Note: papers highlighted in red are reading assignments for each class

1. Overview
   Date: February 29, 2004
   Speakers: Ronen Basri
   Lecture material:
   
   • PowerPoint slides (3.6Mb)
     (These slides cover only part of the lecture.)
   
     To the schedule
   
   
2. Visual Imitation: Linking Vision and Action
   Date: March 14, 2004
   Speakers: Lior Noy
   Lecture material:
   
   • PowerPoint slides (3.65Mb)
   Papers:
   
   • Sensory-Motor Primitives as a Basis for Learning by Imitation:Linking Perception to Action and Biology to Robotics.
     Maja J Mataric, in "Imitation in Animals and Artifacts", Kerstin Dautenhahn and Chrystopher Nehaniv, eds., MIT Press, 2002, 392-422
     Download (0.2Mb PDF)
     
   • Robots that imitate humans.
     Scassellati B. Breazeal C. Trends in Cognitive Science, 6(11):481 487, November 2002.
     Download (0.22Mb PDF)
     
   • Real-time visual system for interaction with a humanoid robot.
     Ude A., Shibata T. and Atkeson C. G., Robotics and Autonomous Systems, 37:115 125, 2001.
     Download (0.45Mb PDF)
     
   Additional papers:
   
   • Turning to the masters: Motion capturing cartoons.
     Chuang E. Bregler C., Loeb L. and Deshpande H. ACM Transactions on Graphics, 21(3):399 407, July 2002.
     Download (3.3Mb PDF)
     
   • Challenges in Building Robots That Imitate People.
     Breazeal C. and Scassellati B, in "Imitation in Animals and Artifacts", Kerstin Dautenhahn and Chrystopher Nehaniv, eds.The MIT Press, 2002.
     Download (2Mb PDF)
     
   • Computational approaches to motor learning by imitation.
     Schaal, S.; Ijspeert, A.; Billard, A. (2003), Philosophical Transaction of the Royal Society of London: Series B, Biological Sciences, 358, 1431, pp.537-547.
     Download (0.7Mb PDF)
     
   
     To the schedule
   
   
3. Matching with Invariant Features
   Date: March 21, 2004
   Speakers: Darya Frolova, Denis Simakov
   Lecture material:
   
   • PowerPoint slides (2.5Mb)
   • Some Matlab code
     • Harris corner detector
     • Scale-invariant functions: DoG   Laplacian
   Papers:
   • Distinctive image features from scale-invariant keypoints.
     David G. Lowe, accepted for publication in the International Journal of Computer Vision, 2004.
     Download (0.5Mb PDF)
     
   • Viewpoint invariant texture matching and wide baseline stereo.
     Frederik Schaffalitzky and Andrew Zisserman, 2001, ICCV 2003.
     Download (1.5Mb PDF)
     
   • A performance evaluation of local descriptors.
     K. Mikolajczk and C. Schmid, In IEEE Conference on Computer Vision and Pattern Recognition, June 2003
     Download (0.4Mb PDF)
     
   • Wide baseline stereo matching based on local, affinely invariant regions.
     Tinne Tuytelaars and Luc Van Gool, BMVC: 412-425, 2000.
     Download (0.8Mb PDF)
     
   • Rotational invariants for wide-baseline stereo.
     Jirí Matas, Petr Bílek, and Ondrej Chum. International Research Report MS03-146, Center for Machine Perception, K333 FEE Czech Technical University, Prague, Czech Republic, March 2003.
     Download (0.32Mb PDF)
     
   
     To the schedule
   
   
4. Object Recognition and Classification
   Date: March 28, 2004
   Speakers: Shimon Ullman
   Papers:
   • Visual Features of Intermediate Complexity and Their Use in Classification.
     Shimon Ullman, Michel Vidal-Naquet and Erez Sali, Nature Neuroscience 2002.
     Download (0.64Mb PDF)
     
   • Class-specific, Top-down Segmentation.
     Eran Borenstein and Shimon Ullman, ECCV 2002.
     Download (6.5Mb PDF)
     
   • View-Invariant Recognition Using Corresponding Object Fragments.
     Evgeniy Bart, Evgeny Byvatov and Shimon Ullman, ECCV 2004.
     Download (0.2Mb PDF)
     
