# Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn

arXiv: https://arxiv.org/abs/1704.05645 · HTML: https://mlsanity.com/paper/1704.05645/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 26 of 26)

- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition](https://mlsanity.com/paper/2207.12100/) (2022)
- [Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2202.04075/) (2022)
- [Lifting Monocular Events to 3D Human Poses](https://mlsanity.com/paper/2104.10609/) (2021)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2112.10570/) (2021)
- [Bootstrapped Representation Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2202.02232/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition](https://mlsanity.com/paper/2404.10210/) (2024)
- [RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model](https://mlsanity.com/paper/2407.06162/) (2024)
- [3D Plant Root Skeleton Detection and Extraction](https://mlsanity.com/paper/2508.08094/) (2025)
- [Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.08599/) (2022)
- [Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2302.13434/) (2023)
- [Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition](https://mlsanity.com/paper/2403.12519/) (2024)
- [Deep video representation learning: a survey](https://mlsanity.com/paper/2405.06574/) (2024)
- [AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement](https://mlsanity.com/paper/2208.03444/) (2022)
- [SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network](https://mlsanity.com/paper/2306.17574/) (2023)
- [RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios](https://mlsanity.com/paper/2412.14643/) (2024)
- [Online hand gesture recognition using Continual Graph Transformers](https://mlsanity.com/paper/2502.14939/) (2025)
- [SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition](https://mlsanity.com/paper/2511.22433/) (2025)
- [Action Capsules: Human Skeleton Action Recognition](https://mlsanity.com/paper/2301.13090/) (2023)
- [SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System](https://mlsanity.com/paper/2311.08094/) (2023)
- [Human Action Recognition (HAR) Using Skeleton-based Spatial Temporal Relative Transformer Network: ST-RTR](https://mlsanity.com/paper/2410.23806/) (2024)
- [LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation](https://mlsanity.com/paper/2506.04561/) (2025)
- [Affinity Contrastive Learning for Skeleton-based Human Activity Understanding](https://mlsanity.com/paper/2601.16694/) (2026)

## Abstract (arXiv)

This paper presents an image classification based approach for skeleton-based video action recognition problem. Firstly, A dataset independent translation-scale invariant image mapping method is proposed, which transformes the skeleton videos to colour images, named skeleton-images. Secondly, A multi-scale deep convolutional neural network (CNN) architecture is proposed which could be built and fine-tuned on the powerful pre-trained CNNs, e.g., AlexNet, VGGNet, ResNet etal.. Even though the skeleton-images are very different from natural images, the fine-tune strategy still works well. At last, we prove that our method could also work well on 2D skeleton video data. We achieve the state-of-the-art results on the popular benchmard datasets e.g. NTU RGB+D, UTD-MHAD, MSRC-12, and G3D. Especially on the largest and challenge NTU RGB+D, UTD-MHAD, and MSRC-12 dataset, our method outperforms other methods by a large margion, which proves the efficacy of the proposed method.