BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learning Transformations for Exemplar Based Matching
DTSTART:20190617T093000
DTEND:20190617T113000
DTSTAMP:20260501T101101Z
UID:354671c661d05e64b9e3923e4f1ae5b2f82c4fe0422f34c62dae72d9
CATEGORIES:Conferences - Seminars
DESCRIPTION:Vidit Vidit\nEDIC candidacy exam\nExam president: Prof. Pierre
  Dillenbourg\nThesis advisor: Prof. Pascal Fua\nThesis co-advisor: Dr. Mat
 hieu Salzman\nCo-examiner: Prof. Ronan Boulic\n\nAbstract\nIn computer vis
 ion\, finding similarity between two images is useful for several tasks li
 ke\, object detection and segmentation\, tracking\, image retrieval\, imag
 e registration\, etc. The task in exemplar based matching is to find regio
 ns in two images\, similar to one presented by the exemplar. This relative
 ly easy sounding task has been one of the challenges in the field.\n\nThe 
 difficulty arises from the fact that exemplar can undergo several geometri
 c and photo-metric transformations\, which makes it visually quite differe
 nt in appearance to the image where the match is to be made. Several appro
 aches have tried to formulate such transformations upto a certain limit. T
 his research proposal is aimed at mitigating challenges faced in previous 
 works with the help of modern machine learning methods.\n\nBackground pape
 rs
LOCATION:BC 329 https://plan.epfl.ch/?room==BC%20329
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR