# Hierarchical growing grid networks for skeleton based action recognition

arXiv: https://arxiv.org/abs/2104.11165 · HTML: https://mlsanity.com/paper/2104.11165/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 70 references that are in the map.
- First posted on arXiv 22 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1804.07453/) (2018)
- [Differential Recurrent Neural Networks for Action Recognition](https://mlsanity.com/paper/1504.06678/) (2015)
- [Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection](https://mlsanity.com/paper/1704.00616/) (2017)
- [Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video](https://mlsanity.com/paper/1506.01911/) (2015)
- [First and Second Order Dynamics in a Hierarchical SOM system for Action Recognition](https://mlsanity.com/paper/2104.06059/) (2021)
- [Online Recognition of Actions Involving Objects](https://mlsanity.com/paper/2104.06070/) (2021)

## Built on by (most cited first, 4 of 4)

- [Online recognition of unsegmented actions with hierarchical SOM architecture](https://mlsanity.com/paper/2104.11637/) (2021)
- [Action in Mind: A Neural Network Approach to Action Recognition and Segmentation](https://mlsanity.com/paper/2104.14870/) (2021)
- [Video Relationship Detection Using Mixture of Experts](https://mlsanity.com/paper/2403.03994/) (2024)
- [Predicting the intended action using internal simulation of perception](https://mlsanity.com/paper/2202.04466/) (2022)

## Abstract (arXiv)

In this paper, a novel cognitive architecture for action recognition is developed by applying layers of growing grid neural networks.Using these layers makes the system capable of automatically arranging its representational structure. In addition to the expansion of the neural map during the growth phase, the system is provided with a prior knowledge of the input space, which increases the processing speed of the learning phase. Apart from two layers of growing grid networks the architecture is composed of a preprocessing layer, an ordered vector representation layer and a one-layer supervised neural network. These layers are designed to solve the action recognition problem. The first-layer growing grid receives the input data of human actions and the neural map generates an action pattern vector representing each action sequence by connecting the elicited activation of the trained map. The pattern vectors are then sent to the ordered vector representation layer to build the time-invariant input vectors of key activations for the second-layer growing grid. The second-layer growing grid categorizes the input vectors to the corresponding action clusters/sub-clusters and finally the one-layer supervised neural network labels the shaped clusters with action labels. Three experiments using different datasets of actions show that the system is capable of learning to categorize the actions quickly and efficiently. The performance of the growing grid architecture is com-pared with the results from a system based on Self-Organizing Maps, showing that the growing grid architecture performs significantly superior on the action recognition tasks.