Link analysis techniques for object modeling and recognition

Abstract

This paper proposes a novel approach for unsupervised modeling and recognition of object categories 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 features are in which categories, directly from the graph by using link analysis techniques. The link analysis techniques are based on well-established graph mining techniques used in diverse applications such as WWW, bioinformatics, and social networks. The techniques operate directly on the patterns 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 both common and more challenging data sets. Also, we extend this link analysis idea to combine it with the statistical framework of topic contents. By doing so, our approach not only dramatically increases performance but also provides feasible solutions to some persistent problems of statistical topic models based on bag-of-words representation such as modeling of geometric information, computational complexity, and the inherent ambiguity of visual words. Our approach can be incorporated in any generative models, but here we consider two popular models, pLSA and LDA. Experimental results show that the topic models updated by adding link analysis terms significantly outperform the standard pLSA and LDA models. Furthermore, we presented competitive performances on unsupervised modeling, classification, and localization tasks with datasets such as MSRC and PASCAL2005.