3 papers
cs.CV2025
DyCAF-Net: Dynamic Class-Aware Fusion Network
Md Abrar Jahin, Shahriar Soudeep, M. F. Mridha +2
Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attenti…
cs.LG2025
CAGN-GAT Fusion: A Hybrid Contrastive Attentive Graph Neural Network for Network Intrusion Detection
Md Abrar Jahin, Shahriar Soudeep, Fahmid Al Farid +4
Cybersecurity threats are growing, making network intrusion detection essential. Traditional machine learning models remain effective in resource-limited environments due to their…
cs.CV2024
Interpretable Dynamic Graph Neural Networks for Small Occluded Object Detection and Tracking
Shahriar Soudeep, Md Abrar Jahin, M. F. Mridha
The detection and tracking of small, occluded objects such as pedestrians, cyclists, and motorbikes pose significant challenges for traffic surveillance systems because of their er…