11 papers
ESC: Emotional Self-Correction for Reliable Vision-Language Models
Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy +9
Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods…
Domain-Adapted Fine-Tuning of ECG Foundation Models for Multi-Label Structural Heart Disease Screening
Duc N. Do, Minh N. Do, Dang Nguyen +14
Transthoracic echocardiography is the reference standard for confirming structural heart disease (SHD), but first-line screening is limited by cost, workflow burden, and specialist…
Domain-invariant Mixed-domain Semi-supervised Medical Image Segmentation with Clustered Maximum Mean Discrepancy Alignment
Ba-Thinh Lam, Thanh-Huy Nguyen, Hoang-Thien Nguyen +5
Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributi…
Scribble-Supervised Medical Image Segmentation with Dynamic Teacher Switching and Hierarchical Consistency
Thanh-Huy Nguyen, Hoang-Loc Cao, Dat T. Chung +5
Scribble-supervised methods have emerged to mitigate the prohibitive annotation burden in medical image segmentation. However, the inherent sparsity of these annotations introduces…
Topology-Aware Spatio-Temporal Graph Transformer for Predicting Smart Grid Failures
Anh Le, Phat K. Huynh, Om P. Yadav +3
Smart grid infrastructure needs improved resilience and preventive maintenance through more accurate predictions. Current methodologies lack accurate representation of spatio-tempo…
Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation
Tien-Dat Chung, Ba-Thinh Lam, Thanh-Huy Nguyen +5
Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samp…