Topics on Vision in Humans
and Machines
CSE 291,
Spring 2007
David
Kriegman
Kriegman
{at} cs.ucsd.edu
Marian
Stewart Bartlett
Marni {at}
salk.edu
This
graduate seminar will explore topics in vision from the perspectives of
computer vision and human visual perception. Topics include stereo, segmentation, motion interpretation,
object recognition, face identity and expression recognition. Papers will
be selected from fields ranging from visual psychophysics, cognitive neuroscience, machine learning, and
computer vision.
Class
structure: Each student will serve as discussion leader twice. Every week, each
student will submit two questions or comments on the readings to the webct
discussion board. Students will also complete tutorials
from the
Tuesdays
9:30-11, Atkinson Hall (Calit2) room 3006.
COURSE URL: http://webct6web.ucsd.edu
Grading:
S/U, 2 units only.
Class
mailing list: cse291 {at} mplab.ucsd.edu
|
4/3 |
Organizational
Meeting. We are changing the time of the class to 9:30-11. Class will be on
Tuesdays with the addition of Thurs 4/5 and 4/19. |
|
4/5 |
Attend Tommy Poggio’s Talk, What
Should Computer Vision Learn from Neuroscience? 4:00 Leichtag Auditorium, bldg 804 on campus map. Related Papers: Serre, Wolf & Poggio, PAMI 2007. pdf Serre, Oliva & Poggio, PNAS 2007. pdf |
|
4/10-4/12 |
No
class |
|
4/17 |
Face
recognition by humans: 19 results all computer vision researchers should know
about. Sinha
et al., Proc IEEE, 2006. pdf. Each
student will choose 2 of the 19 results and follow up on the references to
explore the evidence on which each conclusion is based. What was the 20th result
and why was it dropped? See
sign-up sheet here.
Additional
related papers: Sinha
Chapter in Zhao & Chellappa book pdf O’Toole
chapter in Zhao & Chellappa book pdf |
|
|
Note:
The Thursday 4/19 class was moved to the following week (4/26) so that people
can attend the talk by Vinton Cerf: Tracking the Internet into the 21st Century Date: April 19th, 2007, 10:00am - 11:00am, Calit2
Auditorium, Atkinson Hall, UCSD |
|
4/24 |
Face
recognition by humans: 19 results (continued) |
|
4/26 (TH) |
Face
recognition by humans: 19 results (continued) |
|
5/1 |
Zhao,
Chellapa, Phillips, & Rosenfeld, ACM 2003. Face recognition: A literature
survey. pdf Students
will explore to what degree each approach is compatible with the 19 results. |
|
5/8 |
Zhao, Chellapa & Phillips (continued).
|
|
5/15 |
Recognizing
and learning object categories. ICCV05 short course.
Overview/Intro/Summary;
Part
1. Bags of words Adam,
Nick, Antoni, Patrick Supplemental
papers: J. Ponce, T.L. Berg, M. Everingham,
Lazebnik, M. Marszalek, C. Schmid, Williams, J. Zhang, A. Zisserman.
(2006) Dataset Issues in Object
Recognition, In
Toward Category-Level Object Recognition.
Springer-Verlag Lecture Notes
in Computer Science, J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.),
pdf Svetlana Lazebnik, Cordelia Schmid, and
Jean Ponce (2006). Beyond Bags of Features: Spatial Pyramid Matching for
Recognizing Natural Scene Categories. CVPR 2006, pp. 2169-2178. pdf |
|
5/22 |
(Meet
in room 3010.) Recognizing and learning object categories (cont). Part 2. Parts-based models Phil,
Carly, Miro, Albert Supplemental
papers: Fergus, R. , Perona, P. and Zisserman, A.
Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition.
International Journal of Computer Vision, 2006. pdf Kushal, Schmidt, & Ponce (2007)
Flexible object models for category-level 3-D object recognition. CVPR 2007. pdf |
|
5/29 |
Mark
Frank Talk. Room TBA. |
|
6/7 (Thurs) |
Recognizing
and learning object categories (cont). Part
3. Discriminative Models Part
4. Combined segmentation & recognition Paul,
Alan, Cynthia, Cuong Supplemental
paper: D. Hoiem, A.A. Efros, and M. Hebert, "Putting Objects in
Perspective", CVPR 2006. pdf,
project. |