# Multilevel neural networks with dual-stage feature fusion for human activity recognition

arXiv: https://arxiv.org/abs/2604.16577 · HTML: https://mlsanity.com/paper/2604.16577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 17 Apr 2026.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice](https://mlsanity.com/paper/2404.16958/) (2024)
- [Deep ConvLSTM with self-attention for human activity decoding using wearables](https://mlsanity.com/paper/2005.00698/) (2020)
- [Transfer Learning in Human Activity Recognition: A Survey](https://mlsanity.com/paper/2401.10185/) (2024)
- [Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects](https://mlsanity.com/paper/2202.03274/) (2022)
- [Human Activity Recognition using Multi-Head CNN followed by LSTM](https://mlsanity.com/paper/2003.06327/) (2020)

## Abstract (arXiv)

Human activity recognition (HAR) refers to the process of identifying human actions and activities using data collected from sensors. Neural networks, such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, convolutional LSTM, and their hybrid combinations, have demonstrated exceptional performance in various research domains. Developing a multilevel individual or hybrid model for HAR involves strategically integrating multiple networks to capitalize on their complementary strengths. The structural arrangement of these components is a critical factor influencing the overall performance. This study explores a novel framework of a two-level network architecture with dual-stage feature fusion: late fusion, which combines the outputs from the first network level, and intermediate fusion, which integrates the features from both the first and second levels. We evaluated 15 different network architectures of CNNs, LSTMs, and convolutional LSTMs, incorporating late fusion with and without intermediate fusion, to identify the optimal configuration. Experimental evaluation on two public benchmark datasets demonstrates that architectures incorporating both late and intermediate fusion achieve higher accuracy than those relying on late fusion alone. Moreover, the optimal configuration outperforms baseline models, thereby validating its effectiveness for HAR.