BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Efficient and Understandable Neural Networks for Image and Video A
 nalysis
DTSTART:20240215T160000
DTEND:20240215T170000
DTSTAMP:20260509T055354Z
UID:9adc862a14862f71af289ec23222b6039fe66ea163fa07b0b7f7ce9a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Simone Schaub-Meyer\nAbstract: Recent developments in dee
 p learning have led to significant advances in many areas of computer visi
 on. However\, the success of these methods often depends on having a well-
 defined task\, corresponding training data\, and measuring success by imp
 roved task-specific accuracy. However\, in order to apply new methods in t
 he real-world\, other aspects become relevant as well\, such as required l
 abelled data\, computational requirements\, as well as\, especially in saf
 ety 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-resol
 ution data. In the second part\, I will show how attribution maps\, whic
 h help to gain a better understanding of the predictions\, can be obtaine
 d efficiently.\n \nSpeaker: Dr. Simone Schaub-Meyer\, Technical Universit
 y of Darmstadt & Hessian Center for Artificial Intelligence (hessian.AI)\
 n\nBio: Simone Schaub-Meyer is an independent research group leader at the
  Technical University of Darmstadt\, as well as affiliated with the Hessia
 n Center for Artificial Intelligence. She recently got the renowned Emmy N
 oether Programme (ENP) fund of the German Research Foundation (DFG) suppor
 ting her research group for the next 6 years. The focus of her research is
  on developing efficient\, robust\, and understandable methods and algorit
 hms 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 obta
 ined her doctoral degree from ETH Zurich\, advised by Prof. Dr. Markus Gro
 ss and in collaboration with Disney Research Zurich. In her thesis\, award
 ed with the ETH Medal\, she developed novel methods for motion representat
 ion and video frame interpolation.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR