The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
The use of video and audio features for automated annotation of audio-visual data is becoming widespread. A major limitation of many of the current methods is that the stored inde...
Kieron Messer, Josef Kittler, Barbara Levienaise-O...
This research explores the idea of inducing domain-specific semantic class taggers using only a domain-specific text collection and seed words. The learning process begins by indu...
In the standard formalization of supervised learning problems, a datum is represented as a vector of features without prior knowledge about relationships among features. However, ...
Abstract. Time modeling is a crucial feature in many application domains. However, temporal information often is not crisp, but is uncertain, subjective and vague. This is particul...