Now showing items 1-4 of 4

    • Attributes2Classname: a discriminative model for attribute-based unsupervised zero-shot learning 

      Demirel, B.; Cinbiş, Ramazan Gökberk; İkizler-Cinbiş, N. (IEEE, 2017-10)
      We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. ...
    • Conceptfusion: A flexible scene classification framework 

      Saraç, Mustafa İlker; işcen, Ahmet; Gölge, Eren; Duygulu, Pınar (Springer, 2015-03-04)
      We introduce ConceptFusion, a method that aims high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability. The proposed method combines the advantages of ...
    • FAME: Face association through model evolution 

      Gölge, Eren; Duygulu, Pınar (IEEE, 2015-06)
      We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to ...
    • Hypergraph-theoretic partitioning models for parallel web crawling 

      Türk, Ata; Cambazoğlu, B. Barla; Aykanat, Cevdet (Springer, London, 2012)
      Parallel web crawling is an important technique employed by large-scale search engines for content acquisition. A commonly used inter-processor coordination scheme in parallel crawling systems is the link exchange scheme, ...