Machine Learning and Object Recognition 2015-2016

When: Fridays between 9h45-12h45.
Where: ENSIMAG, room H101.
Who: Lectures by Cordelia Schmid and Jakob Verbeek.
Grading: Final grades are determined as follows
- 50% written exam,
- 25% paper presentation,
- 25% quizes on the presented papers.
Paper presentations:
- each student presents once,
- each paper is presented by a team of two students,
- presentations last for 15 minutes, time yours in advance!

Class 1: November 20, 2015

Jakob Verbeek: Introduction [slides]
Jakob Verbeek: Clustering with k-means and mixture of Gaussians [slides]
Students selects papers they will present.

Class 2: November 27, 2015

Cordelia Schmid: Local invariant features [slides]
Cordelia Schmid: Efficient visual search of local features [slides]

Class 3: December 4, 2015

Cordelia Schmid: Bag-of-features for category classification [slides]
Cordelia Schmid: Category localization [slides]
Student presentation: Nikita Dvornik, Distinctive image features from scale-invariant keypoints.
Student presentation: Hang Yu, Structured Forests for Fast Edge Detection.

Class 4: December 11, 2015

Jakob Verbeek: Generative and Discriminative classification [slides]
Student presentation: Maxime Garcia, Beyond bags of features: spatial pyramid matching for recognizing natural scene categories .
Student presentation: Maha Alsayasneh, Efficient Subwindow Search: a Branch and Bound Framework for Object Localization.

Class 5: December 18, 2015

Jakob Verbeek: Fisher vectors [slides] + Introduction neural networks [slides]
Student presentation: Mina Khalil, Segmentation as selective search for object recognition.
Student presentation: Nachwa Abou Bakr, Rich feature hierarchies for accurate object detection and semantic segmentation.

Class 6: January 8, 2016

Cordelia Schmid: Action recognition [slides] + Optical flow [slides]
Student presentation: Gianni Delannoye-Vignoble, Action Recognition with Improved Trajectories.
Student presentation: Anuvabh Dutt, Fisher vector faces in the wild .

Exam

From 9am to 12am, January 29 2016, Ensimag room D207.
prepare from lecture slides, presented papers, and last year's exam.
You can bring printouts of the research paper presented in the lectures, but not your notes or anything else.