collaborators

17 papers

cs.CV2026

GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformer

Xinyuan Zhao, Yihang Wu, Ahmad Chaddad +2

Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges with convolutional neural n…

cs.CV2026

Impact of domain adaptation in deep learning for medical image classifications

Yihang Wu, Ahmad Chaddad

Domain adaptation (DA) is a quickly expanding area in machine learning that involves adjusting a model trained in one domain to perform well in another domain. While there have bee…

cs.CV2026

Deep Modeling and Interpretation for Bladder Cancer Classification

Ahmad Chaddad, Yihang Wu, Xianrui Chen

Deep models based on vision transformer (ViT) and convolutional neural network (CNN) have demonstrated remarkable performance on natural datasets. However, these models may not be…

cs.CV2026

Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classification

Xinyuan Zhao, Yihang Wu, Ahmad Chaddad +2

While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many or…

cs.CV2026

GazeFormer-MoE: Context-Aware Gaze Estimation via CLIP and MoE Transformer

Xinyuan Zhao, Xianrui Chen, Ahmad Chaddad

We present a semantics modulated, multi scale Transformer for 3D gaze estimation. Our model conditions CLIP global features with learnable prototype banks (illumination, head pose,…

cs.CV2025

Federated CLIP for Resource-Efficient Heterogeneous Medical Image Classification

Yihang Wu, Ahmad Chaddad

Despite the remarkable performance of deep models in medical imaging, they still require source data for training, which limits their potential in light of privacy concerns. Federa…