Welcome to the LIVIA-ETS Lab
We are a dynamic research group at the Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA) at École de technologie supérieure (ÉTS), Université du Québec, Montreal.
Large-scale processing, analysis and interpretation of images and videos
The unifying theme of LIVIA is the perception and modeling of dynamic environments (2D and 3D scenes, speech, etc.) using techniques in artificial intelligence. The laboratory’s scientific orientation revolves around the key foundations of large-scale processing, analysis and interpretation of images and videos.
Our research and development activities are based on six main conceptual axes:
- Machine learning
- Computer vision
- Pattern recognition
- Adaptive and intelligent systems
- Information fusion
- Optimization of complex systems
Perception and modeling of dynamic environments
The techniques developed at LIVIA are used to solve concrete and complex problems. For example, we develop convolutional neural networks to detect tumors or assess the level of depression in patients, working with massive amounts of data that typically has limited annotations.
Our main research initiatives focus on:
- Analysis of medical, satellite, and aerial images
- Biometrics: recognition of individuals from signature, face, voice, etc.
- Automatic processing of handwritten documents
- Affective computing for health monitoring
- Security and surveillance
We are looking for passionate new PhD students, Postdocs, and Master students to join the team (more info) !
News
November 2024
LIVIA presents 5 papers at ICCV 2024! Topics include point cloud adaptation, facial expression capture, few-shot learning, vision-language models, and object detection.
July 2024
🎉 LIVIA presents 7 papers at CVPR 2024! Congratulations to all collaborators! Papers cover conformal prediction, anomaly detection, test-time adaptation, point cloud processing, and more.