Now showing items 1-4 of 4

    • Alignment of uncalibrated images for multi-view classification 

      Arık, Sercan Ömer; Vuraf, E.; Frossard P. (IEEE, 2011)
      Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pair-wise similarity ...
    • Finding compound structures in images using image segmentation and graph-based knowledge discovery 

      Zamalieva, Daniya; Aksoy, Selim; Tilton J. C. (IEEE, 2009-07)
      We present an unsupervised method for discovering compound image structures that are comprised of simpler primitive objects. An initial segmentation step produces image regions with homogeneous spectral content. Then, the ...
    • GCap: Graph-based automatic image captioning 

      Pan J.-Y.; Yang H.-J.; Faloutsos C.; Duygulu, Pınar (IEEE, 2004)
      Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is ...
    • A graph based approach to estimating lexical cohesion 

      Gürkök, Hayrettin; Karamuftuoglu, Murat; Schaal, Markus (ACM, 2008)
      Traditionally, information retrieval systems rank documents according to the query terms they contain. However, even if a document may contain all query terms, this does not guarantee that it is relevant to the query. The ...