Safa Messaoud
Scholar

Safa Messaoud

Google Scholar ID: M2wXrP4AAAAJ
Scientist, Qatar Computing Research Institute (QCRI)
Safe AIEnergy Based ModelsReinforcement LearningComputer VisionHealth intelligence
Citations & Impact
All-time
Citations
166
 
H-index
7
 
i10-index
6
 
Publications
20
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • - Thesis: Toward More Scalable Structured Models
  • - Paper: Max-Sliced Score Matching
  • - Paper: Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning? - Oral Presentation at CVPR 2020, WiCV Workshop 2020, and Deep Vision Workshop 2020
  • - Paper: DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization - Accepted at SIGIR 2021 and Oral Presentation at DRL4IR Workshop (SIGIR) 2021
  • - Paper: Structural Consistency and Controllability for Diverse Colorization - ECCV 2018, WiML Workshop at NeurIPS 2017
  • - Patent: Medical record problem list generation
  • - Research: Reaction–diffusion modelling for microphysiometry on cellular specimens
  • - Patent: Accelerating genomic data parsing on field programmable gate arrays
  • - Paper: Translating Discrete Time SIMULINK to SIGNAL
  • - Thesis: Optimal Architecture Synthesis for Aircraft Electrical Power Systems
Research Experience
  • - Scientist at Qatar Computing Research Institute (QCRI)
  • - Gave a talk at MLDAS symposium organized by Boeing and QCRI at MIT
  • - Served as a senior program committee member for AAAI 23
  • - Served as a reviewer for the Gaze Meets ML workshop @ NeurIPS 22
Education
  • - Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign, advised by Prof. Alexander Schwing
  • - Master's degree in Computer Engineering from Virginia Polytechnic and State University, advised by Prof. Sandeep Shukla
  • - Bachelor and Master's degrees in Electrical Engineering and Information Technology from the Technical University of Munich
  • - Visiting scholar at UC Berkeley, supervised by Prof. Alberto Sangiovanni Vincentelli and Prof. Andreas Herkersdorf
Background
  • Research interests: safe reinforcement learning and structure prediction algorithms, motivated by applications in computer vision and health intelligence.
Miscellany
  • Personal interests not mentioned
Co-authors
0 total
Co-authors: 0 (list not available)