Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...
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...
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...
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...
—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...