activity
20242026
collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

LITEWAY: LIghtweight HAR via Temporal Efficient highWAY

Dominique Nshimyimana, Vitor Fortes Rey, Mengxi Liu +2

Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices. Existing lightwei…

cs.LG2025

Bridging Generalization and Personalization in Human Activity Recognition via On-Device Few-Shot Learning

Pixi Kang, Julian Moosmann, Mengxi Liu +4

Human Activity Recognition (HAR) with different sensing modalities requires both strong generalization across diverse users and efficient personalization for individuals. However,…

cs.LG2025

Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition

Daniel Geissler, Lars Krupp, Vishal Banwari +4

Latent space representations are critical for understanding and improving the behavior of machine learning models, yet they often remain obscure and intricate. Understanding and ex…

cs.LG2025

MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition

Stefan Gerd Fritsch, Cennet Oguz, Vitor Fortes Rey +3

Human activity recognition (HAR) is a long-standing problem in artificial intelligence with applications in a broad range of areas, including healthcare, sports and fitness, securi…

cs.LG2024

Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets

Daniel Geissler, Dominique Nshimyimana, Vitor Fortes Rey +3

The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research priorit…

cs.LG2024

Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization

Daniel Geissler, Bo Zhou, Sungho Suh +1

A fundamental step in the development of machine learning models commonly involves the tuning of hyperparameters, often leading to multiple model training runs to work out the best…