Idiap on LinkedIn Idiap youtube channel Idiap on Twitter Idiap on Facebook
Personal tools
You are here: Home Research Research Groups Computer Vision and Learning

Computer Vision and Learning

The goal of our group is the development of new statistical learning techniques mainly for computer vision, with a particular interest in their computational properties. Our application domains include object detection and scene analysis, tracking of people and biological structures, and image recognition in general.

Current Group Members

Current projects

DIGIT_ARENA - real-time perimeter board content digital replacement
Sport events now use dynamic advertisement by means of LED pitch perimeter boards.
IMIM - Intelligent Monitoring for In-line Manufacturing
This project aims at developing an in line, learning based quality control for laminate welding.
MASH-2 - Massive Sets of Heuristics for Machine Learning II
WILDTRACK - Tracking in the Wild

Computer Vision and Learning Group News

Idiap has a new opening for 2 PhD positions in machine learning Sep 26, 2016
The Idiap Research Institute, affiliated with École Polytechnique Fédérale de Lausanne, seeks two PhD students in machine learning to develop new techniques to speed up the training of deep architectures using importance sampling, and to learn automatically network architectures from data. The starting date is early 2017.
Idiap has a new opening for a Post-doctoral position on vision-based methods for accurate manufacturing defect detection Feb 02, 2016
The Computer Vision and Learning group at the Idiap Research Institute (http://www.idiap.ch/cvl) invites applications for a postdoctoral-position on the development of techniques for accurate defect detection in manufacturing processes.
Idiap has a new opening for a Post-doctoral position on learning invariant embeddings for face recognition Feb 02, 2016
The Computer Vision and Learning group at the Idiap Research Institute (http://www.idiap.ch/cvl) invites applications for a postdoctoral-position on the development of invariant embeddings for face recognition.

Contact

François FLEURET (EPFL Maître d'enseignement et de recherche)

Document Actions