Muhammad Haris Khan
Associate Professor of Computer Vision
Mohamed bin Zayed University of Artificial Intelligence · Abu Dhabi, UAE
I build safe, reliable, and scalable AI systems — spanning visual robustness across distribution shifts, trustworthy prediction through calibration, label-efficient learning, and AI for societal good in healthcare and climate resilience.
8,500+
Citations
$1M+
Research funding as PI
4
Granted US patents
40+
PhD, MSc & RA mentees
LATEST
News
Apr 2026
3 papers at ACL 2026 — GCA Framework for climate intelligence in main conference, 2 in Findings.
Mar 2026
6 papers at CVPR 2026, two selected for Highlight presentations. Domain Generalization Workshop (2nd edition) organized.
Jun 2025
2 papers at ICCV 2025. Organizing the 1st Multimodal Sign Language Recognition Workshop at ICCV 2025.
May 2025
First PhD student graduates — now Lecturer at Alexandria University. One CVPR 2025 paper selected for Highlight.
Mar 2025
Best Paper at ML4AD Workshop, AAAI 2025. 4 papers at CVPR 2025. 2nd Deepfakes Detection Challenge launched at ACM MM 2025.
Nov 2024
Best Paper at DICTA 2024. Best Application Paper (Honorable Mention) at ACCV 2024 for NT-VOT211.
Apr 2024
Spotlight paper at CVPR 2024 for Unsupervised Landmark Discovery. 4 total papers at CVPR 2024.
FOCUS AREAS
Research Themes
🎯 Visual Robustness & Generalization
Vision systems that generalize reliably across unseen domains — domain generalization for detection, segmentation, and multimodal tasks under real-world distribution shifts.
⚖️
Reliable & Trustworthy Prediction
Model calibration, uncertainty estimation, and confidence-aware inference for safe AI deployment — calibrated detection and vision-language model alignment.
⚡
Label-Efficient & Scalable Learning
Few-shot, semi-supervised, and unsupervised methods — unsupervised landmark discovery, few-shot segmentation, and video self-supervised learning.
🌍
AI for Societal Good
Applications in healthcare (diabetic retinopathy, medical imaging), climate resilience, sustainability, and sign language recognition.
Reliable & Trustworthy Models
A-TPT: Angular Diversity Calibration for Test-Time Prompt Tuning of Vision-Language Models
S.A. Ahamed, U.S. Thanthrige, R. Rodrigo, M.H. Khan
ICLR 2026
Cal-DETR: Calibrated Detection Transformer
M.A. Munir, S. Khan, M.H. Khan, M. Ali, F.S. Khan
NeurIPS 2023
Visual Robustness & Generalization
OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP
D. Gupta, M. Singha, S.B. Rongali, A. Jha, M.H. Khan, B. Banerjee
CVPR 2025
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
M.S. Danish, M.H. Khan, M.A. Munir, M.S. Sarfraz, M. Ali
CVPR 2024
Label-Efficient & Scalable Learning
Unsupervised Discovery of Facial Landmarks and Head Pose
S. Tourani, S. Tourani, A. Mahmood, M.H. Khan
CVPR 2025
MSI: Maximize Support-Set Information for Few-Shot Segmentation
S. Moon, S.S. Sohn, H. Zhou, S. Yoon, V. Pavlovic, M.H. Khan, M. Kapadia
ICCV 2023
AI for Societal Good
GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support
M.U. Sheikh, K. Shehzad, S. Khan, F.S. Khan, M.H. Khan
ACL 2026
NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
Y. Liu, A. Mahmood, M.H. Khan
ACCV 2024
Transformers in Medical Imaging: A Survey
F. Shamshad, S. Khan, S.W. Zamir, M.H. Khan, M. Hayat, F.S. Khan, H. Fu
Medical Image Analysis, 2023
EDUCATION
Teaching
AI7102
Introduction to Deep Learning
Fall 2025 · 137 students
4.42 / 5
AI702
Deep Learning
Spring 2025 · 49 students
4.70 / 5
AI701
Foundations of Artificial Intelligence
Fall 2024 · 127 students
4.64 / 5
AI702
Deep Learning
Spring 2024 · 49 students
4.80 / 5
AI701
Foundations of Artificial Intelligence
Fall 2023 · 113 students
4.70 / 5
AI701
Foundations of Artificial Intelligence
Fall 2022 · 118 students
4.30 / 5
COMMUNITY
Service
Area Chair
CVPR
2024–2026
ICLR
2026
NeurIPS
2024–2025
ICML
2025–2026
AAAI
2027
WACV
2024–2027
BMVC
2024–2025
AAAI Senior PC
2026
Editorial
Lead Guest Editor, IJCV — Domain Generalization
Associate Editor, IET Computer Vision
Special Issue Co-chair, IJCNN
2025
Workshops & Challenges
Mechanistic Interpretability for Medical Foundation Models, MICCAI
2026
Explainable Deepfake Detection Challenge, ACM MM Grand Challenge
2026
Domain Generalization Workshop, CVPR
2025 & 2026
Sign Language Recognition Workshop, ICCV
2025
Deepfake Detection Challenge, ACM MM
2025
FAME Challenge, ACM MM
2024
Vision Transformers Workshop, ACCV
2022
Conference Leadership
Technical Program Chair, ACM MM Asia
2026
Bid Winner, ACM MM Asia 2028 — Abu Dhabi
Trustworthy Agentic AI Symposium
2026
Outstanding Reviewer, CVPR
2021 & 2023
RECOGNITION
Awards & Honours
Research & Publication Awards
Best Paper, MONTI Workshop, CVPR
2026
Best Paper, ML4AD Workshop, AAAI
2025
Best Paper, DICTA
2024
Best Application Paper (Honorable Mention), ACCV
2024
Spotlight, ICCV
2017
Spotlight / Highlight, CVPR
2024, 2025, 2026
Oral, WACV
2025, 2026
Oral, AAAI
2026
Oral, ACCV
2022, 2024
Oral, BMVC
2023
Best Workshop Paper, BMVC
2013
Best Paper, FIT Conference
2009
Community & Service Recognition
Outstanding Reviewer, CVPR
2021 & 2023
"Exceeds Expectations" — Teaching, MBZUAI
2024
"Exceeds Expectations" — Service, MBZUAI
2022
Departmental Service Honorarium (×2), COMSATS
2008–2009
Academic & Doctoral Honours
Research Excellence Scholarship, University of Nottingham
2011
MSc passed with Distinction, University of Sussex
2008
Bronze Medal — 3rd position, BSc Computer Science, COMSATS
2006
Let's connect
Contact
Get in touch
Open to research collaborations, PhD and postdoc inquiries, and academic partnerships.
↗
↗
Location
Mohamed bin Zayed University of Artificial Intelligence
Computing and Mathematical Sciences (CMS) Division
Building 1B, Masdar City
Abu Dhabi, UAE