   
     To the schedule
   
   
5. A Bayesian Approach to Recognition
   Date: April 04, 2004
   Speakers: Moshe Blank, Ita Lifshitz
   Lecture material:
   
   • PowerPoint slides (8.3Mb)
   Papers:
   • Object Class Recognition by Unsupervised Scale-Invariant Learning.
     Fergus, R. , Perona, P. and Zisserman, A., Proc. of the IEEE Conf on Computer Vision and Pattern Recognition 2003
     Download (3.6Mb PDF)
     
   • A Bayesian approach to unsupervised One-Shot learning of Object categories.
     L. Fei-Fei, R. Fergus, and P. Perona, Proc. ICCV. 2003
     Download (0.9Mb PDF)
     
   
     To the schedule
   
   
6. Approximate Nearest Neighbor (Local Sensitive Hashing) - Theory
   Date: April 18, 2004
   Speakers: Uri Klein, Erez Eyal
   Lecture material:
   
   • PowerPoint slides (800Kb)
   • Additional slides:
     • Algorithms for Nearest Neighbor Search (60Kb PPT)
       Piotr Indyk
     • Approximate Nearest Neighbor in High Dimensions via Hashing (800Kb PS)
       Aris Gionis, Piotr Indyk and Rajeev Motwani
     • Efficient Nearest Neighbor Searching for Motion Planning (1Mb PPT)
       Anna Atramentov and Steven M. LaValle
   • Additional papers:
     • Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality (preliminary version) (270Kb PS)
       Piotr Indyk and Rajeev Motwani, 1998
     • Two Algorithms for Nearest­Neighbor Search in High Dimensions (255Kb PS)
       Jon M. Kleinberg, 1997
   Papers:
   • Nearest Neighbors in High Dimensional Spaces.
     A Tutorial by Piotr Indyk.
     Download (0.52Mb PS)
     
   • Efficient Search for Approximate Nearest Neighbor in High Dimensional Spaces.
     E. Kushilevitz, R. Ostrovsky, and Y. Rabani. SIAM J. Comput., 30(2):457—474, 2000. Preliminary version appeared in STOC'98.
     Download (0.32Mb PDF)
     
   • Approximate nearest neighbor searching.
     S. Arya and D. M. Mount, Proc. 4th Ann. ACM-SIAM Symposium on Discrete Algorithms (SODA'93), 1993, 271-280.
     Download (0.21Mb PS)
     Code can be found here.
   
     To the schedule
   
   
7. Approximate Nearest Neighbor - Applications to Vision and Matching
   Date: May 02, 2004
   Speakers: Lior Shoval, Rafi Haddad
   Lecture material:
   
   • PowerPoint slides (6.12Mb)
   Papers:
   • Video Google: A Text Retrieval Approach to Object Matching in Videos.
     Sivic, J. and Zisserman, A., Proceedings of the International Conference on Computer Vision (2003)
     Download (1.5Mb PDF)
     
   • Recognizing Objects in Range Data Using Regional Point Descriptors.
     A. Frome, D. Huber, R. Kolluri, T. Bulow, and J. Malik. To appear in European Conference on Computer Vision, Prague, Czech Republic, 2004.
     Download (1.15Mb PDF)
     
   • See also recent NIPS03 workshop on Approximate Nearest Neighbors Methods for Learning and Vision.
     
   
     To the schedule
   
   
8. Action Recognition
   Date: May 09, 2004
   Speakers: Ronen Deitch
   Papers:
   • Recognizing Action at a Distance.
     A.A. Efros, A.C. Berg, G. Mori, J. Malik, Proceedings of the International Conference on Computer Vision (2003)
     Download (1.57Mb PDF)
     
   • The Visual Analysis of Human Movement: A Survey.
     D.M. Gavrila, Computer Vision and Image Understanding, vol.73, no.1, pp.82-98, 1999.
     Download (0.6Mb PDF)
     
   • Event-Based Analysis of Video.
     L. Zelnik-Manor, M. Irani, CVPR 2001.
     Download (0.78Mb PDF)
     
   • Parameterized Modeling and Recognition of activities.
     Y. Yacoob, M.J. Black, Computer Vision and Image Understanding. 73(2), pp. 232-247, 1999.
     Download (2.7Mb PDF)
     
   • The Representation and Recognition of Action Using Temporal Templates.
     J.W. Davis, A.F. Bobick, CVPR 1997.
     Download (1.5Mb PS.GZ)
     
