# Skeleton-based Action Recognition Using LSTM and CNN

arXiv: https://arxiv.org/abs/1707.02356 · HTML: https://mlsanity.com/paper/1707.02356/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2017.

## Built on by (most cited first, 10 of 10)

- [MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition](https://mlsanity.com/paper/2108.09322/) (2021)
- [Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2111.11051/) (2021)
- [The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition](https://mlsanity.com/paper/2105.13061/) (2021)
- [A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2111.06995/) (2021)
- [HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition](https://mlsanity.com/paper/2502.05869/) (2025)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [SLGTformer: An Attention-Based Approach to Sign Language Recognition](https://mlsanity.com/paper/2212.10746/) (2022)
- [Online hand gesture recognition using Continual Graph Transformers](https://mlsanity.com/paper/2502.14939/) (2025)
- [Geo-Adaptive Deep Spatio-Temporal predictive modeling for human mobility](https://mlsanity.com/paper/2211.14885/) (2022)
- [Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art](https://mlsanity.com/paper/2311.12300/) (2023)

## Abstract (arXiv)

Recent methods based on 3D skeleton data have achieved outstanding performance due to its conciseness, robustness, and view-independent representation. With the development of deep learning, Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM)-based learning methods have achieved promising performance for action recognition. However, for CNN-based methods, it is inevitable to loss temporal information when a sequence is encoded into images. In order to capture as much spatial-temporal information as possible, LSTM and CNN are adopted to conduct effective recognition with later score fusion. In addition, experimental results show that the score fusion between CNN and LSTM performs better than that between LSTM and LSTM for the same feature. Our method achieved state-of-the-art results on NTU RGB+D datasets for 3D human action analysis. The proposed method achieved 87.40% in terms of accuracy and ranked 1st place in Large Scale 3D Human Activity Analysis Challenge in Depth Videos.