My research is in the field of Computer Vision, and I am interested in image understanding, object recognition, segmentation, and the machine learning techniques required to tackle such problems. I want to build intelligent machines that can "see" and my research draws upon ideas from computer vision, machine learning, psychology, philosophy, and physics.
You can see all of my publications on my homepage, or grouped into topics below:
Exemplar-SVMs
On the benefits of large-scale learning with a single positive instance.
 |
Ensemble of
Exemplar-SVMs for Object Detection and Beyond
ICCV, 2011. [PDF] [Project Page + Code] |
 |
Data-driven Visual
Similarity for Cross-domain Image Matching
SIGGRAPH ASIA, 2011. [PDF] [Project Page + Video + Data + Code] |
 |
 A Gaussian
Approximation of Feature Space for Fast Image Similarity
MIT CSAIL Technical Report, 2012. [PDF] |
Visual Memex
Towards a category-free representation of the visual world. Motivated by Vannevar Bush.
 |
Beyond Categories: The
Visual Memex Model for Reasoning About Object Relationships
NIPS, 2009. [PDF] [Project Page] |
Multiple Segmentations
While no single segmentation is perfect, each one is wrong in a different way!
 |
Recognition by
Association via Learning Per-exemplar Distances
CVPR, 2008. [PDF] [Project Page + Code] |
 |
Improving Spatial Support
for Objects via Multiple Segmentations
BMVC, 2007. [PDF] [Project Page] |
Range-Data Registration
While an undergraduate at RPI, I worked on the problem of aligning multiple range scans of outdoor scenes.
 |
Registration of Multiple
Range Scans as a Location Recognition Problem:
Hypothesis Generation, Refinement, and Verification
3DIM, 2005. [PDF] |
Fractals
I started dabbling in Fractals when I was in high school, but back in 2008 I revived my interest and started making videos of Newton's Method Fractals. I have some cool videos up on youtube.