Fahimeh Fooladgar

Papers

Total Citations

H-Index

About

Fahimeh Fooladgar is a researcher whose work sits at the intersection of computer vision and robotics, with a primary focus on advancing 3D scene understanding. Her key contributions lie in developing sophisticated deep learning models for semantic segmentation of RGB-Depth images and 3D point clouds—a critical capability for enabling machines to perceive and interact with their environment. She has pioneered multi-modal fusion techniques, notably introducing a multi-modal attention-based fusion model that intelligently combines visual and depth data to improve segmentation accuracy. Her work on the 3M2RNet (Multi-Modal Multi-Resolution Refinement Network) further refines this approach by processing information at multiple resolutions. Fooladgar has also explored novel architectures for handling the inherent irregularity of 3D point clouds, including pointwise attention-based atrous convolutional neural networks. Her most cited paper, "Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images" (2019), has garnered 16 citations, demonstrating its influence in the field. Through these contributions, Fooladgar is helping to build the foundational perception systems that will power next-generation autonomous robots and intelligent agents.