   • Recognizing and Tracking Human Action.
     J. Sullivan and S. Carlsson, ECCV 2002.
     Download (0.6Mb PDF)
     
   
     To the schedule
   
   
9. Mean Shift
   Date: May 16, 2004
   Speakers: Bernard Sarel, Yaron Ukrainitz
   Lecture material:
   
   • PowerPoint slides (7.5Mb)
   Papers:
   • Mean Shift: A Robust Approach toward Feature Space Analysis.
     D. Comaniciu, P. Meer, IEEE Trans. Pattern Analysis Machine Intell., Vol. 24, No. 5, 603-619, 2002
     Download (3.17Mb PDF)
     Segmentation results for the paper
     
   • Mean-shift Blob Tracking through Scale Space.
     R. Collins, Computer Vision and Pattern Recognition (CVPR'03), IEEE, June, 2003.
     Download (0.3Mb PDF)
     
   • Kernel-Based Object Tracking.
     Dorin Comaniciu, Visvanathan Ramesh, Peter Meer.
     Download (2.7Mb PDF)
     
   
     To the schedule
   
   
10. Information Bottleneck - Theory and Applications
    Date: May 23, 2004
    Speakers: Lena Gorelick, Boris Epshtein
    Lecture material:
    
    • PowerPoint slides (7.5Mb)
    • Simulations of Blahut-Arimoto algorithm (AVI files up to 1.5Mb)
      Iterations for different complexity-distortion tradeoffs:
      • small beta (small clustering complexity)  
      • intermediate beta   
      • large beta (large clustering complexity)    
      Varying beta (results after convergence)
    • Matlab implementation
      • Blahut-Arimoto
      • Information Bottleneck
    Papers:
    • The Information Bottleneck method.
      N. Tishby, F. Pereira, and W. Bialek. In Proc. 37th Allerton Conference on Communication and Computation, 1999.
      Download (0.14Mb PDF)
      
    • The Information Bottleneck: Theory and Applications.
      N. Slonim. Ph.D. thesis under the supervision of Prof. N. Tishby, The Hebrew University, 2002.
      Download (1Mb PS.GZ)
      
    • Applying the Information Bottleneck Principle to Unsupervised Clustering of Discrete and Continuous Image Representations.
      Shiri Gordon, Hayit Greenspan, Jacob Goldberger, ICCV 2003
      Download (0.5Mb PDF)
      
    • Parametric Distributional Clustering for Image Segmentation.
      Lothar Hermes, Thomas Zoller, and Joachim M. Buhmann. ECCV 2002, vol. 3, pp. 577-591, LNCS 2352, Springer, 2002
      Download (1.26Mb PDF)
      
    
      To the schedule
    
    
11. Information Bottleneck vs. Maximum Likelihood
    Date: May 30, 2004
    Speakers: Felix Polyakov
    Lecture material:
    
    • PowerPoint slides (2.5Mb)
    Papers:
    • Maximum Likelihood and the Information Bottleneck.
      N. Slonim and Y. Weiss. In advances in Neural Information Processing Systems (NIPS-15), 2002.
      Download (90Kb PS.GZ)
      
    • The Information Bottleneck: Theory and Applications.
      N. Slonim. Ph.D. thesis under the supervision of Prof. N. Tishby, The Hebrew University, 2002.
      Download (1Mb PS.GZ)
      
    • A view of the EM algorithm that justifies incremental, sparse, and other variants.
      Neal, R.M. and Hinton, G.E. , in M. I. Jordan (editor) Learning in Graphical Models, pp. 355-368, Dordrecht: Kluwer Academic Publishers (1998)
      Download (0.15Mb PDF)
      
    
      To the schedule
    
    
12. The "Gist" of a Scene
    Date: June 06, 2004
    Speakers: Garold Fuks, Trayambaka Karra
    Lecture material:
    
    • PowerPoint slides (8Mb)
    Papers:
    • Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes.
      K. Murphy, A. Torralba and W. Freeman.
      Download (0.17Mb PDF)
      
    • Epitomic Analysis of Appearance and Shape.
      Nebojsa Jojic, Brendan Frey, Anitha Kannan. In Proc. ICCV, pages 34-41, 2003.
      Download (0.84Mb PDF)
      Project page
      
    
      To the schedule