Jinxuan Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jinxuan Yu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Bohan Chen
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430079, China
1 shared publication - Bowen Qu
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
1 shared publication - Han Huang
School of Management, Wuhan University of Technology, Wuhan 430070, China
1 shared publication - Jianing Guo
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
1 shared publication - Jingyu Chen
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
1 shared publication - Longxiang Ma
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430079, China
1 shared publication
Latest Publications
- Open Access
- 4 January 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (1) , 24
LLM-Based Pose Normalization and Multimodal Fusion for Facial Expression Recognition in Extreme Poses
Facial expression recognition (FER) technology has progressively matured over time. However, existing FER methods are primarily optimized for frontal face images, and their recognition accuracy significantly degrades when processing profile or large-angle rotated facial images. Consequently, this limitation hinders the practical deployment of FER systems. To mitigate the interference caused by large pose variations and improve recognition accuracy, we propose a FER method based on profile-to-frontal transformation and multimodal learning. Specifically, we first leverage the visual understanding and generation capabilities of Qwen-Image-Edit that transform profile images to frontal viewpoints, preserving key expression features while standardizing facial poses. Second, we introduce the CLIP model to enhance the semantic representation capability of expression features through vision–language joint learning. The qualitative and quantitative experiments on the RAF (89.39%), EXPW (67.17%), and AffectNet-7 (62.66%) datasets demonstrate that our method outperforms the existing approaches.
- 4 January 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (1) , 24
Open AccessLLM-Based Pose Normalization and Multimodal Fusion for Facial Expression Recognition in Extreme Poses
Facial expression recognition (FER) technology has progressively matured over time. However, existing FER methods are primarily optimized for frontal face images, and their recognition accuracy significantly degrades when processing profile or large-angle rotated facial images. Consequently, this limitation hinders the practical deployment of FER systems. To mitigate the interference caused by large pose variations and improve recognition accuracy, we propose a FER method based on profile-to-frontal transformation and multimodal learning. Specifically, we first leverage the visual understanding and generation capabilities of Qwen-Image-Edit that transform profile images to frontal viewpoints, preserving key expression features while standardizing facial poses. Second, we introduce the CLIP model to enhance the semantic representation capability of expression features through vision–language joint learning. The qualitative and quantitative experiments on the RAF (89.39%), EXPW (67.17%), and AffectNet-7 (62.66%) datasets demonstrate that our method outperforms the existing approaches.