EE 598 Fall 2005: Readings in Computer Vision and Learning

 

Syllabus

(last update: 2005.11.16)

 

Instructor: Prof. Fei-Fei Li

Office: 2051 Beckman Institute

Phone: (217)244-5510

Email: feifeili@uiuc.edu

Office hour: by appointment

 

Course website: http://courses.ece.uiuc.edu/ece598/ffl/

 

Course assignments**:

Paper presentation + course project

 

Grading policy**:

Paper presentation         25%

Attendance                   5%      

Class participation         10%

Course project               60%

 

Important dates (i.e. don’t miss these classes):

Wed, Sept 7                  paper presentation assigned

Mon, Sept 26                 course project presentation 1: project proposal

Wed, Sept 28                1-page course project proposal due in class

Mon, Oct 24                  course project presentation 2: mid-term progress report

Wed, Oct 26                 2-page course project progress report due in class

Mon-Wed, Dec 5-7       course project final presentation; paper due in class

 

** Please check the first lecture notes for details

 

Syllabus:

 

 

Date

Description

Remark & References

1

Wed, Aug 24

Course introduction; administration;

what is vision

 

2

Mon, Aug 29

No Class

 

3

Wed, Aug 31

No Class

 

4

Mon, Sept 5

Object Recognition: an overview;

Refresher on probability

 

5

Wed, Sept 7

Graphical model tutorial #1;

Overview of papers and presentation assignment

Must attend

6

Mon, Sept 12

Graphical model tutorial #2

 

7

Wed, Sept 14

Graphical model tutorial #3

 

8

Mon, Sept 19

Graphical model tutorial #4;

Overview of the course project

 

9

Wed, Sept 21

1. global statistics methods for recognition (Hongcheng)

- Turk & Pentland 1991

- Belhumeur et al. 1997

2. low level vision (Juan Carlos)

- Freeman et al. 2000

- Tappen & Freeman 2003

10

Mon, Sept 26

Project presentation: what do I plan to do? what do you think? Suggestions?

Must attend

11

Wed, Sept 28

Building blocks – feature detectors and descriptors; (Fei-Fei)

 

4. comparison of detectors and descriptors

(Jilin)

- Milokajczyk et al. 2005a

- Milokajczyk et al. 2005b

12

Mon, Oct 3

5. single object recognition (Allen)

- Lowe 1999

- Brown & Lowe 2003

6. single 3-D object segmentation (Akash)

- Ferrari et al. 2004

- Rothganger et al. 2004

13

Wed, Oct 5

7. object seg. & categ. I (Nicolas)

- Ullman et al. 2001, 2002

8. object seg. & categ. II (Allen)

- Leibe et al. 2004, 2005

14

Mon, Oct 10

9. generative model: layered rep. I (Mandor)

- Torr, et al. 2001

- Kumar et al. 2004, 2005

10. generative model: layered rep. II (Alex)

- Frey et al. 2003

- Winn and Jojic, 2005

15

Wed, Oct 12

11. discriminative model: CRF on segmentation (Mithun)

- Kumar & Herbert 2003

16

Mon, Oct 17

Dr. Silvio Savarese substitute

12. texton and histogram I. (Hao)

- Leung & Malik 2000

- Csurka 2004

13. texton and histogram II. (Himanshu)

- Winn et al. 2005

17

Wed, Oct 19

Work on your course project

 

18

Mon, Oct 24

Project presentation: what have I done? What are the challenges and what do I plan to do?

