BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Graph Matching for Visual Correspondence
DTSTART:20081201T161500
DTSTAMP:20260406T172820Z
UID:a3857840dab8537d5055372ce55155e874fe2559aaabcc6d3f167bfe
CATEGORIES:Conferences - Seminars
DESCRIPTION: Dr. Lorenzo Torresani\, Microsoft Research Cambridge\, UK\nIn
  this talk I will present a novel energy minimization approach to the prob
 lem of establishing correspondences between sparse image features related 
 by an unknown non-rigid mapping and corrupted by clutter and occlusion. I 
 will describe a correspondence objective formulated as a function of the a
 ppearance and the spatial arrangement of the features. Optimization of thi
 s energy is an instance of graph matching\, which is in general a NP-hard 
 problem. I will present a novel graph matching optimization technique base
 d on the dual decomposition approach. In our evaluation this method outper
 forms existing graph matching techniques and in the majority of our exampl
 es is able to find the global minimum of our objective within a minute.\n\
 nThis talk reports on joint work with Vladimir Kolmogorov and Carsten Roth
 er.\n\nBio:\nLorenzo Torresani is a Post Doc Researcher at Microsoft Resea
 rch Cambridge. He received a Laurea Degree in Computer Science with summa 
 cum laude honors from the University of Milan (Italy) in 1996\, and an M.S
 . and a Ph.D. in Computer Science from Stanford University in 2001 and 200
 5\, respectively. He worked at Riya\, Inc.\, at the Courant Institute of N
 ew York University\, and at Digital Persona\, Inc. His research interests 
 are in computer vision\, machine learning\, and computer animation. He was
  the recipient of the Best Student Paper Prize at the IEEE Conference on C
 omputer Vision and Pattern Recognition 2001. In January 2009\, he will joi
 n the Computer Science Department at Dartmouth College as an assistant pro
 fessor.\n\nL. Torresani's homepage
LOCATION:INM202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR