Alexander Toshev

I am a Research Scientist working primarily in the field of computer vision and machine learning. My recent work includes object detection and segmentation, human pose estimation, learning from limited data.

Prior to Google I was a Ph.D. Candidate in Computer and Information Science at the School of Engineering and Applied Sciences, University of Pennsylvania. where I worked on shape-based recognition; co-segmentation for image matching; parsing of 3D Range Imagery.

Prior to Philadelphia, I did my undergraduate studies at the University of Karlsruhe, Germany. I spent six months in the Spring of 2005 at INRIA, France, working on my diploma thesis on activity recognition. In the Summer of 2008 I was an intern at Google Research, New York, working on object detection in videos.

Google Publications

Previous Publications

  •  

    Shape-based Object Detection via Boundary Structure Segmentation

    Alexander Toshev, Ben Taskar, Kostas Daniilidis

    International Journal of Computer Vision, vol. 99 (2012), pp. 123-146 (to appear)

  •  

    Cascaded Models for Articulated Pose Estimation

    Alexander Toshev, Benjamin Sapp, Ben Taskar

    European Conference in Computer Vision (2010)

  •  

    Detecting and Parsing Architecture at City Scale from Range Data

    Alexander Toshev, Philippos Mordohai, Ben Taskar

    Computer Vision and Pattern Recognition (2010)

  •  

    Object Detection via Boundary Structure Segmentation

    Alexander Toshev, Ben Taskar, Kostas Daniilidis

    Computer Vision and Pattern Recognition (2010)

  •  

    Submodular Function Minimization

    Alexander Toshev

    University of Pennsylvania (2010)

  •  

    An APRIORI-based Method for Frequent Composite Event Discovery in Videos

    Alexander Toshev, Francois Bremond, Monique Thonnat

    International Conference on Computer Vision Systems (2006)