Much of recent action recognition research is based on
space-time interest points extracted from video using a Bag
of Words (BOW) representation. It mainly relies on the discrimi...
Matteo Bregonzio (Queen Mary, University of London...
One-class classification naturally only provides one-class of exemplars, the target class, from which to construct the classification model. The one-class approach is constructed...
Multiple instance learning (MIL) is a branch of machine learning that attempts to learn information from bags of instances. Many real-world applications such as localized content-...
A significant fraction of Web data is available only for short periods of time. We consider methods to keep track and to record such dynamic information automatically. The main p...
Labeling text data is quite time-consuming but essential for automatic text classification. Especially, manually creating multiple labels for each document may become impractical ...