Week 1: Introduction, Matlab Tutorial
Week 2: Image Filtering
- Slides: PDF
- Here are the codes I demoed in the class.
Try the template matching code
Pay attention to how "correlation" and "convolution" are used.
Compare with the simple version
Try the code on a template image
and two test images
Week 3: Features
- Slides on image features: PDF
- Corner detection code: harris.m
- Slides on seam carving: PDF
Week 4: Shape
- Slides on binary images: PDF
- Slides on shape: PDF
Week 5: Model Fitting
Week 6: Camera Model and 3D Reconstruction
Week 7: Motion
Week 8: Tracking
Week 9-10: Action Recognition
Week 10-11 Human Pose
- A. Efros, A. Berg, G. Mori, J. Maliak
"Recognizing Actions at a Distance", ICCV '03.
- E. Shechtman and M. Irani, Space-time behavior based correlation - OR -
How to tell if two underlying motion fields are similar without computing them? IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 29(11): 2045-2056, November 2007.
- L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, Actions as Space-Time Shapes. In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 29(12): 2247-2253, December 2007.
- Action recongnition using space-time interest point.
- Action detection using trajectories.
Week 12 Recognition, Retrieval
- Greg Mori and Jitendra Malik, Recovering 3d Human Body Configurations Using Shape Contexts, IEEE Tr
ansactions on Pattern Analysis and Machine Intelligence (T-PAMI), 28(7):1052-1062, July, 2006.
- P. Felzenszwalb, D. HuttenlocherPictorial Structures for Object Recognition
International Journal of Computer Vision, Vol. 61, No. 1, January 2005.Pose Page
- D. Ramanan, D. A. Forsyth, A. Zisserman. "Tracking People by Learning their Appearance" IEEE Pattern Analy
sis and Machine Intelligence (PAMI). Jan 2007.
- C. J. Taylor, "Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalib
Computer Vision and Image Understanding, Vol: 80, No: 10, Pgs: 349-363, October 2000.