Efficient and Understandable Neural Networks for Image and Video Analysis


Event details

Date 15.02.2024
Hour 16:0017:00
Speaker Dr. Simone Schaub-Meyer
Category Conferences - Seminars
Event Language English
Abstract: Recent developments in deep learning have led to significant advances in many areas of computer vision. However, the success of these methods often depends on having a well-defined task, corresponding training data, and measuring success by improved task-specific accuracy. However, in order to apply new methods in the real-world, other aspects become relevant as well, such as required labelled data, computational requirements, as well as, especially in safety critical scenarios, how trust-worthy a model is. In my talk, I will first discuss how motion in videos can be used to learn representations in an unsupervised way as well as methods to efficiently handle higher-resolution data. In the second part, I will show how attribution maps, which help to gain a better understanding of the predictions, can be obtained efficiently.
Speaker: Dr. Simone Schaub-Meyer, Technical University of Darmstadt & Hessian Center for Artificial Intelligence (hessian.AI)

Bio: Simone Schaub-Meyer is an independent research group leader at the Technical University of Darmstadt, as well as affiliated with the Hessian Center for Artificial Intelligence. She recently got the renowned Emmy Noether Programme (ENP) fund of the German Research Foundation (DFG) supporting her research group for the next 6 years. The focus of her research is on developing efficient, robust, and understandable methods and algorithms for image and video analysis. Before starting her own group, she was a postdoctoral researcher in the Visual Inference Lab of Prof. Stefan Roth. Prior to joining TU Darmstadt, she was a postdoctoral researcher at the Media Technology Lab at ETH Zurich working on augmented reality. She obtained her doctoral degree from ETH Zurich, advised by Prof. Dr. Markus Gross and in collaboration with Disney Research Zurich. In her thesis, awarded with the ETH Medal, she developed novel methods for motion representation and video frame interpolation.

Practical information

  • General public
  • Free


  • IVRL


  • Yufan Ren

Event broadcasted in