# Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors

arXiv: https://arxiv.org/abs/2007.07172 · HTML: https://mlsanity.com/paper/2007.07172/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 19 of 19)

- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition](https://mlsanity.com/paper/2304.05088/) (2023)
- [Differentiable Network Pruning for Microcontrollers](https://mlsanity.com/paper/2110.08350/) (2021)
- [Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors](https://mlsanity.com/paper/2305.13124/) (2023)
- [COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition](https://mlsanity.com/paper/2503.07259/) (2025)
- [Temporal Action Localization for Inertial-based Human Activity Recognition](https://mlsanity.com/paper/2311.15831/) (2023)
- [RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition](https://mlsanity.com/paper/2512.08984/) (2025)
- [WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches](https://mlsanity.com/paper/2509.04736/) (2025)
- [Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition](https://mlsanity.com/paper/2208.07547/) (2022)
- [SoK: Behind the Accuracy of Complex Human Activity Recognition Using Deep Learning](https://mlsanity.com/paper/2405.00712/) (2024)
- [Left-Right Swapping and Upper-Lower Limb Pairing for Robust Multi-Wearable Workout Activity Detection](https://mlsanity.com/paper/2408.03947/) (2024)
- [Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition](https://mlsanity.com/paper/2206.04855/) (2022)
- [In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models against Variability](https://mlsanity.com/paper/2503.11466/) (2025)
- [DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition](https://mlsanity.com/paper/2505.20894/) (2025)
- [Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing](https://mlsanity.com/paper/2507.12002/) (2025)
- [Sensor-Specific Transformer (PatchTST) Ensembles with Test-Matched Augmentation](https://mlsanity.com/paper/2510.21282/) (2025)
- [PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks](https://mlsanity.com/paper/2605.09434/) (2026)
- [GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery](https://mlsanity.com/paper/2605.22086/) (2026)

## Abstract (arXiv)

Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gait analysis. Although our collective know-how to solve Human Activity Recognition (HAR) problems with wearables has progressed immensely with end-to-end deep learning paradigms, several fundamental opportunities remain overlooked. We rigorously explore these new opportunities to learn enriched and highly discriminating activity representations. We propose: i) learning to exploit the latent relationships between multi-channel sensor modalities and specific activities; ii) investigating the effectiveness of data-agnostic augmentation for multi-modal sensor data streams to regularize deep HAR models; and iii) incorporating a classification loss criterion to encourage minimal intra-class representation differences whilst maximising inter-class differences to achieve more discriminative features. Our contributions achieves new state-of-the-art performance on four diverse activity recognition problem benchmarks with large margins -- with up to 6% relative margin improvement. We extensively validate the contributions from our design concepts through extensive experiments, including activity misalignment measures, ablation studies and insights shared through both quantitative and qualitative studies.