Title:	Vahab-LiU-1
DNr:	LiU-gpu-2024-17
Project Type:	LiU Compute
Principal Investigator:	Abdolvahab Khalili Sadaghiani <abdolvahab.khalili.sadaghiani@liu.se>
Affiliation:	Linköpings universitet
Duration:	2025-01-03 – 2026-01-01
Classification:	10207
Keywords:

Abstract

My project focuses on developing an advanced object detection framework by integrating Convolutional Neural Networks (CNNs), Transformer architectures, and Graph Neural Networks (GNNs). Object detection is a crucial task in computer vision, with applications ranging from autonomous vehicles to medical imaging. While existing methods excel at detecting individual objects, they often fail to account for spatial and contextual relationships among detections. This project addresses this limitation by enhancing the detection pipeline with graph-based reasoning, enabling better understanding and refinement of object relationships.