BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:CMIH Hub seminar series
SUMMARY:Multi-modal Image Processing: Data Models\, Algori
 thms\, and Applications - Miguel Rodrigues\, UCL 
DTSTART;TZID=Europe/London:20180525T130000
DTEND;TZID=Europe/London:20180525T140000
UID:TALK105652AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/105652
DESCRIPTION:Many real-world data processing problems often inv
 olve heterogeneous images associated with differen
 t imaging modalities. These images are often assoc
 iated with the same phenomenon – sharing common at
 tributes – so it is of interest to devise new mech
 anisms that can effectively leverage the availabil
 ity of such multi-modal data in a number of data p
 rocessing tasks.\n\n \n\nThis talk proposes a mult
 i-modal image processing framework based on joint 
 sparse representations induced by coupled dictiona
 ry learning. In particular\, our framework can cap
 ture favorable structure similarities across diffe
 rent image modalities such as edges\, corners\, an
 d other elementary primitives in a learned sparse 
 transform domain\, instead of the original pixel d
 omain\, allowing us to develop new multimodal imag
 e processing algorithms for a number of tasks.\n\n
  \n\nPractical experiments with imaging data relat
 ed to a number of applications – ranging from medi
 cal imaging\, art investigation\, and more – demon
 strate that our framework can lead to notable bene
 fits in relation to other state-of-the-art approac
 hes\, including deep learning algorithms.\n\n \n\n
 This talk summarizes joint work with various colla
 borators including Ingrid Daubechies (Duke U)\, Yo
 nina Eldar (Technion)\, Lior Weizmann (Technion)\,
  Nikos Deligiannis (VUB)\, Bruno Cornellis (VUB)\,
  Pingfan Song (UCL)\, Joao Mota (Heriot Watt U)\, 
 Pier Luigi Dragotti (Imperial College London)\, Xi
 n Deng (Imperial College London)
LOCATION:MR5\, Centre for Mathematical Sciences
CONTACT:Rachel Furner
END:VEVENT
END:VCALENDAR