|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| CS 395T:
Object Recognition, Spring 2007 |
|
|
| Tentative
schedule and reading list |
|
|
|
|
|
| Topics |
Class
dates |
Slides |
Presenter/demo |
Papers (to be discussed
on class day listed) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Introduction |
Thurs |
18-Jan |
pdf |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Faces |
Tues |
23-Jan |
pdf |
|
M. Turk and A.
Pentland. Face Recognition Using Eigenfaces.
CVPR 1991 |
|
| |
|
|
pdf |
Joonsoo |
G. Edwards, T.
Cootes, and C. Taylor. Face
Recognition Using Active Appearance Models.
ECCV 1998. |
|
|
Thurs |
25-Jan |
pdf |
Zubair |
P. Viola and M.
Jones. Rapid object detection using a boosted cascade of simple
features. CVPR 2001 |
|
|
|
|
|
|
Sinha, P., Balas,
B.J., Ostrovsky, Y., & Russell, R. Face recognition by humans: 20 results
all computer vision researchers should know about. (under review) |
|
|
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Electronic Privacy
Information Center Face Recognition page |
|
|
| |
|
|
|
|
|
|
Face Recognition Home Page |
|
|
| |
|
|
|
|
|
|
CMU Face detection demo |
|
|
| |
|
|
|
|
|
|
Information
on using OpenCV for Viola-Jones style face detection |
|
|
| |
|
|
|
|
|
|
Robert Schapire's
page with links to boosting papers, including introductions |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pdf |
|
Background on recognition
models |
|
| Part-based models |
Tues |
30-Jan |
pdf |
Pushkala |
P.
Felzenszwalb and D. Huttenlocher.
Efficient Matching of Pictorial Structures. CVPR 2000. |
|
|
|
|
|
|
|
|
|
(optional) M.
Fischler and R. Elschlager. The representation and matching of pictorial
images. IEEE Transactions on Computers, Volume 22, 1973. |
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Matlab
code for parts and structure model from ICCV 2005 short course |
|
|
|
|
|
|
|
|
|
|
Thurs |
1-Feb |
pdf |
Tuyen |
M. Weber, M. Welling
and P. Perona. Unsupervised Learning of Models for Recognition. In ECCV, 2000. |
|
|
|
|
|
|
Prateek |
R. Fergus, P.
Perona, and A. Zisserman. Object class recognition by unsupervised scale
invariant learning. In CVPR03. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
EM overview, Duda and Hart book, Ch
3.9 |
|
|
|
|
|
|
|
|
|
|
Christopher
Bishop's "Machine Learning Techniques for Computer Vision" ECCV
2004 tutorial |
|
|
|
|
|
|
|
|
|
Matlab
code for constellation model demo from Perona's lab |
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| (Invariant) local features |
Tues |
6-Feb |
pdf |
|
Background on interest
operators |
|
|
|
|
|
pdf |
|
|
|
|
| |
Thurs |
8-Feb |
pdf |
Sudheendra |
D. Lowe. Distinctive Image Features from
Scale-Invariant Keypoints. IJCV 2004. |
|
|
| |
|
|
pdf |
Mohan |
K.Mikolajczyk
and C.Schmid. An affine invariant
interest point detector. ECCV 2002. |
|
|
| |
|
|
|
|
|
(optional)
J. Matas, O. Chum, M.Urban, and T. Pajdla.
Robust Wide Baseline Stereo from Maximally Stable Extremal
Regions. BMVC 2002. |
|
| |
|
|
|
|
P.
Moreels and P. Perona. Evaluation of
Features Detectors and Descriptors based on 3D objects. ICCV 2005 |
|
| |
|
|
|
|
|
|
| |
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Lowe's SIFT demo software |
|
|
| |
|
|
|
|
|
SIFT++ code
from Andrea Vedaldi |
|
|
| |
|
|
|
|
|
|
Software for region
detectors and descriptors from the Visual Geometry Group at Oxford |
|
|
|
|
| |
|
|
|
|
|
|
Multiple View Geometry in
Computer Vision - sample chapters from
Hartley and Zisserman book, Matlab code |
|
|
|
| |
|
|
|
|
|
|
Data
from Pierre Moreels's experiments |
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Segmentation |
Tues |
13-Feb |
pdf |
Inwoo |
X.
Ren and J. Malik. Learning a
Classification Model for Segmentation.
