BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Video Super-Resolution with Convolutional Neural Networks
DTSTART:20160826T100000
DTEND:20160826T120000
DTSTAMP:20260410T111508Z
UID:9713b1c4fb176b22c293c3d244e85f7aae286f8423d18c69360c1e33
CATEGORIES:Conferences - Seminars
DESCRIPTION:Ruofan Zhou\nEDIC Candidacy Exam\nExam President: Prof. Pascal
  Fua\nThesis Director: Prof. Sabine Süsstrunk\nCo-examiner: Prof. Wenzel 
 Jakob\nBackground PapersLarge-scale Video Classification with Convolutiona
 l Neural Networks by Andrej Karpathy\, George Toderici\, Sanketh Shetty\, 
 Thomas Leung\, Rahul Sukthankar\, Li Fei-FeiLearning a Deep Convolutional 
 Network for Image Super-Resolution by Chao Dong\, Chen Change Loy\, Kaimin
 g He\, Xiaoou TangOn Bayesian Adaptive Video Super Resolution by Ce Liu\, 
 Deqing SunAbstract\;\nSuper resolving real-world video sequences remains t
 o be a challenging research task in computer vision field. While nowadays 
 convolutional neural networks have achieved state-of-the-art performance o
 n many vision tasks. In this proposal\, we discuss three existing works on
  super-resolution task or CNN architecture that inspire us on applying CNN
  on video super-resolution task. The first paper has proposed a Bayesian-b
 ased model for video super-resolution task that estimate motion\, blur ker
 nel and noise level simultaneously to adapt to a variety of noise levels a
 nd blur kernels. Using different convolutional neural networks\, the later
  two papers achieve promising results on single-image super resolution and
  video classification respectively.\nBased on the key ideas from these thr
 ee papers\, we propose our research plan to design a CNN architecture for 
 video super-resolution.
LOCATION:BC 329 https://plan.epfl.ch/?room==BC%20329
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR