BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Topologically Better Delineation of Curvilinear Structures
DTSTART:20191010T140000
DTEND:20191010T160000
DTSTAMP:20260428T102253Z
UID:0c35d4a762595b4d479322cd21d5b9c2a851dd5910e00a299fa1da50
CATEGORIES:Conferences - Seminars
DESCRIPTION:Doruk Oner\nEDIC candidacy exam\nExam president: Prof. Bertran
 d Merminod\nThesis advisor: Prof. Pascal Fua\nCo-examiner: Dr. Graham Knot
 t\n\nAbstract\nDelineation of curvilinear structures is a popular directio
 n of research in computer vision since such structures are used in many re
 al world problems like biomedical image analysis. The idea is to find cent
 erlines of the desired structures in a given image while preserving the ov
 erall topology of the structure. In this proposal\, we analyzed three work
 s that are related to this problem. We presented the problems they solved\
 , the methods they used\, results of the works and how we can integrate th
 ese work to our research. The first paper focuses on an end-to-end 3D conv
 olutional network to produce individual segments. The second paper is a su
 rvey paper on deformable models\, their extensions and applications. The t
 hird paper is on a new method on unsupervised reconstruction of 3D point c
 louds. Finally\, we talked about our current research\, and future plans a
 nd discussed how to use these papers to improve our research to obtain top
 ologically better capture of curvilinear structures.\n\nBackground papers\
 nUnsupervised Domain Adaptation by Backpropagation\, by Yaroslav Ganin and
  Victor Lempitsky\,  ICML 2015.\nNetwork Snakes: Graph-Based Object Delin
 eation with Active Contour Models\, by Matthias Butenuth and Christian Hei
 pke\, Machine Vision and Applications 2012.\nMaximin Affinity Learning of 
 Image Segmentation\, by Srinivas C. Turaga\, Kevin L. Briggman\, Moritz He
 lmstaedter\, Winfried Denk and H. Sebastian Seung\, NIPS 2009.\n\n 
LOCATION:INF 211 https://plan.epfl.ch/?room==INF%20211
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR