# Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition

arXiv: https://arxiv.org/abs/2110.12163 · HTML: https://mlsanity.com/paper/2110.12163/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 23 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [Stratified Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1801.00820/) (2017)
- [Human Activity Recognition from Wearable Sensor Data Using Self-Attention](https://mlsanity.com/paper/2003.09018/) (2020)
- [Deep Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1807.07963/) (2018)
- [Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables](https://mlsanity.com/paper/1811.08127/) (2018)
- [Semi-Supervised Convolutional Neural Networks for Human Activity Recognition](https://mlsanity.com/paper/1801.07827/) (2018)
- [Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection](https://mlsanity.com/paper/1701.01077/) (2017)

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

- [Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition](https://mlsanity.com/paper/2210.01459/) (2022)
- [Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applications](https://mlsanity.com/paper/2203.10794/) (2022)
- [TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation](https://mlsanity.com/paper/2209.09092/) (2022)
- [Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition](https://mlsanity.com/paper/2406.16886/) (2024)
- [RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition](https://mlsanity.com/paper/2512.08984/) (2025)
- [Worker Activity Recognition in Manufacturing Line Using Near-body Electric Field](https://mlsanity.com/paper/2308.03514/) (2023)
- [Efficient Deep Clustering of Human Activities and How to Improve Evaluation](https://mlsanity.com/paper/2209.08335/) (2022)
- [RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment](https://mlsanity.com/paper/2607.26631/) (2026)
- [Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2212.13918/) (2022)
- [Deep Adversarial Learning with Activity-Based User Discrimination Task for Human Activity Recognition](https://mlsanity.com/paper/2410.12819/) (2024)

## Abstract (arXiv)

User dependence remains one of the most difficult general problems in Human Activity Recognition (HAR), in particular when using wearable sensors. This is due to the huge variability of the way different people execute even the simplest actions. In addition, detailed sensor fixtures and placement will be different for different people or even at different times for the same users. In theory, the problem can be solved by a large enough data set. However, recording data sets that capture the entire diversity of complex activity sets is seldom practicable. Instead, models are needed that focus on features that are invariant across users. To this end, we present an adversarial subject-independent feature extraction method with the maximum mean discrepancy (MMD) regularization for human activity recognition. The proposed model is capable of learning a subject-independent embedding feature representation from multiple subjects datasets and generalizing it to unseen target subjects. The proposed network is based on the adversarial encoder-decoder structure with the MMD realign the data distribution over multiple subjects. Experimental results show that the proposed method not only outperforms state-of-the-art methods over the four real-world datasets but also improves the subject generalization effectively. We evaluate the method on well-known public data sets showing that it significantly improves user-independent performance and reduces variance in results.