PulseAugur
EN
LIVE 09:33:00

Gated Fusion Leads Multi-modal Activity Recognition on HARMES Dataset

By PulseAugur Editorial · [2 sources] ·

Researchers have conducted a comparative study of seven sensor fusion techniques for multi-modal human activity recognition using the HARMES dataset. The study found that Gated Multi-modal Fusion achieved the highest performance, with a macro F1-score of 0.82. This method surpassed the baseline concatenation-based late fusion by 6 percentage points. The code for the experiments has been made publicly available on GitHub. AI

IMPACT This research provides a benchmark for sensor fusion techniques in multi-modal human activity recognition, potentially guiding future model development.

RANK_REASON The cluster contains an academic paper detailing a comparative study of machine learning techniques on a specific dataset.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Gated Fusion Leads Multi-modal Activity Recognition on HARMES Dataset

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Ahmed Mohamady, Robin Burchard, Kristof Van Laerhoven ·

    A Comparison of Fusion Techniques for Multi-Modal Human Activity Recognition on the HARMES Dataset

    arXiv:2606.27886v1 Announce Type: new Abstract: Recent advances in Human Activity Recognition (HAR) from wearable sensors have shown that multi-modal deep learning models consistently outperform their uni-modal counterparts. Modalities can include IMUs, RGB cameras, audio signals…

  2. arXiv cs.LG TIER_1 English(EN) · Kristof Van Laerhoven ·

    A Comparison of Fusion Techniques for Multi-Modal Human Activity Recognition on the HARMES Dataset

    Recent advances in Human Activity Recognition (HAR) from wearable sensors have shown that multi-modal deep learning models consistently outperform their uni-modal counterparts. Modalities can include IMUs, RGB cameras, audio signals, and others. One important aspect of multi-moda…

RELATED ENTITIES

RELATED TOPICS