I am a PhD student in the Computer Science and Engineering Department at UCSD. My advisor is Serge Belongie, and I am part of the SO(3) Computer Vision group. My research interests include machine vision & learning. More specifically I am interested in learning with ambiguity (multiple instance learning), learning distance metrics, part based object detection & recognition, local feature description, and online/adaptive learning for tracking. I am currently funded by the IGERT fellowship.

Contact

• Email: bbabenkocs.ucsd.edu
• Office: 4106 EBU3b
• Office Phone: (858) 534-8819

News

• *NEW* My technical report with Piotr Dollar and Serge Belongie titled "Multiple Instance Learning with Query Bags" is now posted here
• *NEW* My work with Steve Branson and Serge Belongie titled "Similarity Functions for Categorization: from Monolithic to Category Specific" was accepted as an oral presentation at ICCV 2009
• Code and data for MILTrack (Babenko et al. CVPR'09) is now on the project page!
• Wojek et al. recently showed that MPL outperforms other algorithms on a pedestrian detection task. Check out their paper here.
• My work on Tracking with Online Multiple Instance Learning has been accepted to CVPR'09. Paper pdf, data, and code coming soon!
• Tiny ASIMO!