Fatimah Zohra
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.
Biography
Fatimah Zohra is a Ph.D. candidate in Computer Science at King Abdullah University of Science and Technology (KAUST), where she works in the Image and Video Understanding Lab (IVUL) under the supervision of Prof. Bernard Ghanem. Before her Ph.D., she was a Computer Scientist at Adobe working on a large-scale distributed platform. She received her M.S. in Computer Science from KAUST and her B.S. in Computer Science from The University of Texas at Austin.
Expertise and Interests
Fatimah's research focuses on fine-grained representation learning for vision-language and video models. She developed β-CLIP (CVPR 2026), which achieves state-of-the-art fine-grained vision-language alignment among methods trained without hard negatives, and HyperGS, a feedforward Gaussian video representation that encodes orders of magnitude faster than prior methods.
Education
- Bachelor of Science (B.S.)
- Computer Science, The University of Texas at Austin (UT Austin), United States, 2015
- Master of Science (M.S.)
- Computer Science, King Abdullah University of Science and Technology (KAUST), Saudi Arabia, 2021
