CS 684  Object Recogntion-Fall 2005

Note: Course has been moved to the Viz-Center and now meets MWF 0900-0950 in the Viz-Center conference room,
8th floor, Center for Visualization and Virtual Environments University of Kentucky, 1 Quality Street, Suite 800.

Syllabus

Syllabus(pdf)

General Info

This is a reading class on visual object recognition. It will focus mainly on recognition with invariant local regions and descriptors.

Homework

There will be three assignments.

Assignment 1:
Collect 4 images (no more, no less, it is important that the image names come up in groups of 4 upon an ls) of each of 100 objects. (i.e. 4x100=400 images).
The images should be 640x480, JPEG with low compression. Examples

Assignment 2:
Recognition (Individual)

Assignment 3:
Recognition (Group)

Links

Here are the papers that we will read in class:

[1] D. Lowe. Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision, 60(2):91–110, 2004.

 

[2] J. Matas, O. Chum, U. Martin, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proc. British Machine Vision Conference, volume 1, pages 384–393, Sep 2002.

 

[3] K. Mikolajczyk and C. Schmid. Scale and affine invariant interest point detectors. Int. Journal of Computer Vision, 1(60):63–86, 2004

 

[4] T.Tuytelaars and L. Van Gool. Matching widely separated views based on affine invariant regions. Int. Journal of Computer Vision, 1(59):61–85, 2004

 

[5] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Van Gool. A comparison of affine region detectors. Technical Report, accepted to IJCV, 2005

 

[6] Stephan Obdrzalek and Jiri Matas Object Recognition using Local Affine Frames

on Distinguished Regions, BMVC 02, http://cmp.felk.cvut.cz/~matas/papers/obdrzalek-bmvc02.pdf

 

[7] Stephan Obdrzalek and Jiri Matas,Image Retrieval Using Local Compact DCT-based Representation, DAGM’03, 25th Pattern Recognition Symposium

September 10-12, 2003, Magdeburg, Germany, http://cmp.felk.cvut.cz/~matas/papers/obdrzalek-dagm03.pdf

 

[8] M. Brown, R. Szeliski, and S. Winder. Multi-image matching using multi-scale oriented patches. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'2005), volume I, pages 510-517, San Diego, CA, June 2005.

 

[9] S. Belongie, J. Malik, and J. Puzicha. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(4):509.522, April 2002.

 

[10] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. Technical Report, accepted to PAMI, 2005

 

[11] J. Sivic and A. Zisserman. Video Google: A text retrieval approach to object matching in

videos. In Proc. International Conference on Computer Vision, Oct 2003

 

[12] Stephan Obdrzalek and Jiri Matas, Sub-linear Indexing for Large Scale Object Recognition Accepted for publication at British Machine Vision Conference (BMVC) 2005

September 2005, Oxford, UK, http://cmp.felk.cvut.cz/~matas/papers/obdrzalek-tree-bmvc05.pdf

 

[13] V. Lepetit, P. Lagger, and P. Fua. Randomized trees for real-time keypoint recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2005

 

<>[14] Wolfson and Rigoutsos, Geometric Hashing: An Overview, http://graphics.stanford.edu/courses/cs468-01-winter/papers/wr-ghao-97.pdf

 

<>[15]  Indyk, P. and Motwani, R. (1998) Approximate nearest neighbors: Towards removing the curse of dimensionality. In Proc. 30th Ann. ACM Symp. on Theory of Computing,

Dallas, TX.

 

[16] Alexander C. Berg, Tamara L. Berg, Jitendra Malik, Shape Matching and Object Recognition using Low Distortion Correspondence, CVPR 2005


[17] F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce. Object modeling and recognition using local affine-invariant image descriptors and multi-view spatial contraints. Accepted for IJCV.

 

[18] Jiri Matas and Ondrej Chum. Randomized ransac with T_d test.
Image and Vision Computing, 22(10):837-842, September 2004

 

[19] Greg Mori, Jitendra Malik, Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA (2003).  
http://www.cs.berkeley.edu/~mori/

[20] Maximilian Riesenhuber and Tomaso Poggio, "Models of object recognition," Nature Neuroscience, 3 (2000), pp. 1199 - 1204.

 

[21] Freund and Schapire, "A short introduction to boosting," JJSAI, 1999

 

[22] Paul Viola and Michael Jones, "Rapid object detection using a boosted cascade of simple features," Conference on Computer Vision and Pattern Recognition, 2001, pp. 511-518.

 
[23] Jan Sochman Jiri Matas, WaldBoost – Learning for Time Constrained Sequential Detection, CVPR 05, http://cmp.felk.cvut.cz/~matas/papers/sochman-waldboost-cvpr05.pdf

 

[24] Rob Fergus, Pietro Perona, and Andrew Zisserman, "Object Class Recognition by Unsupervised Scale-Invariant Learning," Conference on Computer Vision and Pattern Recognition, (2003)

[25] K. Grauman and T. Darrell.  The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features. To appear, Proceedings of the IEEE International Conference on Computer Vision, Beijing, China, October 2005.

[26] A.A. Efros and T.K. Leung, "Texture Synthesis by Non-parametric Sampling," International Conference on Computer Vision (1999).

[27] Erik B. Sudderth, Antonio Torralba, William T. Freeman, and Alan S. Willsky, Learning Hierarchical Models of Scenes, Objects, and Parts, ICCV 2005

[28] Xin Fan, Chun Qi Dequn Liang Hua Huang, Probabilistic Contour Extraction Using Hierarchical Shape Representation

[29] Epshtein, Ullman, Identifying Semantically Equivalent Object Fragments

[30] Histograms of Oriented Gradients for Human Detection, N. Dalal and B. Triggs. CVPR 2005 I:pp.886-893.

[31] Robert Strzodka, et al A Graphics Hardware Implementation of the Generalized Hough Transform for fast Object Recognition, Scale, and 3D Pose Detection.

[32] Dirk Walther, Ueli Rutishauser, Christof Koch, Pietro Perona, Selective visual attention enables learning and recognition of multiple objects in cluttered scenes