High-Level Computer Vision
Overview
This course will cover essential techniques for high-level computer vision. These techniques facilitate semantic interpretation of visual data, as it is required for a broad range of applications like robotics, driver assistance, multi-media retrieval, surveillance, etc. In this area, the recognition and detection of objects, activities, and visual categories have seen dramatic progress over the last decade. We will discuss the methods that have led to a state-of-the-art performance in this area and provide the opportunity to gather hands-on experience with these techniques.
Course Information
Semester: SS
Year: 2025
Lecture start: Wednesday April 9
Tutorial start: Monday April 14
Time:
Lecture: Wednesdays 10:00 - 12:00 (start at 10:15)
Tutorial: Mondays 10:00 - 12:00
Location: E 1.5 002
Registration:
Lecturer: Prof. Dr. Bernt Schiele
TAs: Amin Parchami-Araghi
Office Hour: Tuesday 10:00 AM - 11:00 AM, E1.4 629
Contacting TAs:
Literature:
- "Computer Vision: Algorithms and Applications" by Richard Szeliski (in particular chapter on image formation)
- Mikolajcyk, Schmid: A Performance Evaluation of Local Descriptors, TPAMI, 2005
- Boiman, Shechtman, Irani: A Performance Evaluation of Local Descriptors, CVPR, 2008
- Gehler, Nowozin: On feature combination for multi class object classification, ICCV, 2009
- Krizhevsky, Sutskever, Hinton: ImageNet Classification with Deep Convolutional Networks, NIPS, 2012
- "Pattern recognition and machine learning" by Christopher M. Bishop
- "Computer vision" by David A. Forsyth and Jean Ponce