BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IEM Seminar series: Responsibility by design in audio-visual machi
 ne perception
DTSTART:20220523T150000
DTEND:20220523T160000
DTSTAMP:20260916T055404Z
UID:333395359e58211ef4fe9b3929f34c8cabf81b28709ea1e1a5e636ff
CATEGORIES:Conferences - Seminars
DESCRIPTION:Andrea Cavallaro\, The Alan Turing Institute\, UK\nAbstract: M
 achine perception models designed for human facing applications are natura
 l interfaces between the physical and the digital world. These models are 
 transforming the ability of autonomous systems to see\, hear and confident
 ly act in a wide range of scenarios. However\, the issue of trust is a key
  challenge for the widespread acceptance of these models\, as they capture
  behaviours that reveal personal information. In this talk I will focus on
  how we guide machine learning models to learn to serve consensual purpose
 s in human facing applications. I will discuss how we train these models t
 o extract features that are effective for target tasks and prevent unwante
 d downstream inferences. I will also discuss our recent work that protects
  selected information by appropriately crafting data perturbations that en
 able maintaining and even improving sound and image quality.\n\nBio: Andre
 a Cavallaro is Turing Fellow at The Alan Turing Institute\, the UK Nationa
 l Institute for Data Science and Artificial Intelligence\, and Full Profes
 sor at Queen Mary University of London\, a Russell Group university. He is
  the founding Director of the Centre for Intelligent Sensing and the Direc
 tor of Research of the School of Electronic Engineering and Computer Scien
 ce. He is a Fellow of the International Association for Pattern Recognitio
 n for “contributions to image processing and multi-sensor scene understa
 nding\,” and a Fellow of the Higher Education Academy. He serves as Edit
 or-in-Chief of Signal Processing: Image Communication\, as Senior Area Edi
 tor for the IEEE Transactions on Image Processing\, as member of the IEEE 
 Video Signal Processing and Communication Technical Committee and as membe
 r of the Technical Directions Board of the IEEE Signal Processing Society.
 \n\nProfessor Cavallaro received his Ph.D. in Electrical Engineering from 
 the École polytechnique fédérale de Lausanne (EPFL). He was a Research 
 Fellow with British Telecommunications (BT) and was awarded the Royal Acad
 emy of Engineering Teaching Prize\; three student paper awards on target t
 racking and perceptually sensitive coding at IEEE ICASSP in 2005\, 2007 an
 d 2009\; and the best paper award at IEEE AVSS 2009. He was selected as IE
 EE Signal Processing Society Distinguished Lecturer (2020-2021) and is the
  past Chair of the IEEE Image\, Video\, and Multidimensional Signal Proces
 sing Technical Committee (2020-2021). He also served as elected member of 
 the IEEE Multimedia Signal Processing Technical Committee and chair of the
  Awards committee of the IEEE Signal Processing Society\, Image\, Video\, 
 and Multidimensional Signal Processing Technical Committee.\n 
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202 https://epfl.zoom.u
 s/j/68411626701
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR