# Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention

arXiv: https://arxiv.org/abs/1810.04038 · HTML: https://mlsanity.com/paper/1810.04038/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2018.

## Built on by (most cited first, 27 of 27)

- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task](https://mlsanity.com/paper/2411.14452/) (2024)
- [Explainable Activity Recognition for Smart Home Systems](https://mlsanity.com/paper/2105.09787/) (2021)
- [TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation](https://mlsanity.com/paper/2209.09092/) (2022)
- [Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables](https://mlsanity.com/paper/2308.03805/) (2023)
- [Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition](https://mlsanity.com/paper/2205.10071/) (2022)
- [MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition](https://mlsanity.com/paper/2505.20744/) (2025)
- [Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition](https://mlsanity.com/paper/2210.03382/) (2022)
- [Siamese Networks for Weakly Supervised Human Activity Recognition](https://mlsanity.com/paper/2307.08944/) (2023)
- [Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition](https://mlsanity.com/paper/2101.06634/) (2021)
- [Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition](https://mlsanity.com/paper/2103.04279/) (2021)
- [Attention-Based Sensor Fusion for Human Activity Recognition Using IMU Signals](https://mlsanity.com/paper/2112.11224/) (2021)
- [Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2203.04153/) (2022)
- [SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network](https://mlsanity.com/paper/2507.00050/) (2025)
- [Deconfounding Causal Inference through Two-Branch Framework with Early-Forking for Sensor-Based Cross-Domain Activity Recognition](https://mlsanity.com/paper/2507.03898/) (2025)
- [Activity-Aware Deep Cognitive Fatigue Assessment using Wearables](https://mlsanity.com/paper/2105.02824/) (2021)
- [Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems](https://mlsanity.com/paper/2106.02549/) (2021)
- [SpiroMask: Measuring Lung Function Using Consumer-Grade Masks](https://mlsanity.com/paper/2201.09280/) (2022)
- [Robust Multimodal Fusion for Human Activity Recognition](https://mlsanity.com/paper/2303.04636/) (2023)
- [Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches](https://mlsanity.com/paper/2512.19713/) (2025)
- [Description of Structural Biases and Associated Data in Sensor-Rich Environments](https://mlsanity.com/paper/2104.04885/) (2021)
- [Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity Recognition](https://mlsanity.com/paper/2305.03810/) (2023)
- [Game Theory Solutions in Sensor-Based Human Activity Recognition: A Review](https://mlsanity.com/paper/2311.06311/) (2023)
- [AUGlasses: Continuous Action Unit based Facial Reconstruction with Low-power IMUs on Smart Glasses](https://mlsanity.com/paper/2405.13289/) (2024)
- [Redundant feature screening method for human activity recognition based on attention purification mechanism](https://mlsanity.com/paper/2503.23537/) (2025)
- [Leveraging Imperfect Medical Data: A Manifold-Consistent Spatio-Temporal Network for Sensor-based Human Activity Recognition](https://mlsanity.com/paper/2605.00913/) (2026)

## Abstract (arXiv)

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To further improve the understandability and mean F1 score, we add continuity constraints, considering that continuous sensor signals are more robust than discrete ones. We evaluate the approaches on three datasets and obtain state-of-the-art results. Furthermore, qualitative analysis shows that the attention learned by the models agree well with human intuition.