ICCV 2003. |
|
|
| |
|
|
imgs |
Changhai (demo) |
D. Martin, C.
Fowlkes, and J. Malik. Learning to
Detect Natural Image Boundaries…, PAMI 2004 |
|
|
| |
|
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Superpixels code |
|
|
| |
|
|
|
|
|
|
Xiaofeng Ren's
page on superpixels |
|
|
| |
|
|
|
|
|
|
Berkeley
Segmentation Dataset and Benchmark |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pdf |
|
Background on bags of
words |
|
|
| Bags of features and |
Thurs |
15-Feb |
|
|
J.
Sivic and A. Zisserman. Video Google:
A Text Retrieval Approach to Object Matching in Videos. ICCV 2003. |
|
|
| feature vocabularies/dictionaries |
|
|
pdf |
Shilpa |
G.
Csurka, C. Bray, C. Dance, and L. Fan. Visual categorization with bags of
keypoints. In Workshop on Statistical
Learning in Computer Vision, ECCV, 2004. |
|
| |
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Video
Google Demo webpage |
|
|
| |
|
|
|
|
|
|
LIBSVM: library for support
vector machines |
|
|
| |
Tues |
20-Feb |
pdf |
Sainath |
F.
Perronnin, C. Dance, G. Csurka, M. Bressan.
Adapted Vocabularies for Generic Visual Categorization, ECCV 2006. |
|
|
|
| |
|
|
pdf |
Andrew |
Moosmann,
Triggs and Jurie. Fast Discriminative
Visual Codebooks using Randomized Clustering Forests, NIPS 2006 |
|
|
|
|
|
|
J.
Winn, A. Criminisi and T. Minka.
Object categorization by learned universal visual dictionary. ICCV 2005. |
|
|
|
|
pdf |
Duy (demo) |
|
(optional) Nowak,
Jurie and Triggs. Sampling Strategies
for Bag-of-Features Image Classificaiton, ECCV 2006 |
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Pascal Visual
Object Classes Challenge 2005 |
|
|
|
|
|
|
|
|
Pascal
Visual Object Classes Challenge 2006 |
\ |
|
|
|
|
|
|
|
|
Demo
videos for Winn et al. papers |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Geometry, spatial constraints |
Thurs |
22-Feb |
pdf |
Priyanka |
S.
Savarese, J. Winn, A. Criminisi.
Discriminative Object Class Models of Appearance and Shape by
Correlatons. CVPR 2006 |
|
|
|
|
|
pdf |
Brendan |
M.
Marszalek and C. Schmid. Spatial
Weighting for Bag-of-Features. CVPR
2006. |
|
|
|
|
|
|
|
|
(optional)
S. Lazebnik, C. Schmid, and J. Ponce.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing
Natural Scene Categories, CVPR 2006 |
|
|
Tues |
27-Feb |
pdf |
Elden |
D.
Crandall, P. Felzenszwalb, and D. Huttenlocher. Spatial priors for part-based
recognition using statistical models. CVPR 2005. |
|
|
|
|
pdf |
Goo |
Y.
Lamdan, J.T. Schwartz, and H. Wolfson. Geometric hashing: A general and
efficient model-based recognition scheme. ICCV 1988. |
|
|
|
|
|
|
|
(supplementary
overview) H. Wolfson and I. Rigoutsos. Geometric Hashing: An Overview. IEEE Computational Science &
Engineering. 4:4, 1997. |
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
K-fans source code
from David Crandall |
|
|
|
|
|
|
|
|
Chum
and Matas CVPR 2006 paper: Geometric Hashing with Local Affine Frames |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Shape (descriptors and
matching) |
Thurs |
1-Mar |
pdf |
Chia-Chih (+demo) |
D.
Gavrila. Pedestrian Detection from a
Moving Vehicle. ECCV 2000 |
|
|
|
|
|
|
|
pdf |
Medha (+demo) |
S.
Belongie, J. Malik, and J. Puzicha. Shape matching and object recognition
using shape contexts. PAMI 2002. |
|
|
|
|
|
|
|
|
(optional) A. Berg, T.
Berg, and J. Malik. Shape matching and object recognition using low
distortion correspondence. CVPR 2005. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Shape contexts and visual
CAPTCHAs |
|
|
|
|
|
|
|
|
|
Shape
context project page, link to Matlab demo software |
|
|
| **CLASS IN RLM 5.112** |
Tues |
6-Mar |
pdf |
Changhai |
T.
Sebastian, P. Klein, and B. Kimia: Recognition of Shapes by Editing Shock
Graphs. ICCV 2001. |
|
|
|
|
pdf |
Jong Taek |
A.
