Date of Original Version
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June, 2008
Abstract or Table of Contents
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interactions of all unit visual features across the entire training set and we infer information, such as which fea- tures are in which categories, directly from the graph by using link analysis techniques. The link analysis techniques are based on well-established graphmining techniques used in diverse applications such as WWW, bioinformatics, and social networks. The techniques operate directly on the pat- terns of connections between features in the graph rather than on statistical properties, e.g., from clustering in feature space. We argue that the resulting techniques are simpler, and we show that they perform similarly or better compared to state of the art techniques on common data sets. We also show results on more challenging data sets than those that have been used in prior work on unsupervised modeling.