In this paper, we exploit the problem of inferring images’ semantic concepts from community-contributed images and their associated noisy tags. To infer the concepts more accura...
The paper is concerned with two-class active learning. While the common approach for collecting data in active learning is to select samples close to the classification boundary,...
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
Typical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-...
Doris Baum, Daniel Schneider, Rolf Bardeli, Jochen...
Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...