DUAL-Net: Joint Domain-Invariant and User-Adaptive Feature Learning for Gesture Recognition
Sensors · 02.07.2026 · 26 (13) · 4182
DOI: 10.3390/s26134182 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.07.2026. Verfasst von Shuangjiao Zhai und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, North University of China, Taiyuan 030051, China. Hauptthemen laut MEDLINE: Gestures, Pattern Recognition, Automated. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Natural Science Basic Research Program of Shanxi Province.
Abstract (Originalsprache)
Human activity recognition has become an important component of human–computer interaction and ubiquitous computing. Among various sensing technologies, WiFi-based gesture recognition has attracted increasing attention due to its contactless nature and robustness to visual occlusion. However, environmental variations and user-specific differences often lead to significant performance degradation, particularly in cross-user scenarios. Existing methods primarily focus on learning domain-invariant representations, which may overlook user-specific characteristics that are essential for accurate recognition. To address this issue, we propose the Domain-invariant and User-Adaptive Learning Network (DUAL-Net), a dual-branch framework that jointly models domain-invariant and user-adaptive representations. Specifically, DUAL-Net incorporates a contrastive fusion learning (CFL) module with modality-specific encoders to learn complementary representations from WiFi and vision modalities. Furthermore, a spatial matrix difference (SMD)-guided cross-modal generation (CMG) module is introduced to generate user-adaptive WiFi features by incorporating structural priors derived from skeletal representations. To improve deployment efficiency, DUAL-Net adopts a two-stage learning framework, where adaptation is conducted offline to reduce online computational overhead. Experiments on the MM-Fi dataset and a self-collected dataset show that DUAL-Net achieves superior cross-user recognition performance compared with existing single-modality and multimodal methods. In addition, SMD-guided conditioning improves recognition accuracy by up to 8.79% over diffusion generation without structural guidance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, North University of China, Taiyuan 030051, China.
- School of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030600, China.
ORCID-Profile: Shuangjiao Zhai, Yujie Guo
Förderung
- Natural Science Foundation of China
- Natural Science Basic Research Program of Shanxi Province
Zitieren
APA
Zhai, S., Yang, B., Dai, Z., Guo, Y., Jing, B., Qin, J., & Qin, P. (2026). DUAL-Net: Joint Domain-Invariant and User-Adaptive Feature Learning for Gesture Recognition. Sensors, 26(13), 4182. https://doi.org/10.3390/s26134182
Vancouver
Zhai S, Yang B, Dai Z, Guo Y, Jing B, Qin J, et al. DUAL-Net: Joint Domain-Invariant and User-Adaptive Feature Learning for Gesture Recognition. Sensors. 2026;26(13):4182. doi:10.3390/s26134182
BibTeX
@article{Zhai2026,
author = {Zhai, Shuangjiao and Yang, Bo and Dai, Zixin and Guo, Yujie and Jing, Baojin and Qin, Jia and Qin, Pinle},
title = {DUAL-Net: Joint Domain-Invariant and User-Adaptive Feature Learning for Gesture Recognition},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {4182},
doi = {10.3390/s26134182}
}
EUVIMED