CIS 680, Vision and Learning,
In this course, we will explore this connection between vision and learning. We will cover topics in 1) image texture synthesis; 2) object detection and segmentation; 3) dynamic object tracking; 4) object and scene recognition; 5) human activity recognition and inference.
Date
Topics
Papers
Discussion
1/13
**Texture:**synthesis- a practical guide
1/18
Texture: analysis-image statistics, similar measure
Martin & Fowlkes & Malik,
Rubner & Tomasi & Guibas,
Puzicha et.al.
1/20
**Texture:**synthesis/analysis: probabilistic formulation
1/25
**Texture:**synthesis/analysis: probabilistic formulation
1/27
**Object Detection:**face detection- statistical approaches
Scheinderman &Kanade,
Viola &Jones
2/1
**Object Detection:**more on boosting &bagging
2/3
Object Detection: flexible object detection via Graphical Models
2/8
Object Detection: flexible object detection via Graphical Models
2/10
Object Detection: efficient inference procedures for Graphical models(HMM, Tree, MRF):
Tutorial, Ghahramani &Jordan,
Smyth &Heckerman,
2/15
Object Detection: Learning graphical models from examples
Song & Goncalves &Perona
Fergus, Perona, & Zisserman
2/17
Object Detection: Review on EM, HMM
2/22
Object Detection: variational approach for graph inference
Jordan &Ghahramani & Jaakkola & Saul
Saul, et.al.
2/22
Object Tracking: Sampling, particle filtering
2/24
Object Tracking: Markov Chain Monte Carlo(MCMC) methods
3/1
Image Representation: PCA, ICA, Mixture Models
Bell & Sejnowski
Roweis &Ghahramani
3/15
Image Representation: Learning Image Features
Lee & Seung
Stauffer & Grimson
3/16
Object Recognition: Digit Recognition with Shape Context,
3/17
Object Recognition: Digit/Face Recognition, Support Vector Machine(SVM),
3/22
Object Recognition: Neutral Net,
3/24
Object Recognition: Neutral Net,
3/29
**Object Recognition:**Multi-class Object Recognition
3/31
Grouping: Object Segmentation: Graph cuts approaches
4/5
**Grouping:**Object Segmentation: Graph cuts approaches, Multiscale Graph Cuts
4/7
**Grouping:**Stereophesis, Image labeling: Markov Random Field, and Graph Cuts
Ishikawa Geiger,Boykov, Veksler, Zabih
4/12
Grouping: Grouping with Partial labeling
4/14
**Grouping:**Co-Training, knowledge transfer
Barnard, et. al., Blum & Mitchell,
4/22(class Tu. cancelled)
Action Recognition: Learning Grammatical models of Human Actions
4/26
Review