Full Professor · LIVIA
Eric Granger
Full Professor, Department of Systems Engineering, ÉTS Montréal
Researching computer vision
Building computer-vision and machine-learning systems that are accurate, adaptive and trustworthy, for healthcare, biometrics, surveillance and intelligent embedded systems.
0
Journal papers
0
Conference papers
0
Doctoral theses supervised
0
Book chapters
Computer VisionDeep LearningPattern RecognitionFace RecognitionBiometricsDomain AdaptationTransfer LearningMedical ImagingAffective ComputingMultimodal FusionVideo SurveillanceWeakly-Supervised LearningEmbedded Neural Networks
Computer VisionDeep LearningPattern RecognitionFace RecognitionBiometricsDomain AdaptationTransfer LearningMedical ImagingAffective ComputingMultimodal FusionVideo SurveillanceWeakly-Supervised LearningEmbedded Neural Networks
About
Bridging vision, learning & real-world impact
Eric Granger is a Full Professor in the Department of Systems Engineering at the École de technologie supérieure (ÉTS), Université du Québec, where he works within LIVIA, the Laboratory of Imaging, Vision and Artificial Intelligence. His research develops machine-learning and deep-learning models for computer vision and pattern recognition, with a focus on systems that remain reliable when deployed in the messy conditions of the real world.
A recurring theme of his work is learning from data with limited annotations, through domain adaptation, transfer learning, weak supervision and multimodal information fusion, applied to high-stakes domains such as medical imaging, biometric authentication, video surveillance and affective computing for health. He holds a B.Sc.A. from UQAM and an M.Sc.A. and Ph.D. from Polytechnique Montréal, and has supervised 30+ doctoral theses alongside numerous master's projects.
He leads and contributes to several research chairs and institutes spanning embedded AI for connected buildings, digital health, and international learning-systems research.
Research interests
What Eric works on
◉
Computer Vision & Pattern Recognition
Recognition, detection and analysis in images and video, including facial analysis.
◈
Deep & Machine Learning
Deep neural networks and adaptive classification frameworks for real-world data.
◆
Face Recognition & Biometrics
Video-based identification and biometric authentication systems.
❖
Domain Adaptation & Transfer Learning
Models that generalize and personalize across users and shifting conditions.
♥
Medical Imaging & Affective Computing
Health technologies, emotion recognition and computer-assisted diagnosis.
⬡
Multimodal Fusion & Surveillance
Combining vision, audio and signals; intelligent video-surveillance systems.
Leadership & affiliations
Roles & research chairs
★
LIVIA
Full Professor in the Laboratory of Imaging, Vision and Artificial Intelligence at ÉTS.
⚙
Distech Controls Research Chair
Embedded Neural Networks for Connected Building Control.
⚕
FRQS co-Chair, AI & Digital Health
Advancing artificial intelligence for health technologies.
☷
ILLS & itechsanté
Member of the International Laboratory on Learning Systems (CNRS-FRQ) and the Research Institute for Innovation in Health Technologies.
Selected work
Recent datasets & benchmarks
Education
Academic background
- Ph.D., EngineeringPolytechnique Montréal
- M.Sc.A.Polytechnique Montréal
- B.Sc.A.Université du Québec à Montréal (UQAM)
Contact
Get in touch
✉
🏢
Office
F-5088 · 1100 Notre-Dame St W, Montréal, QC H3C 1K3