Thayananthan, B. Stenger, P. H. S.
Torr, and R. Cipolla. Shape Context
and Chamfer Matching in Cluttered Scenes.
CVPR 2003. |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
March 8: Project
proposals due |
|
|
|
| |
|
|
|
|
|
|
| Text and images |
Thurs |
8-Mar |
pdf |
Yong Jae |
T.
Berg, A. Berg, J. Edwards, M. Maire, R. White, Y. Teh, E. Learned-Miller, D.
Forsyth. Names and Faces in the News.
CVPR 2004. |
|
|
|
|
|
|
|
(follow-up)
T. Berg, A. Berg, J. Edwards, D. Forsyth. Who's in the Picture. NIPS 2004 |
|
|
|
|
|
|
|
(optional)
J. Weinman and E. Learned-Miller.
Improving Recognition of Novel Input with Similarity, CVPR 2006 |
|
|
| |
|
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Names and Faces in
the News data from Tamara Berg et al. |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Spring break |
Tues |
13-Mar |
|
|
|
Spring break |
|
| Spring break |
Thurs |
15-Mar |
|
|
|
Spring break |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Tues |
20-Mar |
pdf |
Michael |
K.
Barnard, P. Duygulu, N. de Freitas, D. Forsyth, D. Blei, and M. Jordan.
Matching words and pictures. JMLR, 3:1107-1135, 2003. |
|
|
|
|
pdf |
Duy |
M.
Johnson and R. Cipolla. Improved Image Annotation and Labelling Through
Multi-Label Boosting. BMVC 2005. |
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Data from Barnard
et al. paper |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Learning similarity measures |
Thurs |
22-Mar |
pdf |
Brendan |
T. Hertz,
A. Bar-Hillel and D. Weinshall, Learning Distance Functions for Image
Retrieval, CVPR 2004 |
|
|
|
|
|
pdf |
Pushkala |
A. Frome, Y.
Singer, and J. Malik. Image Retrieval
and Classification Using Local Distance Functions. NIPS 2006. |
|
|
Tues |
27-Mar |
pdf |
|
G.
Shakhnarovich, P. Viola, T. Darrell, Fast Pose Estimation with Parameter
Sensitive Hashing, ICCV 2003. |
|
|
|
|
|
pdf |
Mohan |
V.
Athitsos and S. Sclaroff. Boosting
Nearest Neighbor Classifiers for Multiclass Recognition. Workshop on Learning in CVPR 2005. |
|
|
|
|
|
|
V.
Athitsos and S. Sclaroff. Efficient
Nearest Neighbor Classification Using a Cascade of Approximate Similarity
Measures. CVPR 2005 |
|
|
|
|
|
|
|
(optional)
Xing, Ng, Jordan and Russell, Distance Metric Learning, with application to
clustering with side information, NIPS 2002. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Datasets
from Vassilis Athitsos et al.'s BoostMap papers |
|
|
|
|
|
|
|
|
|
Matlab LSH code from
Greg Shakhnarovich |
|
|
|
|
|
|
|
|
|
Distance learning
code from Tomer Hertz |
|
|
|
|
|
|
|
|
|
Study
on similarity search in high-dimensional spaces (Weber et al 1998) |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Fast
indexing |
Thurs |
29-Mar |
pdf |
William |
D.
Nister and H. Stewenius. Scalable
Recognition with a Vocabulary Tree.
CVPR 2006. |
|
|
|
|
|
Prateek |
S.
Obdrzalek and Jiri Matas. Sub-linear
Indexing for Large Scale Object Recognition.
BMVC 2005. |
|
|
| |
|
|
|
|
|
(optional)
J. Beis and D. Lowe. Shape Indexing
Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces. CVPR 1997. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Of related interest: |
Nister and Stewenius's dataset |
|
|
|
|
|
|
|
|
|
|
|
Shape
context project page, link to Matlab demo software |
|
|
|
|
|
|
|
|
|
|
|
Nearest Neighbor
Methods in Learning and Vision: Theory and Practice |
|
|
|
|
|
|
|
|
|
|
LSH code package from
Piotr Indyk's lab |
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
| Context |
Tues |
3-Apr |
pdf |
Joonsoo + Jong Taek |
Murphy, Torralba
& Freeman. Using the Forest to See
the Trees: A Graphical Model Relating Features, Objects, and Scenes. NIPS
2003 |
|
| |
|
|
|
|
|
(optional)
T. Strat. Employing Contextual
Information in Computer Vision (1993) |
|
|
|
Thurs |
5-Apr |
pdf |
Andrew |
X. He,
R. Zemel, and M. Carreira-Perpinan.
Multiscale Conditional Random Fields for Image Labeling. CVPR 2004 |
|
|
|
|
|
pdf |
Yong Jae + Inwoo |
D.
