# Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints

arXiv: https://arxiv.org/abs/1909.05704 · HTML: https://mlsanity.com/paper/1909.05704/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)
- [UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition](https://mlsanity.com/paper/2107.08580/) (2021)
- [Contrastive Positive Mining for Unsupervised 3D Action Representation Learning](https://mlsanity.com/paper/2208.03497/) (2022)
- [Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2108.04536/) (2021)
- [ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting](https://mlsanity.com/paper/2209.00065/) (2022)
- [LAC: Latent Action Composition for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2308.14500/) (2023)
- [Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition](https://mlsanity.com/paper/2202.11374/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation](https://mlsanity.com/paper/2406.18011/) (2024)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)
- [AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement](https://mlsanity.com/paper/2208.03444/) (2022)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [Action Recognition with Domain Invariant Features of Skeleton Image](https://mlsanity.com/paper/2111.11250/) (2021)
- [Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics](https://mlsanity.com/paper/2408.01701/) (2024)
- [Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2210.06192/) (2022)
- [I2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation](https://mlsanity.com/paper/2310.15568/) (2023)
- [Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercises](https://mlsanity.com/paper/2408.02855/) (2024)
- [A Survey on Human Action Recognition](https://mlsanity.com/paper/2301.06082/) (2022)
- [Learning to Simplify Spatial-Temporal Graphs in Gait Analysis](https://mlsanity.com/paper/2310.03396/) (2023)
- [Collaboratively Self-supervised Video Representation Learning for Action Recognition](https://mlsanity.com/paper/2401.07584/) (2024)
- [Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition](https://mlsanity.com/paper/2401.14034/) (2024)
- [Unsupervised Motion Retargeting for Human-Robot Imitation](https://mlsanity.com/paper/2402.05115/) (2024)
- [An Improved Graph Pooling Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2404.16359/) (2024)

## Abstract (arXiv)

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural Networks (RNNs) with Long-Short Term Memory (LSTM); and (ii) skeleton image representations used as input to a Convolutional Neural Network (CNN). Although RNN approaches present excellent results, such methods lack the ability to efficiently learn the spatial relations between the skeleton joints. On the other hand, the representations used to feed CNN approaches present the advantage of having the natural ability of learning structural information from 2D arrays (i.e., they learn spatial relations from the skeleton joints). To further improve such representations, we introduce the Tree Structure Reference Joints Image (TSRJI), a novel skeleton image representation to be used as input to CNNs. The proposed representation has the advantage of combining the use of reference joints and a tree structure skeleton. While the former incorporates different spatial relationships between the joints, the latter preserves important spatial relations by traversing a skeleton tree with a depth-first order algorithm. Experimental results demonstrate the effectiveness of the proposed representation for 3D action recognition on two datasets achieving state-of-the-art results on the recent NTU RGB+D~120 dataset.