
- [VA-LSTM] View adaptive recurrent neural networks for high performance human action recognition from skeleton data (ICCV 2017) [arxiv]
- Learning action recognition model from depth and skeleton videos (ICCV 2017) [paper]
- [STA-LSTM] An end-to-end spatio-temporal attention model for human action recognition from skeleton data (AAAI 2017) [arxiv]
- Skeleton-based action recognition using LSTM and CNN (ICME Workshop 2017) [arxiv]
- Skeleton-based action recognition with convolutional neural networks (ICME Workshop 2017) [arxiv]
- PKU-MMD: A large scale benchmark for continuous multi-modal human action understanding (ACMMM Workshop 2017) [arxiv]
- [Temporal Conv] Interpretable 3d human action analysis with temporal convolutional networks (CVPR Workshop 2017) [arxiv]
Before 2017
- [Trust Gate ST-LSTM] Spatio-temporal lstm with trust gates for 3d human action recognition (ECCV 2016) [arxiv] [Github]
- [Part-aware LSTM] NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (CVPR 2016) [arxiv]
- Rolling rotations for recognizing human actions from 3d skeletal data (CVPR 2016) [paper]
- Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks (AAAI 2016) [paper]
- Skeleton based action recognition with convolutional neural network (ACPR 2015) [paper]
- [H-RNN] Hierarchical recurrent neural network for skeleton based action recognition (CVPR 2015) [paper]
- Jointly learning heterogeneous features for rgb-d activity recognition (CVPR 2015) [paper]
- [LieGroup] Human action recognition by representing 3d skeletons as points in a lie group (CVPR 2014) [paper]
- Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations (IJCAI 2013) [paper]
arXiv papers
- Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition [arxiv][Github] (Accepted at WACV 2022)
- Sparse Semi-Supervised Action Recognition with Active Learning [arxiv]
- STAR: Sparse Transformer-based Action Recognition [arxiv] [Github]
- [DenseIndRNN] Deep Independently Recurrent Neural Network (Preprint) [arxiv] [Github]
- Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention [arxiv] (Accepted at ICME 2019)
- [DSTA-Net] Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition [arxiv] (Accepted at ACCV 2020)
- SynSE: Syntactically Guided Generative Embeddings for Zero Shot Skeleton Action Recognition [arxiv] [Github] (Accepted at ICIP 2021)
- [PoseC3D] Revisiting Skeleton-based Action Recognition [arxiv][Github]
- Leveraging Third-Order Features in Skeleton-Based Action Recognition [arxiv][Github]
Skeleton-based Action Recognition under Adversarial Attack
- Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack (CVPR 2021) [arxiv]
- BASAR:Black-box Attack on Skeletal Action Recognition (CVPR 2021) [arxiv]
Leaderboards on NTU-RGB+D and NTU-RGB+D 120 Datasets
NTU-RGB+D
Year | Methods | Cross-Subject | Cross-View |
---|---|---|---|
2014 | Lie Group | 50.1 | 52.8 |
2015 | H-RNN | 59.1 | 64.0 |
2016 | Part-aware LSTM | 62.9 | 70.3 |
2016 | Trust Gate ST-LSTM | 69.2 | 77.7 |
2017 | Two-stream RNN | 71.3 | 79.5 |
2017 | STA-LSTM | 73.4 | 81.2 |
2017 | Ensemble TS-LSTM | 74.6 | 81.3 |
2017 | Visualization CNN | 76.0 | 82.6 |
2017 | C-CNN + MTLN | 79.6 | 84.8 |
2017 | Temporal Conv | 74.3 | 83.1 |
2017 | VA-LSTM | 79.4 | 87.6 |
2018 | Beyond Joints | 79.5 | 87.6 |
2018 | ST-GCN | 81.5 | 88.3 |
2018 | DPRL | 83.5 | 89.8 |
2019 | Motif-STGCN | 84.2 | 90.2 |
2018 | HCN | 86.5 | 91.1 |
2018 | SR-TSL | 84.8 | 92.4 |
2018 | MAN | 82.7 | 93.2 |
2019 | RA-GCN | 85.9 | 93.5 |
2019 | DenseIndRNN | 86.7 | 93.7 |
2018 | PB-GCN | 87.5 | 93.2 |
2019 | AS-GCN | 86.8 | 94.2 |
2019 | VA-NN (fusion) | 89.4 | 95.0 |
2019 | AGC-LSTM (Joint&Part) | 89.2 | 95.0 |
2019 | 2s-AGCN | 88.5 | 95.1 |
2020 | SGN | 89.0 | 94.5 |
2020 | GCN-NAS | 89.4 | 95.7 |
2019 | 2s-SDGCN | 89.6 | 95.7 |
2019 | DGNN | 89.9 | 96.1 |
2020 | MV-IGNET | 89.2 | 96.3 |
2020 | 4s Shift-GCN | 90.7 | 96.5 |
2020 | DecoupleGCN-DropGraph | 90.8 | 96.6 |
2020 | PA-ResGCN-B19 | 90.9 | 96.0 |
2020 | MS-G3D | 91.5 | 96.2 |
2021 | EfficientGCN-B4 | 91.7 | 95.7 |
2021 | CTR-GCN | 92.4 | 96.8 |
NTU-RGB+D 120
Year | Methods | Cross-Subject | Cross-Setup |
---|---|---|---|
2019 | SkeleMotion (Magnitude-Orientation) | 62.9 | 63.0 |
2019 | SkeleMotion + Yang et al | 67.7 | 66.9 |
2019 | TSRJI | 67.9 | 59.7 |
2020 | SGN | 79.2 | 81.5 |
2020 | MV-IGNET | 83.9 | 85.6 |
2020 | 4s Shift-GCN | 85.9 | 87.6 |
2020 | DecoupleGCN-DropGraph | 86.5 | 88.1 |
2020 | MS-G3D | 86.9 | 88.4 |
2020 | PA-ResGCN-B19 | 87.3 | 88.3 |
2021 | EfficientGCN-B4 | 88.3 | 89.1 |
2021 | CTR-GCN | 88.9 | 90.6 |
Others
- Kinetics-Skeleton Dataset
- SYSU 3D
- N-UCLA
- SBU
- CAD-120
- UT-Kinect
- MSR Action3D
- J-HMDB
- CAD-120
- Florence 3D
- UAV-Human
Acknowledge
If you have any problems, suggestions or improvements, please feel free to contact me (haocongrao@gmail.com). Welcome to refine current taxonomy, enrich collection of skeleton-based models, and discuss any constructive ideas.