Hoiem, A. Efros, and M. Hebert, Putting Objects in Perspective, CVPR 2006. |
|
| |
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Code for
gist feature from Antonio Torralba |
|
|
| |
|
|
|
|
|
|
Datasets used by He et al. |
|
|
| |
|
|
|
|
|
|
Bill
Freeman's slides on Using the Forest to See the Trees paper |
|
| |
|
|
|
|
|
|
Code for portions
of Hoiem et al. method |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
| Unsupervised category
learning |
Tues |
10-Apr |
pdf |
Elden + Priyanka |
Sivic,
J., Russell, B., Efros, A., Zisserman, A. and Freeman, W. Discovering Objects and their Location in
Images. ICCV 2005 |
|
| |
|
|
pdf |
Elden + Priyanka |
Russell,
B. C. , Efros, A. A. , Sivic, J. , Freeman, W. T. and Zisserman, A. Using Multiple Segmentations to Discover
Objects and their Extent in Image Collections. CVPR 2006 |
|
| |
Thurs |
12-Apr |
pdf |
Zubair + Shilpa |
K.
Grauman and T. Darrell. Unsupervised
Learning of Categories from Sets of Partially Matching Image Features. CVPR 2006 |
|
|
| |
|
|
|
|
|
(background)
K. Grauman and T. Darrell. The Pyramid
Match Kernel: Discriminative Classification with Sets of Image Features. ICCV
2005 |
|
| |
|
|
pdf |
Sudheendra |
R. Fergus,
L. Fei-Fei, P. Perona, and A. Zisserman.
Learning Object Categories from Google’s Image Search. ICCV 2005. |
|
|
| |
|
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
LabelMe tool and data |
|
|
| |
|
|
|
|
|
|
libpmk: Pyramid Match code and
toolkit |
|
|
| |
|
|
|
|
|
|
Data
and images from Russell et al. paper |
|
|
| |
|
|
|
|
|
|
Data from Fergus et
al. paper |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
| Interclass transfer learning |
Tues |
17-Apr |
pdf |
Tuyen+Duy |
L.
Fei-Fei, R. Fergus, and P. Perona. A Bayesian approach to Unsupervised
One-Shot learning of Object categories. ICCV 2003 |
|
| |
|
|
pdf |
Goo |
E. Bart, S.
Ullman. Cross-generalization: learning
novel classes from a single example by feature replacement. CVPR, 2005. |
|
| |
Thurs |
19-Apr |
pdf |
Changhai |
Torralba, A., Murphy, K.
and Freeman, W. Sharing Features: Efficient Boosting Procedures for
Multiclass Object Detection. CVPR 2004 |
|
| |
|
|
pdf |
Medha |
A.
Opelt, A. Pinz, and A. Zisserman.
Incremental learning of object detectors using a visual shape
alphabet. CVPR 2006. |
|
| |
|
|
|
|
|
|
| |
|
|
|
|
Of related interest: |
Sharing
features code |
|
|
| |
|
|
|
|
|
|
Graz datasets |
|
|
| |
|
|
|
|
|
|
Pascal
Visual Object Classes Challenge 2006 |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
| Concurrent segmentation |
|
|
|
|
|
|
| and recognition |
|
|
|
|
**CLASS IN RLM 5.112** |
|
| **CLASS IN RLM 5.112** |
Tues |
24-Apr |
pdf |
Chia-Chih |
E.
Borenstein. and S. Ullman. Class-specific, top-down segmentation. ECCV 2002. |
|
| |
|
|
pdf |
Sainath |
Z.
Tu, X. Chen, A. Yuille, and S-C. Zhu.
Image Parsing: Unifying Segmentation, Detection, and Object
Recognition. IJCV 2005. |
|
| |
|
|
pdf |
Michael |
A.
Kannan, J. Winn, and C. Rother.
Clustering appearance and shape by learning jigsaws. NIPS 2006 |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
| |
Thurs |
26-Apr |
|
|
TBD |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
| Project presentations |
Tues |
1-May |
|
|
Project
presentations |
|
| Project presentations |
Thurs |
3-May |
|
|
Project
presentations |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
| |
Fri |
4-May |
|
|
Project papers due |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|