We study the problem of classifying images into a given, pre-determined taxonomy. The task can be elegantly translated into the structured learning framework. Structured learning, ...
We propose a new transductive learning algorithm for learning optimal linear representations that utilizes unlabeled data. We pose the problem of learning linear representations a...
Psychophysical studies have shown that humans actively exploit temporal information such as contiguity of images in object recognition. We have recently developed a recognition sy...
Arnulf B. A. Graf, Christian Wallraven, Heinrich H...
We empirically study the relationship between supervised and multiple instance (MI) learning. Algorithms to learn various concepts have been adapted to the MI representation. Howe...
The detection of people is one of the foremost problems for indexing, browsing and retrieval of video. The main difficulty is the large appearance variations caused by action, clot...