Browsing Computer Science by Author "Thangali, Ashwin"

OpenBU

Browsing Computer Science by Author "Thangali, Ashwin"

Sort by: Order: Results:

  • Thangali, Ashwin; Sclaroff, Stan (Boston University Computer Science Department, 2009-03-11)
    Locating hands in sign language video is challenging due to a number of factors. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Video can be captured ...
  • Yuan, Quan; Thangali, Ashwin; Sclaroff, Stan (Boston University Computer Science Department, 2005-06-10)
    Nearest neighbor search is commonly employed in face recognition but it does not scale well to large dataset sizes. A strategy to combine rejection classifiers into a cascade for face identification is proposed in this ...
  • Ablavsky, Vitaly; Thangali, Ashwin; Sclaroff, Stan (Boston University Computer Science Department, 2008-06)
    Partial occlusions are commonplace in a variety of real world computer vision applications: surveillance, intelligent environments, assistive robotics, autonomous navigation, etc. While occlusion handling methods have been ...
  • Yuan, Quan; Thangali, Ashwin; Ablavsky, Vitaly; Sclaroff, Stan (Boston University Computer Science Department, 2008-06)
    Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground ...
  • Yuan, Quan; Thangali, Ashwin; Ablavsky, Vitaly; Sclaroff, Stan (Boston University Computer Science Department, 2007)
    Object detection can be challenging when the object class exhibits large variations. One commonly-used strategy is to first partition the space of possible object variations and then train separate classifiers for each ...
  • Thangali, Ashwin; Sclaroff, Stan (Boston University Computer Science Department, 2004-11-02)
    A novel technique to detect and localize periodic movements in video is presented. The distinctive feature of the technique is that it requires neither feature tracking nor object segmentation. Intensity patterns along ...

Search OpenBU


Advanced Search

Browse

Deposit Materials