Machine Learning and Category Representation 2012-2013

When: Fridays between 9h-12h
Where: ENSIMAG building in Montbonnot
Who: Lectures by Cordelia Schmid and Jakob Verbeek.
Grading: Final grades are determined as follows
- 50% written exam,
- 25% paper presentation (done in pairs of students),
- 25% weekly quizes (on the other papers that you did not present yourself).

Schedule is subject to changes, dates are correct

Class 1: November 16, 2012

Jakob Verbeek: Clustering with k-means, and EM for mixture of Gaussians [slides]
Student presentation 1: Shreyas Saxena + Gurkirt Singh [slides]
Scale and affine invariant interest point detectors, Mikolajczyk, Schmid, IJCV 2004.

Jakob Verbeek: classification methods 1 [slides]
Student presentation 2: Prasad Samarakoon + Xinwu Mo [slides]
Visual categorization with bags of keypoints Csurka, Dance, Fan, Willamowski, Bray, ECCV Workshop on Statistical Learning in Computer Vision, 2004

Jakob Verbeek: classification methods 1 + Fisher vector image representation [slides]
Student presentation 3: Camille Schreck + Romain Vavassori [slides]
Beyond bags of features: spatial pyramid matching for recognizing natural scene categories, Lazebnik, Schmid and Ponce, CVPR 2006.
Student presentation 4: JiRi Pytela + Ayan Basu Nath [slides]
Aggregating local descriptors into a compact image representation, Jegou, Perronnin, Douze, Sanchez, Perez, Schmid, PAMI 2012.

Cordelia Schmid: object category localization [slides]
Student presentation 5: Marion Millien-Lepine + Nuwan Jayalath [slides]
Histograms of Oriented Gradients for Human Detection, Dalal, Triggs, CVPR 2005.
Student presentation 6: Simon Chalumeau + Gregoire Vignon [slides]
Object Detection with Discriminatively Trained Part Based Models, Felzenszwalb, Girshick, McAllester and Ramanan, PAMI 2010.
Student presentation 7: Benoit Arbelot + Alejandro Blumentals [slides]
Segmentation as Selective Search for Object Recognition, van de Sande, Uijlings, Gevers, Smeulders, ICCV 2011.

January 2013, time 9 am - 12 am, room H206.
prepare from lecture slides, presented papers, and last year's exam.
You can bring the slides and research papers during the exam, nothing else !