CSE 590V: Computer Vision Reading Group

CSE590V is a Seminar/Reading Group focused on recent trends in computer vision. We will cover papers from recent computer vision conferences (CVPR, ICCV, ECCV). The seminar is open to everyone. We especially encourage first year graduate students who may be considering computer vision or related areas as potential research avenues.

The seminar meets every week from 3:30PM to 5:00PM in AC403.

The class mailinglist is cse590v(at)cs.washington.edu.

Those of you who are taking the course or are interesting in keeping up with the topics being discussed in the seminar, please subscribe to the mailinglist at https://mailman.cs.washington.edu/mailman/listinfo/cse590v

Organizers

Eli Shechtman, elishe(at)cs.washington.edu
Ira Kemelmacher-Shlizerman, kemelmi(at)cs.washington.edu
Natalia Larios Delgado, nlarios(at)u.washington.edu
Sameer Agarwal, sagarwal(at)cs.washington.edu
Yasutaka Furukawa, furukawa(at)cs.washington.edu

Schedule

10/12 - Ian, Kathleen
Papers:
1. N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar Attribute and Simile Classifiers for Face Verification, ICCV 2009.
2. N. Kumar, P. N. Belhumeur, and S. K. Nayar, FaceTracer: A Search Engine for Large Collections of Images with Faces, ECCV, 2008.
10/19 - Evan, Paramjit
Papers:
1. E. Candes and M. Wakin, An introduction to compressive sampling. IEEE Signal Processing Magazine, 2008.
2. V. Cevher, A. Sankaranarayanan, M. Duarte, D. Reddy, R. Baraniuk, and R. Chellappa, Compressive sensing for background subtraction. ECCV, 2008.
10/26 - Alex, Daniel
Papers:
1. A. Levin, Y. Weiss, F. Durand, W. T. Freeman. Understanding and evaluating blind deconvolution algorithms. CVPR 2009 (Best paper award runner up)
2. R. Fergus, B. Singh, A. Hertzmann, S. Roweis, W. T. Freeman. Removing camera shake from a single image.SIGGRAPH 2006
11/02 - Rahul, Gilbert
Papers:
1. Victor Lempitsky, Pushmeet Kohli, Carsten Rother, and Toby Sharp Image Segmentation with A Bounding Box Prior , ICCV 2009
2. Sara Vicente, Vladimir Kolmogorov, and Carsten Rother Graph cut based image segmentation with connectivity priors, CVPR 2009
11/09 - Mike, Kevin

G. Heitz, G. Elidan, B. Packer, and D. Koller Shape-Based Object Localization for Descriptive Classification , IJCV 2009

11/16 - CVPR deadline, No Seminar
11/23 - Peter, Qi

J.M. Morel and G.Yu, ASIFT: A New Framework for Fully Affine Invariant Image Comparison, SIIMS, 2(2), 2009.

11/30 - Ankit, Jia

C. Liu, J. Yuen, A. Torralba
Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment, CVPR 2009.
C. Liu, J. Yuen A. Torralba J. Sivic W. T. Freeman
SIFT flow: dense correspondence across difference scenes, ECCV 2008.

12/07 - Lin, Sarah

C. Desai, D. Ramanan, C. Fowlkes
Discriminative models for multi-class object layout, ICCV 2009.
P. Felzenszwalb, D. McAllester, D. Ramanan
A Discriminatively Trained, Multiscale, Deformable Part Model, IEEE CVPR 2008.

Papers

Low level vision

Understanding Blind Deconvolution

Geodesic Image Segmentation
Single Image Haze Removal Using Dark Channel Prior , Kaiming He (The Chinese University of Hong Kong), Jian Sun (Microsoft Research Asia), Xiaoou Tang (The Chinese University of Hong Kong)

Compressive Sensing

Several tutorials here - http://dsp.rice.edu/cs, not sure which is best.

Sparse Coding

Yair Weiss, Hyun Sung Chang and William T. Freeman, "Learning Compressed Sensing", Allerton 2007

Emmanuel Candes and Michael Wakin, An introduction to compressive sampling, IEEE Signal Processing Magazine, 25(2), pp. 21 - 30, March 2008

Locality Sensitive Hashing

Median Shift http://www.cs.tau.ac.il/~liors/research/papers/mode_detection.pdf

MIT LSH site. See section 3 in the user manual

Book: G. Shakhnarovich, T. Darrell and P. Indyk, Nearest-Neighbor Methods in Learning and Vision: Theory and Practice 2006. Introduction and LSH chapter

A. Andoni and P. IndykNear-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions, Communications of the ACM, vol. 51, no. 1, 2008, pp. 117-122.

V. Athitsos, M. Potamias, P. Papapetrou and G. Kollios. Nearest Neighbor Retrieval Using Distance-Based Hashing. ICDE 2008.

Discrete Optimization

Minimizing Sparse Higher Order Energy Functions of Discrete Variables (Carsten Rother (Microsoft Research Cambridge), Pushmeet Kohli (Microsoft Research Cambridge), Wei Feng (The Chinese University of Hong Kong), Jiaya Jia (The Chinese University of Hong Kong))

Higher-Order Clique Reduction in Binary Graph Cut (Hiroshi Ishikawa (Nagoya City University)), CVPR 2009.

