We investigate the problem of automatically labelling
faces of characters in TV or movie material with their
names, using only weak supervision from automaticallyaligned
subtitl...
Supervised learning from multiple labeling sources is an increasingly important problem in machine learning and data mining. This paper develops a probabilistic approach to this p...
We propose a new supervised texture segmentation and classification technique based on combining features extracted from the discrete wavelet frames of an image (specifically, the...
We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several ...
In this paper we present a proposal for the development of dialog systems that, on the one hand, takes into account the benefits of using standards like VoiceXML, whilst on the ot...