|
Th 2:00- 3:20pm, DBH 1423
Course Code: 35520 OverviewWe will read and discuss recent papers in the compuer vision literature. Discussion will be led by a different student each week. I would like to try and focus our efforts on understanding the problem of modeling interactions between segmentation, scene geometry, context and recognition. There is a proposed list of recent papers [here] Schedule:
Graph cut based image segmentation with connectivity priors S. Vicente, V. Kolmogorov, C. Rother, CVPR 2008
Interactive Graph Cuts for Optimal Boundary & Region Segmentation
Y. Boykov. M-P Jolly, ICCV 2001
GrabCut -- Interactive Foreground Extraction using Iterated Graph Cuts C. Rother, V. Kolmogorov, A. Blanke, SIGGRAPH 2004.
"Dynamic Graph Cuts for Efficient Inference in Markov Random Fields"
P. Kohli, P. Torr, IEEE PAMI 2007
Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes E. Sudderth, M. Jordan, NIPS 2008
Learning to
Combine Bottom-Up and Top-Down Segmentation, Levin and Weiss, ECCV'06.
Bottom-up Recognition
and Parsing of the Human Body, P. Srinivasan and J. Shi, CVPR 2007
Auto-context and Its Application to High-level Vision Tasks, Zhuowen Tu, CVPR, 2008 Properties and applications of shape recipes A. Torralba and W. T. Freeman, CVPR 2003.
Example Based 3D Reconstruction from Single 2D Images, T. Hassner and R. Basri, CVPR 2006.
Geometric context from a single image, Hoiem, Efros, Hebert, ICCV 2005.
Make3D: Learning 3-D Scene Structure from a Single Still Image, A. Saxena, M. Sun, A. Ng, IEEE PAMI, 2008.
Closing the Loop in Scene Interpretation D. Hoiem, A. Efros, M. Hebert, CVPR 2008
Cascaded Classification Models: Combining Models for Holistic Scene Understanding
G. Heitz, S. Gould, A. Saxena, D. Koller, NIPS 2008
|