Must attend

19

Wed, Oct 26

Generative model: the constellation model for object categories

(Fei-Fei)

- Weber et al. 1998

- Fergus et al. 2003

- Fei-Fei et al. 2003

20

Mon, Oct 31

14. discriminative model: NN (Akash)

 

- LeCun et al. 1998, 2004

- Rowley et al. 1998

15. discriminative model: SVM (Mandor)

- Pontil & Verri 1998

21

Wed, Nov 2

16. discriminative model: boosting 1

(Wei)

- Viola & Jones 2000, 2003

- Schneiderman & Kanade 2004

22

Tue, Nov 8

Guest lecturer: Pedro Felzenszwalb

4:30pm - 6pm, Beckman Institute

 

23

Wed, Nov 9

17. generative model: LDA

(Nicolas)

- Blei et al. 2003

 - Barnard et al. 2003

18. generative model: pictures and words (Himanshu)

- Berg et al. 2004

 

 

 

 

24

Mon, Nov 14

19. discriminative model: boosting 2 (Alex)

- Opelt et al. in press

 

20. discriminative model: boosting 3 ( Hao )

- Torralba et al. 2004

25

Wed, Nov 16

21. generative model: objects and scenes

(Juan Carlos)

- Sudderth et al. 2005

- Murphy et al. 2003

natural scene categorization

(Fei-Fei)

- Oliva et al. 2001

- Fei-Fei & Perona 2005

26

Mon, Nov 28

22. hybrid model 1

(Jilin)

- Tu et al. 2005

 

27

Wed, Nov 30

23. generative model: epitome

(Tony)

 - Jojic et al. 2003

- Cheung et al. 2005

24. hybrid model 2

(Hongcheng or Nicolas)

- Holub et al. 2005

28

Mon, Dec 5

Course project final presentation

Beckman Institute Room 3369 1:30pm – 3:30pm 

Must attend

Final paper due in class

29

Wed, Dec 7

Course project final presentation

Beckman Institute Room 3369 1:30pm – 3:30pm 

Must attend

Final paper due in class

 

 

 

 

 

 

 

References

 