Shape Priors and Discrete MRFs for Knowledge-based Segmentation, Olivier Duchenne (Ecole Normale Superieure), Francis Bach (INRIA - ENS), In So Kweon (KAIST), Jean Ponce (Ecole Normale Superieure)

A Tensor-Based Algorithm for High-Order Graph Matching, A. Besbes, N. Paragios, N. Komodakis, and G. Langs

Photometry

A Linear Formulation of Shape from Specular Flow Guillermo D. Canas, Yuriy Vasilyev, Yair Adato, Todd Zickler, Steven Gortler, Ohad Ben-Shahar ICCV 2009

A Projective Framework for Radiometric Image Analysis (Ping Tan (National University of Singapore), Todd Zickler (Harvard University)) CVPR 2009

Shape from Varying Illumination and Viewpoint [ pdf ] [www] Neel Joshi and David Kriegman / In Proc. IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, October 2007.

Isotropy, Reciprocity and the Generalized Bas-Relief Ambiguity [ pdf ] Ping Tan, Satya P. Mallick, Long Quan, David Kriegman, and Todd Zickler / IEEE Conf. on Computer Vision and Pattern Recognition, June 2007.

What does the sky tell us about the camera? Jean-Francois Lalonde, Srinivasa G. Narasimhan, and Alexei A. Efros European Conference on Computer Vision, 2008.

What do color changes reveal about an outdoor scene? Kalyan Sunkavalli, Fabiano Romeiro, Wojciech Matusik, Todd Zickler, Hanspeter Pfister Accepted to CVPR 2008

Looking Around the Corner Using Transient Imaging -- Ahmed Kirmani, Tyler Hutchison, James Davis, Ramesh Raskar, iccv'09

Feature extraction and description

ASIFT - a truely affine invariant SIFT (Greatly outperforms other detectors!)
CHoG: Compressed Histogram of Gradients: A Low Bit-Rate Feature Descriptor , Vijay Chandrasekhar (Stanford University), Gabriel Takacs (Stanford University), David Chen (Stanford University), Sam Tsai (Stanford University), Radek Grzeszczuk (Nokia Research Center), Bernd Girod (Stanford University)

Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning Mohammad Norouzi (Simon Fraser University), Mani Ranjbar (Simon Fraser University), Greg Mori (Simon Fraser University)

Learning Invariant Features Through Topographic Filter Maps, Koray Kavukcuoglu Marc Aurelio Ranzato Rob Fergus Yann LeCun (Courant Institute of Mathematical Sciences)

Frequency-tuned Salient Region Detection

Optimization and learning

Regularized Multi-Class Semi-Supervised Boosting

Multi-Class Active Learning for Image Classification, Prateek Jain (University of Texas at Austin), Ashish Kapoor (Microsoft Research)

Global Optimization for Alignment of Generalized Shapes,Li, H.S. and Shen, T. and Huang, X.L.

Active Learning for Large Multi-class Problems

Implicit Elastic Matching with Random Projections for Pose-variant Face Recognition, John Wright (University of Illinois), Gang Hua (Microsoft Live Labs Research)

Image classification, and Object detection and recognition

Class-Specic Hough Forests for Object Detection, J. Gall (BIWI, ETH Zurich and MPI Informatik) and V. Lempitsky (MSR Cambrige)

Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework, Li-Jia Li (Princeton University), Richard Socher (Princeton University), Li Fei-Fei (Princeton University)

Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification, Jianchao Yang (University of Illinois at Urbana-Champaign), Kai Yu (NEC Labs America), Yihong Gong (NEC Laboratories America, Inc.), Thomas Huang (University of Illinois at Urbana-Champaign)

An Empirical Study of Context in Object Detection

Optimal Scanning for Faster Object Detection

"Attribute and Simile Classifiers for Face Verification," N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar, IEEE International Conference on Computer Vision (ICCV), Oct, 2009.

Expression-Insensitive 3D Face Recognition using Sparse Representation, Xiaoxing Li (Virginia Tech), Tao Jia (Virginia Tech), Richard (hao) Zhang (Simon Fraser University)

Estimating Human Shape and Pose from a Single Image,Peng Guan, Alexander Weiss, Alexandru O. Bălan, Michael J. Blake

Geremy Heitz and Daphne Koller. Learning Spatial Context: Using Stuff to Find Things. eccv'08

Spectral Hashing Y. Weiss. and A. Torralba and R. Fergus NIPS 2008

Small codes and large databases for recognition A. Torralba, R. Fergus and Y. Weiss CVPR 2008

Recognition via Association, http://www.cs.cmu.edu/~tmalisie/projects/cvpr08/

http://www.eecs.berkeley.edu/~chunhui/index_files/glam-09.pdf

http://www.eecs.berkeley.edu/~chunhui/index_files/lagm-09.pdf

Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment , C. Liu, J. Yuen, A. Torralba, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

Learning Shape Prior Models for Object Matching