Current Topics in Computer Vision and Machine Learning
|4 ECTS credits|
Find a list of current courses on the Teaching page.
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 NIPS and ICML 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.
Successful participants will be awarded 4 ECTS credits.
Master students: Bachelor degree Attendance of the lectures Computer Vision, Machine Learning, or Pattern Recognition and Neural Networks, or evidence of equivalent knowledge.
- Ethical Guidelines for the Authoring of Academic Work in German and English
- Declaration of Compliance in German and English
- LaTeX for the report (mandatory!): Template
- Slide template (optional): PPT, Keynote, LaTeX
We will announce the precise dates soon
- Introductory Meeting: 17.04.2018 16:30-17:30 - mandatory for all participants - Slides
- Outline due: 14.05.2018 23:59
- Report due: 11.06.2018 23:59
- Slides due: 16.07.2018 23:59
- Presentations: 01.08.2018 - 03.08.2018 - Please hand in your corrected report at this date!
For all questions concerning the seminar, please contact
UMIC Research Centre
Mies-van-der-Rohe-Strasse 15, Room 129
|Introductory Meeting||Mandatory for everyone. The different seminar topics will be presented in this meeting.|
|Presentation Day 1 Morning||Mandatory for everyone. 9:00 – 10:00 FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks 10:00 – 11:00 Dynamic Routing Between Capsules 11:00 – 12:00 Forecasting Human Dynamics from Static Images|
|Presentation Day 1 Afternoon||13:00 – 14:00 Deformable GANs for Pose-based Human Image Generation 14:00 – 15:00 Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints 15:00 – 16:00 Zero-Shot Detection|
|Presentation Day 2 Morning||9:00 – 10:00 MobileNetV2: Inverted Residuals and Linear Bottlenecks 10:00 – 11:00 Instance Embedding Transfer to Unsupervised Video Object Segmentation, 11:00 – 12:00 Coherent Online Video Style Transfer|
|Presentation Day 2 Afternoon||13:00 – 14:00 Tracking by Prediction: A Deep Generative Model for Multi-Person localization and Tracking 14:00 – 15:00 Hybrid computing using a neural network with dynamic external memory 15:00 – 16:00 Learning to Navigate in Cities Without a Map|