MSAFNet: a novel approach to facial expression recognition in embodied AI systems
Intelligence & Robotics · 11.04.2025 · 5 (2) · 313-32
DOI: 10.20517/ir.2025.16 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligence & Robotics, online erschienen am 11.04.2025. Verfasst von Huifang He und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 66 Literaturangaben.
Abstract (Originalsprache)
In embodied artificial intelligence (EAI), accurately recognizing human facial expressions is crucial for intuitive and effective human-robot interactions. We introduce multi-scale attention and convolution-transformer fusion network, a deep learning framework tailored for EAI, designed to dynamically detect and process facial expressions, facilitating adaptive interactions based on the user's emotional state. The proposed network comprises three distinct components: a local feature extraction module that utilizes attention mechanisms to focus on key facial regions, a global feature extraction module that employs Transformer-based architectures to capture comprehensive global information, and a global-local feature fusion module that integrates these insights to enhance facial expression recognition accuracy. Our experimental results on prominent datasets such as FER2013 and RAF-DB indicate that our data-driven approach consistently outperforms existing state-of-the-art methods.
Zitieren
APA
He, H., Liao, R., & Li, Y. (2025). MSAFNet: a novel approach to facial expression recognition in embodied AI systems. Intelligence & Robotics, 5(2), 313-32. https://doi.org/10.20517/ir.2025.16
Vancouver
He H, Liao R, Li Y. MSAFNet: a novel approach to facial expression recognition in embodied AI systems. Intelligence & Robotics. 2025;5(2):313-32. doi:10.20517/ir.2025.16
BibTeX
@article{He2025,
author = {He, Huifang and Liao, Runbin and Li, Yating},
title = {MSAFNet: a novel approach to facial expression recognition in embodied AI systems},
journal = {Intelligence & Robotics},
year = {2025},
volume = {5},
number = {2},
pages = {313--32},
doi = {10.20517/ir.2025.16}
}
EUVIMED