Close
Metadata

@InProceedings{PedrosaTrai:2013:BaBaUs,
               author = "Pedrosa, Glauco Vitor and Traina, Agma Juci Machado",
          affiliation = "{University of Sao Paulo} and {University of Sao Paulo}",
                title = "From Bag-of-Visual-Words to Bag-of-Visual-Phrases using n-Grams",
            booktitle = "Proceedings...",
                 year = "2013",
               editor = "Boyer, Kim and Hirata, Nina and Nedel, Luciana and Silva, 
                         Claudio",
         organization = "Conference on Graphics, Patterns and Images, 26. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "image retrieval, bag-of-features, sift, keypoints, bag-of-words.",
             abstract = "The Bag-of-Visual-Words has emerged as an effective modeling 
                         approach to represent local image features. It describes local 
                         image features by assigning them a visual word according to a 
                         visual dictionary. The image representation is given by the 
                         frequency of each visual word in the image, as a similar 
                         representation used in textual documents. In this paper, we 
                         present a novel approach building a high-level description using a 
                         group of words (phrases) for representing an image. We introduce 
                         the use of n-grams for image representation, based on the idea of 
                         {"}Bag-of-Visual-Phrases{"}. In the field of computational 
                         linguistics, an n-gram is a phrase formed by a sequence of 
                         n-consecutive words. As analogy, we represent an image by a 
                         combination of n-consecutive visual words. We made representative 
                         experiments using three public benchmark databases of textures and 
                         nature scenes and two medical databases to demonstrate an area 
                         that can benefit from the proposed technique. Our proposed 
                         Bag-of-Visual-Phrases approach improved up to 44% the retrieval 
                         precision and up to 33% the classification rate compared to the 
                         traditional Bag-of-Visual-Words, being a valuable asset for 
                         content-based image retrieval and image classification.",
  conference-location = "Arequipa, Peru",
      conference-year = "Aug. 5-8, 2013",
             language = "en",
           targetfile = "PID2854877.pdf",
        urlaccessdate = "2020, Nov. 25"
}


Close