Scholar
Muhammad Haris Khan
Google Scholar ID: ZgERfFwAAAAJ
Faculty at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) - UAE
Domain Generalization
Domain Adaptation
Landmark Detection
Model Calibration
Few-shot Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
4,416
H-index
23
i10-index
35
Publications
20
Co-authors
12
list available
Contact
GitHub
Open ↗
LinkedIn
Open ↗
Publications
8 items
MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
2026
Cited
0
AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis
2026
Cited
0
Balancing Multimodal Domain Generalization via Gradient Modulation and Projection
2026
Cited
0
Towards Multimodal Domain Generalization with Few Labels
2026
Cited
0
Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision
2026
Cited
0
Towards Calibrating Prompt Tuning of Vision-Language Models
2026
Cited
0
OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
2026
Cited
0
VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping
2026
Cited
0
Resume (English only)
Academic Achievements
2025: Multiple papers accepted at top-tier conferences including ICCV, ICIP, CVPR (one selected for Highlight/Spotlight), AAAI (oral), and ACM MM
2024: Best Application Paper Award at ACCV 2024 for 'NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking'
2024: Best Paper Award at DICTA 2024 for 'Matching Confidences and Softened Target Occurrences for Calibration'
2024: Best Paper Award at ML4AD workshop
2024: Published multiple papers at NeurIPS, WACV, DICTA, ACCV, Interspeech, etc.
Leading a special issue on 'Visual Domain Generalization for Real-World Applications'
Released the first and largest curated repository of resources on Video Self-Supervised Learning (VideoSSL)
Research Experience
Assistant Professor at MBZUAI, Department of Computer Vision
Organized multiple international workshops, including 'Domain Generalization: Evolution, Breakthroughs, and Future Horizons' at CVPR 2025
Organizing a special session on 'Data-efficient Vision Transformers: Challenges & Applications' at IEEE IJCNN 2025
Serving as Area Chair for WACV 2025, NeurIPS 2024, and BMVC 2024
Serving as Associate Editor for IET Computer Vision journal
Co-authors
12 total
Ling Shao, Fellow of IEEE/IAPR
Terminus; Founder of IIAI/MBZUAI
Muhammad Akhtar Munir
Mohamed bin Zayed University of Artificial Intelligence, UAE
M. Saquib Sarfraz
Mercedes-Benz / Karlsruhe Institute of Technology (KIT)
Yanwei Pang
Tianjin University
Georgios (Yorgos) Tzimiropoulos
Samsung AI Center, Cambridge | Queen Mary University of London
Muzammal Naseer
Asst. Professor, Khalifa University
Michel Valstar
Professor in Automatic Human Behaviour Understanding, University of Nottingham
Tony Pridmore
University of Nottingham
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up