[image 01719] 講演会のお知らせ:R.Cipolla教授(英国ケンブリッジ大学)

Jun Sato junsato @ nitech.ac.jp
2016年 3月 25日 (金) 09:57:49 JST


Image-MLの皆様:

ケンブリッジ大学のR. Cipolla教授の講演会が近づきましたので、
案内を再送させていただきます。是非、多数ご参加ください。

詳しくは、以下をご覧ください。
http://www.cv.nitech.ac.jp/event/2015/2016_3_28_lecture/講演会案内.pdf

名古屋工業大学 佐藤 淳

------------------------------
名古屋工業大学 情報科学フロンティア研究院 特別講演会
日時:3月28日(月)14:00-16:00
場所:名古屋工業大学 4号館1階 大ホール
主催・共催:
 名古屋工業大学 情報科学フロンティア研究院
 名古屋工業大学 グローバル共生情報研究センター

Title: 
   Computer Vision: Geometry, Uncertainty and Machine Learning

Speaker:
   Prof. Roberto Cipolla
   University of Cambridge
   http://mi.eng.cam.ac.uk/~cipolla/

Abstract: 
   The last decade has seen a revolution in the theory and application of computer vision and machine learning. I will begin with a brief review of some of the fundamentals with a few examples from my own research group (3R’s of computer vision - Reconstruction, Registration and Recognition - see research videos at http://mi.eng.cam.ac.uk/~cipolla/archive.htm).
   I will then introduce some recent results from two real-time deep learning systems that exploit geometry and compute model uncertainty. 
   The first, SegNet, is a deep convolutional network architecture designed to map input RGB images to pixel labels for scene understanding. It is composed of an encoder network and a decoder network which ends with a softmax classifier. The entire architecture can be trained end-to-end using stochastic gradient descent. SegNet can produce dense pixel-wise class labels in real-time with a measure of model uncertainty. See demo and code – http://mi.eng.cam.ac.uk/projects/segnet/
   Secondly, PoseNet is a real-time relocalisation system.  Deep networks are trained to regress the camera's 3D position and orientation from a single image. The algorithm can operate over large scale indoor and outdoor areas in real time. See demo and code - http://mi.eng.cam.ac.uk/projects/relocalisation/




image メーリングリストの案内