research

My research is on improving techniques, such as structured prediction, for understanding scenes from 2-D and 3-D data. I am also interested in techniques for improving real-time performance onboard robot systems.

publications

Contextual Classification with Functional Max-Margin Markov Networks
D. Munoz, J. A. Bagnell, N. Vandapel, M. Hebert
CVPR 2009 (Oral presentation)
[pdf] [bibtex]


Onboard Contextual Classification of 3-D Point Clouds with Learned High-order Markov Random Fields
D. Munoz, N. Vandapel, M. Hebert
ICRA 2009
[pdf][bibtex]


Directional Associative Markov Network for 3-D Point Cloud Classification
D. Munoz, N. Vandapel, M. Hebert
3DPVT 2008 (Oral presentation)
[pdf] [bibtex]


tutorials

Advances in Minimizing Submodular Energy Functions with Graph Cuts
Computer Vision Misc. Reading Group, Carnegie Mellon University
May 28, 2008 [pdf] [ppt]

Analysis: TextonBoost and Semantic Texton Forests
16-721: Learning-Based Methods in Vision, Carnegie Mellon University
February 9, 2009 [pdf] [ppt]

presentations

Contextual Classification with Functional Max-Margin Markov Networks
National Robotics Engineering Center Seminar, Pittsburgh, PA
October 7, 2009

3-D Point Cloud Classification with Max-Margin Markov Networks
Machine Learning Lunch Seminar, Carnegie Mellon University
December 1, 2008