Current Work
- I just finished defending my Ph.D. thesis, Learning Probabilistic Models of visual motion. Horray!
- Articulated Skeletons from Motion
- Learning Parts-Based Models journal article: This article has an expanded coverage of MCVQ, and introduces a new model "Multiple Cause Factor Analysis" (MCFA). It has just appeared at JMLR. More information, as well as code and related papers, are available on the project website.
- I recently gave a Google Tech Talk on my latest tracking project. You can view it online.
- I have a new paper appearing at ICML 2006 on Combining
Discriminative Features to Infer Complex Trajectories. My
paper, talk, and some nice videos of tracking a basketball, can be
found at the project website. You can
see one of the videos from my ICML talk right here:
Get the Flash Player to see this player.
- Incremental Visual Tracking - This is a method for visual tracking of objects in video, based on a new algorithm for incremental PCA. There is a new journal article on this project appearing soon in the IJCV Special Issue: Learning for Vision.
During the summer and fall of 2003, I
was an intern at Honda Research
Institute in Mountain View, California, with Ming-Hsuan Yang. One of
the projects we were working on is the vision system of Honda's ASIMO robot.
Publications
- Learning Probabilistic Models for Visual Motion
David Ross, Ph.D. Thesis, University of Toronto, Canada, 2008. [to appear] - Unsupervised learning of skeletons from motion
David Ross, Daniel Tarlow, and Richard Zemel. 10th European Conference on Computer Vision (ECCV 2008), 2008. [PDF] - Learning stick-figure models using nonparametric Bayesian
priors over trees
Edward Meeds, David Ross, Richard Zemel, and Sam Roweis. IEEE Conference on Computer Vision and Pattern Recognition, 2008. [PDF] - Learning Articulated Skeletons From Motion
David Ross, Daniel Tarlow, and Richard Zemel. Workshop on Dynamical Vision at ICCV, 2007. [PDF] project website - Incremental Learning for Robust Visual Tracking
David Ross, Jongwoo Lim, Ruei-Sung Lin, Ming-Hsuan Yang.
In the International Journal of Computer Vision, Special Issue: Learning for Vision, 2008. [PS.GZ] [PDF] project website - Inducing Features from Visual Noise
Andrew Cohen, Richard Shiffrin, Jason Gold, David Ross, and Michael Ross. Journal of Vision, 7(8):15, 2007. [PDF] - Learning Parts-Based Representations of Data
David Ross and Richard Zemel. Journal of Machine Learning Research, 7(Nov):2369-2397, 2006. [PDF] project website - Combining Discriminative Features to Infer Complex
Trajectories
David Ross, Simon Osindero, and Richard Zemel. In Proceedings of the Twenty-Third International Conference on Machine Learning, 2006. [PS.GZ] [PDF] project website - Incremental Learning for Visual Tracking
Jongwoo Lim, David Ross, Ruei-Sung Lin, Ming-Hsuan Yang
In L. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems 17, MIT Press, 2005. [PS.GZ] [PDF] project website - Adaptive Discriminative Generative Model and Its
Applications
Ruei-Sung Lin, David Ross Jongwoo Lim, Ming-Hsuan Yang
In L. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems 17, MIT Press, 2005. [PS.GZ] [PDF] project website - Adaptive Probabilistic Visual Tracking with Incremental
Subspace Update
David Ross, Jongwoo Lim, Ming-Hsuan Yang
In T. Pajdla and J. Matas, editors, Proc. Eighth European Conference on Computer Vision (ECCV 2004), 2004. [PS.GZ] [PDF] project website - Multiple Cause Vector Quantization
David Ross and Richard Zemel
In S. Becker, S. Thrun, and K. Obermayer, editors, Advances in Neural Information Processing Systems 15, MIT Press, 2003. [PS.GZ] [PDF] project website - Learning Parts-Based Representations of Data (thesis
version)
David Ross, University of Toronto, M.Sc. Thesis, 2003. [PS.GZ] [PDF] project website - Bibtex entries for all of the above are available here.
Code
- The source code for most of my research projects is available for download here. Included are Matlab implementations of a number of machine learning & computer vision algorithms, but there are also a few other hacks.
- Parallel Computing: Here is some code I've written/modified, as well as some getting-started tips for parallel computing using Matlab.
- Latest Update The code for the "Combining Discriminative Features" learning/tracking algorithm is now available. cdf_2007-07-13.zip
Other Stuff
- LaTeX Notes Here are a few tricks for making documents with LaTeX.
- Presentations on various papers, prepared for seminar classes.
- Pictures from my wedding,from my recent trip to Poland, Karolina's move to California, and on Flickr.