Vision Foundation Models

Fine-Grained Visual Representations through Sparse Selection of Localized Features

Fatimah Zohra, Ph.D. Student, Computer Science

Oct 19, 19:00 - 20:00

B1 R2202

vision transformer implicit neural representation spatio-temporal modeling Vision Foundation Models visual computing

This thesis studies and develops sparse localized feature selection techniques for vision transformer (ViT) models to improve representation of fine-grained visual details across images and videos to capture fine-grained spatial and temporal structure that are often lost in global representations of current ViT foundation models.

Abdelrahman Eldesokey

Postdoctoral Research Fellow

Computer Vision Diffusion Models Vision Foundation Models Multi-Modal Large Language Models

Abdelrahman Eldesokey is a Postdoctoral Fellow at KAUST, working on Generative AI and Computer Vision. His research focuses on diffusion models, multimodal large language models, and vision foundation models, aiming to make generative systems more controllable, interpretable, and reliable.

Fatimah Zohra

Ph.D. Student, Computer Science

vision language models Computer Vision Vision Foundation Models image and video processing

Fatimah Zohra is a Ph.D. candidate in Computer Science at King Abdullah University of Science and Technology (KAUST), advised by Prof. Bernard Ghanem, where her research focuses on fine-grained visual representation learning for vision-language and video models through sparse selection of localized features.