Now showing items 1-9 of 9

    • Benefit maximizing classification using feature intervals 

      İkizler, Nazlı (Bilkent University, 2002)
      For a long time, classification algorithms have focused on minimizing the quantity of prediction errors by assuming that each possible error has identical consequences. However, in many real-world situations, this ...
    • Human action recognition using distribution of oriented rectangular patches 

      İkizler, Nazlı; Duygulu, Pınar (Springer, 2007-10)
      We describe a "bag-of-rectangles" method for representing and recognizing human actions in videos. In this method, each human pose in an action sequence is represented by oriented rectangular patches extracted over the ...
    • Human action recognition with line and flow histograms 

      İkizler, Nazlı; Cinbiş, R. Gökberk; Duygulu, Pınar (IEEE, 2008-12)
      We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of lines which are fitted to boundaries of ...
    • Maximizing benefit of classifications using feature intervals 

      İkizler, Nazlı; Güvenir, H. Altay (Springer, Berlin, Heidelberg, 2003)
      There is a great need for classification methods that can properly handle asymmetric cost and benefit constraints of classifications. In this study, we aim to emphasize the importance of classification benefits by means ...
    • Person search made easy 

      İkizler, Nazlı; Duygulu, Pınar (Springer, Berlin, Heidelberg, 2005)
      In this study, we present a method to extensively reduce the number of retrieved images and increase the retrieval performance for the person queries on the broadcast news videos. A multi-modal approach which integrates ...
    • Recognizing actions from still images 

      İkizler, Nazlı; Cinbiş, R .Gökberk; Pehlivan, Selen; Duygulu, Pınar (IEEE, 2008-12)
      In this paper, we approach the problem of under- standing human actions from still images. Our method involves representing the pose with a spatial and ori- entational histogramming of rectangular regions on a parse ...
    • Resim arama sonuçlarının çizge tabanlı bir yöntemle yeniden sıralanması 

      Sevil, Sare; Zitouni, Hilal; İkizler, Nazlı; Özkan, D.; Duygulu, Pınar (IEEE, 2008-04)
      Arama motorları aracılığı ile arama yapmak günümüzde internetin en yaygın kullanım amaçlarından biridir. Ancak sorgu sonuçları, özellikle resim arama sorgularında, çoğu zaman sorgu ile ilgli olmayan sonuçlar da içerebilmektedir. ...
    • Searching video for complex activities with finite state models 

      İkizler, Nazlı; Forsyth, D. (IEEE, 2007-06)
      We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments ...
    • Understanding human motion : recognition and retrieval of human activities 

      İkizler, Nazlı (Bilkent University, 2008)
      Within the ever-growing video archives is a vast amount of interesting information regarding human action/activities. In this thesis, we approach the problem of extracting this information and understanding human motion ...