# Feature Learning for Accelerometer based Gait Recognition

arXiv: https://arxiv.org/abs/2007.15958 · HTML: https://mlsanity.com/paper/2007.15958/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 2 of 2)

- [Human Gait Recognition Using Bag of Words Feature Representation Method](https://mlsanity.com/paper/2203.13317/) (2022)
- [Classification of anomalous gait using Machine Learning techniques and embedded sensors](https://mlsanity.com/paper/2110.06139/) (2021)

## Abstract (arXiv)

Recent advances in pattern matching, such as speech or object recognition support the viability of feature learning with deep learning solutions for gait recognition. Past papers have evaluated deep neural networks trained in a supervised manner for this task. In this work, we investigated both supervised and unsupervised approaches. Feature extractors using similar architectures incorporated into end-to-end models and autoencoders were compared based on their ability of learning good representations for a gait verification system. Both feature extractors were trained on the IDNet dataset then used for feature extraction on the ZJU-GaitAccel dataset. Results show that autoencoders are very close to discriminative end-to-end models with regards to their feature learning ability and that fully convolutional models are able to learn good feature representations, regardless of the training strategy.