—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting ...
We design and analyze interacting online algorithms for multitask classification that perform better than independent learners whenever the tasks are related in a certain sense. W...
In this paper we propose a Gaussian-kernel-based online kernel density estimation which can be used for applications of online probability density estimation and online learning. ...
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
We describe a generative model of the relationship between two images. The model is defined as a factored threeway Boltzmann machine, in which hidden variables collaborate to de...
Joshua Susskind, Roland Memisevic, Geoffrey Hinton...