Link analysis techniques for object modeling and recognition

Gunhee Kim
master's thesis, tech. report CMU-RI-TR-08-14, Robotics Institute, Carnegie Mellon University, May, 2008

  • Adobe portable document format (pdf) (2MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

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.

Computer Vision, Data Mining


Text Reference
Gunhee Kim, "Link analysis techniques for object modeling and recognition," master's thesis, tech. report CMU-RI-TR-08-14, Robotics Institute, Carnegie Mellon University, May, 2008

BibTeX Reference
   author = "Gunhee Kim",
   title = "Link analysis techniques for object modeling and recognition",
   booktitle = "",
   school = "Robotics Institute, Carnegie Mellon University",
   month = "May",
   year = "2008",
   number= "CMU-RI-TR-08-14",
   address= "Pittsburgh, PA",