Current Topics in Computer Vision and Machine Learning

Seminar Description

Computer Vision is a very active research field with many interesting applications. Many of its recent successes are due to advances in Machine Learning research. It is therefore useful to study the two fields together and to draw cross-links between them.

The conferences with the strongest impact in Computer Vision are CVPR, ICCV, and ECCV, whereas NeurIPS, ICML and ICLR have the strongest impact on the Machine Learning community. In this seminar we will discuss recent results presented at those conferences with a focus on the most interesting and innovative ideas. Participating students have the chance to get familiar with state-of-the-art solutions to problems in Computer Vision and Machine Learning and will get an insight into the involved techniques.

Each participant will work on one topic and summarize it in a seminar paper and a short presentation. The seminar papers and the presentations will be in English.

Prerequisites

The seminar is addressed at Master students of Computer Science, Media Informatics, Software Systems Engineering or Data Science in their 2nd-4th semester.

We expect students to already have substantial knowledge about Computer Vision and/or Machine Learning from successful participation in at least one of the lectures Computer Vision, Machine Learning, Computer Vision 2, Advanced Machine Learning, Pattern Recognition and Neural Networks (or comparable lectures).

See the Moodle course room for further details.