Leveraging Key-Points Encoded Human Pose Images for Human Activity Recognition
Abstract
Human Activity Recognition (HAR) is a significant area of interest with diverse potential applications; however, the existing literature lacks a high-performance reference solution. This study aims to fill this gap and focuses on the domain of device-free HAR, investigating a little-explored vision-based approach for action representation: the Encoded Human Pose Image (EHPI). The research explores various architectural choices for EHPI generation and provides a performance baseline using the public MCAD dataset. Additionally, to overcome the difficulty of limited datasets in HAR in literature, as an additional contribution we introduce and share the UCBM-ELT dataset. It is an in-house realized dataset that focuses on atomic-level action analysis in more complex and realistic scenarios and aims to enhance model generalizability and robustness by incorporating intra-class variations.
Cite
Text
Dobici et al. "Leveraging Key-Points Encoded Human Pose Images for Human Activity Recognition." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91575-8_6Markdown
[Dobici et al. "Leveraging Key-Points Encoded Human Pose Images for Human Activity Recognition." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/dobici2024eccvw-leveraging/) doi:10.1007/978-3-031-91575-8_6BibTeX
@inproceedings{dobici2024eccvw-leveraging,
title = {{Leveraging Key-Points Encoded Human Pose Images for Human Activity Recognition}},
author = {Dobici, Gaia Virginia and Minutillo, Luca and Cordelli, Ermanno and Chirico, Francesco and Foglia, Goffredo and Soda, Paolo},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {88-102},
doi = {10.1007/978-3-031-91575-8_6},
url = {https://mlanthology.org/eccvw/2024/dobici2024eccvw-leveraging/}
}