  1. K. Barnard, P. Duygulu, D. Forsyth, N. de Freitas, D. Blei and M. Jordan. Matching words and pictures. J. of Machine Learning.  2003.
  2. P. Belhumeur, J. P. Hespanha and D. J. Kriegman. Eigenfaces vs. fisherfraces: recognition using class specific linear projection. PAMI.  1997.
  3. T. Berg, A. Berg, J. Edwards, M. Maire, R. White, Y-W The, E. Learned-Miller and D.A. Forsyth. Names and faces in the news. CVPR. 2004
  4. D. Blei, A. Ng and M. Jordan. Latent Dirichlet allocation. J. of Machine Learning. 2003
  5. E. Borenstein and S. Ullman. Class-specific, top-down segmentation. ECCV. 2002
  6. E. Borenstein, E. Sharon and S. Ullman. Combining top-down and bottom-up segmentation. CVPR. 2002
  7. M. Brown and D. Lowe. Recognizing panoramas. ICCV. 2003
  8. V. Cheung, B. Frey and N. Jojic. Video epitomes. CVPR. 2005
  9. G. Csurka, C.Dance, L. Fan, J. Willamowski and C. Bray. Visual categorization with bags of keypoints. ECCV. 2004
  10. L. Fei-Fei, R. Fergus and P. Perona. A Bayesian approach to unsupervised one-shot learning of object categories. ICCV. 2003
  11. L. Fei-Fei and P. Perona. A Bayesian hierarchical model for learning natural scene categories. CVPR. 2005
  12. R. Fergus, P. Perona and A. Zisserman. Object class recognition by unsupervised scale-invariant learning. CVPR. 2003
  13. V. Ferrari, T. Tuytelaars and L. Van Gool. Simultaneous object recognition and segmentation from single or multiple model views. CVPR. 2004.
  14. W.T. Freeman, E. Pasztor and O. Carmichael. Learning low-level vision. IJCV. 2000
  15. B. Frey, and N. Jojic. A Comparison of algorithms for inference and learning in probabilistic graphical model. IEEE PAMI 2003
  16. B. Frey, N. Jojic and A. Kannan. Learning appearance and transparency manifolds of occluded objects in layers. CVPR. 2003.
  17. A. Holub, M. Welling and P. Perona. Combining generative models and fisher kernels for object recognition. ICCV. 2005.
  18. N. Jojic, B. Frey and A. Kannan. Epitomic analysis of appearance and shape. ICCV. 2003
  19. M.P. Kumar, P. Torr and A. Zisserman. Learning layered pictorial structures from video. 2004.
  20. M.P. Kumar, P. Torr and A. Zisserman. ObjCut. CVPR. 2005
  21. S. Kumar and M. Hebert. Disciminative random fields: a discriminative framework for contextual interaction in classification. ICCV. 2003
  22. Y. LeCun, L. Botton, Y. Bengio and P. Haffner. Gradient-based learning applied to document recognition. PAMI. 1998
  23. Y. LeCun, F.J. Huang and L. Bottou. Learning methods for generic object recognition with invariance to pose and lighting. CVPR. 2004
  24. B. Leibe, A. Leonardis and B. Schiele. Combined object categorization and segmentation with an implicit shape model. ECCV workshop. 2004
  25. B. Leibe, E. Seemann and B. Schiele. Pedestrian detection in crowded scenes. CVPR. 2005
  26. T. Leung and J. Malike. Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV. 2001
  27. D. Lowe. Object recognition from local scale-invariant features. ICCV. 1999
  28. K. Mikolajczyk and C. Schmid. A Performance evaluation of local descriptors. PAMI. 2005
  29. K. Milokajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir and L. Van Gool. A comparison of affine region detectors. IJCV. 2005
  30. K. Murphy, A. Torralba and W.T. Freeman. Using forest to see trees: A graphical model relating features, objects and scenes. NIPS. 2003
  31. A. Oliva and A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV.  2001
  32. Opelt, M. Fussenegger, A. Pinz and P. Auer. Generic object recognition with Boosting. PAMI. In press.
  33. M. Pontil and A. Verri. Support vector machines for 3-D object recognition.  PAMI. 1998
  34. F. Rothganger, S. Lazebnik and J. Ponce. 3D object model and recognition using local affine-invariant image descriptors and multi-view spatial constraints. IJCV. 2004
  35. H. Rowley, S. Baluja and T. Kanade. Neural network-based face detection. PAMI. 1998
  36. H. Schneiderman and T. Kanade. Object detection using the statistics of parts. IJCV. 2004
  37. E. Sudderth, A. Torralba and W.T. Freeman. Learning Hierarchical Models of Scenes, Objects, and Parts. ICCV. 2005
  38. M. Tappen and W.T. Freeman. Comparison of graph cuts with Belief Propagation for stereo, using identical MRF parameters. ICCV. 2003
  39. P. Torr, R. Szeliski and P. Anandan. An integrated Bayesian approach to layer extraction from image sequences. PAMI. 2001
  40. A. Torralba, K. Murphy and W.T. Freeman. Sharing visual features for multiclass and multiview object detection. CSAIL technote. 2004
  41. Z.Tu, X. Chen, A. Yuille and S-C Zhu. Image parsing: unifying segmentation, detection and recognition. IJCV. 2005.
  42. M. Turk and A. Pentland. Eigenfaces for recognition. J. of cognitive neuroscience. 1991.
  43. S. Ullman, M. Vidal-Naquet and E. Sali. Visual features of intermediate complexity and their use in classification. Nature Neuroscience. 2002
  44. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR. 2000
  45. P. Viola and M. Jones. Robust real-time face detection. IJCV. 2004
  46. M. Weber, M. Welling and P. Perona. Unsupervised learning of models for recognition. ECCV. 2000
  47. J. Winn and C. Bishop. Variational Message Passing. J. of Machine Learning. 2004
  48. J. Winn, A. Criminisi and T. Minka. Object categorization by learned universal visual dictionary. ICCV. 2005
  49. J. Winn and N. Jojic. LOCUS: learning object classes with unsupervised segmentation. ICCV. 2005