We propose Action-Reaction Learning as an approach for analyzing and synthesizing human behaviour. This paradigm uncovers causal mappings between past and future events or between...
Objects are usually embedded into context. Visual context has been successfully used in object detection tasks, however, it is often ignored in object tracking. We propose a metho...
Helmut Grabner, Jiri Matas, Philippe Cattin, Luc V...
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...
Many computer vision problems can be formulated in
a Bayesian framework with Markov Random Field (MRF)
or Conditional Random Field (CRF) priors. Usually, the
model assumes that ...
—Local classifiers are sometimes called lazy learners because they do not train a classifier until presented with a test sample. However, such methods are generally not complet...
Eric K. Garcia, Sergey Feldman, Maya R. Gupta, San...