[old
presentations]
[old FAQs]
| |
Gerald Dalley's MIT Home Page
Until I graduated in the summer of 2009,
I
was a Ph.D. student studying
Computer Vision in
the Activity Perception
Project group at the Massachusetts Institute of Technology.
My research interests include the intersection of visual tracking, object recognition, and
machine learning.
Post-graduation, I accepted a position at D. E.
Shaw & Co. as a quantitative developer (a hybrid position that lies
between a software developer and a quantitative analyst).
Contact Information
Gerald Dalley dalleyg@ieee.org
Teaching and Recent Pre-Graduation Extra-Curricula
During the Spring 2007 semester, I was a recitation instructor for 6.001,
MIT's exciting and fast-paced introductory course to computer science. My
6.001 page
has copies of handouts, announcements, and helpful links for the course.
The information will be most helpful for those using the Scheme programming
language (note that starting in 2007, MIT transitioned to Python).
For the 2006-2007 academic year I served as co-chair of the
Graduate Student Council's
Housing and
Community Affairs Committee. The HCA committee is the main advocacy branch
of the GSC. The committee's work focuses on ensuring that the MIT graduate
experience is enjoyable, affordable, safe, healthy, and marked by a welcoming
community. A large portion of the work carried out by the HCA is done through a
set of subcommittees, each of which focuses on a particular aspect of student
life.
Publications
- G. Dalley. Improved Robustness and Efficiency for Automatic
Visual Site Monitoring. PhD Thesis. Massachusetts Institute of
Technology. Jun. 2009. [full
res. pdf (90.4MB)][low res. pdf
(5.4MB)][pedestrian detection
source code (.zip)]
- G. Dalley, J. Migdal, and W.E.L. Grimson. "Background Subtraction
for Temporally Irregular Dynamic Textures", Workshop on Applications of
Computer Vision. Jan. 2008. [pdf]
- G. Dalley and X. Wang. "Event Detection Using an Attention-Based
Tracker", Workshop on Performance Evaluation of Tracking Systems at
the IEEE International Conference on Computer Vision. Oral
Presentation. Oct. 2007. [pdf]
- G. Dalley, Tomáš Ižo. "Schematic Querying of Large Tracking Databases",
CSAIL Technical Report: MIT-CSAIL-TR-2006-043, 12 June 2006. [pdf]
- K. Tieu, G. Dalley, and W.E.L. Grimson. "Inference of Non-Overlapping
Camera Network Topology by Measuring Statistical Dependence",
International Conference on Computer Vision. Oral Presentation. Oct.
2005. [pdf]
- G. Dalley, W. Freeman, and J. Marks. "Single-frame Text
Super-resolution: A Bayesian Approach", International Conference on Image
Processing. Oct. 2004. [pdf]
- L. Lee, G. Dalley, and K. Tieu. "Learning Pedestrian Models for
Silhouette Refinement", International Conference on Computer Vision.
Oct. 2003. pp. 663--670. [pdf]
- G. Dalley and P. Flynn. "Pair-wise range image registration: A study in
outlier classification", Computer Vision and Image Understanding.
Jan. 2003. pp. 104--115. [pdf]
- G. Dalley. "Vehicle Recognition in Cluttered Environments". M.S. Thesis,
The Ohio State University. June 2002. [pdf]
- G. Dalley and P. Flynn. "Range image registration: A software platform
and empirical evaluation". In Proceedings of the 3rd International
Conference on 3-D Digital Imaging and Modeling. pp. 246--253, 2001. [pdf]
- G. Dalley. "A Software Test-bed for the Registration of 3D Range
Images". B.S. Thesis, The Ohio State University. August 2000. [pdf]
Recent Talks
- "Improved Robustness and Efficiency for Automatic Visual Site
Monitoring", PhD Thesis Defense, MIT, 9 June 2009. [pptx
with videos (45MB)][pdf (6.5MB)][low-res
pdf (3.2MB)]
- "Background Subtraction for Temporally Irregular Dynamic Textures", WACV
Workshop, Jan. 2008. [ppt][pdf][avi
(sample results)]
- "Event Detection Using an Attention-Based Tracker", Federal University
of Paraná, 22 Oct. 2007. [pptx][ppt][pdf]
- "Event Detection Using an Attention-Based Tracker", PETS Workshop
at ICCV 2007. [pptx][pdf]
- "Inference of Non-Overlapping Camera Network Topology by Measuring
Statistical Dependence", ICCV 2005. [ppt][pdf]
|