Scholar
Hayat Ullah
Google Scholar ID: xnXPj0UAAAAJ
PhD Candidate @ Florida Atlantic University
Citations & Impact
Citations
677
H-index
12
i10-index
12
Publications
20
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition' accepted for publication in IEEE Transactions on Circuits and Systems for Video Technology; published a white paper in collaboration with NVIDIA's Sustainable Computing Library; serving as a reviewer for AAAI 2026; successfully passed Ph.D. Candidacy Exam.
Research Experience
- Graduate Research Assistant at Intelligent Systems, Computer Architecture, Analytics and Security Laboratory (ISCAAS LAB), Florida Atlantic University; Graduate Research Assistant at Kansas State University (January 2022 - July 2024); Full-time Researcher at Sejong University (February 2021 - December 2021); Machine Learning Engineer (Intern) at NINE VR (July 2020 - December 2020); Graduate Research Assistant at Sejong University (March 2019 - January 2021).
Education
- Pursuing a PhD degree in Computer Science (major in Computer Vision) at Florida Atlantic University under the supervision of Prof. Arslan Munir; completed Master’s degree in 2021 at Sejong University, South Korea.
Background
- PhD candidate in Computer Science (major in Computer Vision); primary research focuses on multimodal-driven video analytics, including action and activity recognition, temporal action localization, and spatio-temporal action detection in videos; specializes in pretraining, fine-tuning, and zero-shot evaluation of vision-language models (VLMs) for complex video understanding tasks; expertise also extends to knowledge distillation, enhancing adversarial robustness, and scaling deep learning models through distributed training.
