Sciweavers

90 search results - page 18 / 18
» On the Set of Images Modulo Viewpoint and Contrast Changes
Sort
View
CORR
2010
Springer
121views Education» more  CORR 2010»
13 years 14 days ago
Deep Self-Taught Learning for Handwritten Character Recognition
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...
Frédéric Bastien, Yoshua Bengio, Arn...
3DIM
2003
IEEE
13 years 9 months ago
Approximate K-D Tree Search for Efficient ICP
A method is presented that uses an Approximate Nearest Neighbor method for determining correspondences within the Iterative Closest Point Algorithm. The method is based upon the k...
Michael A. Greenspan, Mike Yurick
ERCIMDL
2007
Springer
159views Education» more  ERCIMDL 2007»
13 years 11 months ago
Reducing Costs for Digitising Early Music with Dynamic Adaptation
Abstract. Optical music recognition (OMR) enables librarians to digitise early music sources on a large scale. The cost of expert human labour to correct automatic recognition erro...
Laurent Pugin, John Ashley Burgoyne, Ichiro Fujina...
PR
2008
328views more  PR 2008»
13 years 5 months ago
Activity based surveillance video content modelling
This paper tackles the problem of surveillance video content modelling. Given a set of surveillance videos, the aims of our work are twofold: firstly a continuous video is segment...
Tao Xiang, Shaogang Gong
TVCG
2010
165views more  TVCG 2010»
13 years 3 months ago
A Visual Backchannel for Large-Scale Events
—We introduce the concept of a Visual Backchannel as a novel way of following and exploring online conversations about large-scale events. Microblogging communities, such as Twit...
Marian Dörk, Daniel M. Gruen, Carey Williamso...