Group Seminar in

Center for Image and Vision Science (CIVS)

Summer, 2004

Aug 4, 2PM, BH 4760
- Leo Zhu, Visual Object Learning
  - Fergus, R. , Perona, P. and Zisserman, A. Object Class Recognition by Unsupervised Scale-Invariant Learning. Proc. of the IEEE Conf on Computer Vision and Pattern Recognition 2003.
  - Fergus, R. , Perona, P. and Zisserman, A. A Visual Category Filter for Google Images. Proc. of the 8th European Conf. on Computer Vision, ECCV 2004.
  - Fei-Fei, L. , Fergus, R. and Perona, P. A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories. Proc. of the 9th Inter. Conf. on Computer Vision, ICCV 2003.
Aug 11, 2PM, BH 4760
- Cheng-en Guo, Primal Sketch
  - Cheng-en Guo's Ph.D. Thesis
- Yizhou Wang and Ziqiang Liu, Distinctive Image Features from Scale-Invariant Key-points – Lowe’s Method
  - David G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints International Journal of Computer Vision, 60, 2 (2004), pp. 91-110.
- Daniel Cramers, Recent advances on shape priors for level set segmentation: Dynamic labeling, intrinsic alignment and non-parametric density estimation
  - D. Cremers, N. Sochen, C. Schnörr, Multiphase Dynamic Labeling for Variational Recognition-driven Image Segmentation, European Conference on Computer Vision, Prague, 2004. Springer LNCS, Vol. 3024, pp. 74-86.
  - D. Cremers, S. Soatto, A Pseudo Distance for Shape Priors in Level Set Segmentation, 2nd IEEE Intl. Workshop on Variational, Geometric and Level Set Methods (VLSM), Nice, 2003, 169-176.
  - D. Cremers, S. Osher, S. Soatto. Kernel Density Estimation and Intrinsic Alignment for Knowledge-driven Segmentation: Teaching Level Sets to Walk.
Aug 18, 2PM, BH 4760
- Songfeng Zheng, Shape Matching with Belief Propagation
  - Coughlan, J. and Shen, H. Shape Matching with Belief Propagation: Using Dynamic Quantization to Accommodate Occlusion and Clutter, GMVB 2004
  - P.F. Felzenszwalb and D.P. Huttenlocher. Efficient Belief Propagation for Early Vision. Proc. of the IEEE Conf on Computer Vision and Pattern Recognition 2004. Source code available in the link.
Aug 25, 2PM, BH 4760
- Feng Han, Discriminative Models
  - C. Rother, V. Kolmogorov and A. Blake. Interactive Foreground Extraction using Iterated Graph Cuts. ACM Transactions on Graphics (SIGGRAPH'04), 2004.
  - A. Blake, C. Rother, M. Brown, P. Perez, and P. Torr. Interactive image segmentation using an adaptive GMMRF model. Eur. Conf. on Computer Vision, ECCV, Prague, 2004.
  - S. Kumar and M. Hebert, Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification, in proc. IEEE International Conference on Computer Vision (ICCV), October 2003.
- Long Zhu, Discriminate versus Generative Models
  - Rubenstein, D. and Hastie, T. "Discriminative vs Informative Learning" A comparison of two frequently used but different paradigms for training classifiers.
  - Andrew Y. Ng and Michael Jordan. On Discriminative vs. Generative Classifiers: A comparison of logistic regression and Naive Bayes, In NIPS 14,, 2002.
  - Rajat Raina, Yirong Shen, Andrew Y. Ng and Andrew McCallum. Classification with Hybrid Generative/Discriminative Models, In NIPS 16, 2004.
Sep 2, 2PM, BH 4760
- Hong Chen, An Introduction to Max-Flow/Min-Cut Algorithms
  - R.K. Ahuja, T.L. Magnanti, and J.B. Orlin, Network Flows: Theory, Algorithms, and Applications. Prentice Hall, 1993.
  - Here is a course link that reviews the Max-Flow / Min-Cut problem. See lecture 7-11 for details. http://cs261.stanford.edu/
  - Yuri Boykov, Vladimir Kolmogorov, An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision, In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1124-1137, Sept. 2004.
- Xiangrong Chen, Energy Minimization for Computer Vision by Graph Cuts
  - D. Greig, B.Porteous, and A. Seheult, Exact Maximum A Posteriori Estimation for Binary Images, J. Royal Statistical Soc., Series B, vol.51, no. 2, pp.271-279, 1989.
  - Yuri Boykov, Olga Veksler and Ramin Zabih. Fast Approximate Energy Minimization via Graph Cuts, IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11), November 2001. Preliminary version appears in: International Conference on Computer Vision, September 1999
  - Vladimir Kolmogorov and Ramin Zabih. What Energy Functions can be Minimized via Graph Cuts? In: IEEE Transactions on Pattern Analysis and Machine Intelligence, February 2004. Earlier version appears in European Conference on Computer Vision, May 2002 (best paper award).
  - Ramin Zabih. Energy Minimization for Computer Vision via Graph Cuts (video). Microsoft Multi-University / Research Laboratory Seminar Series.