Block-Seminar "Machine Learning for Computer Vision"
Language
English
Termine und Informationen
Erster Termin für Themenvergabe |
Mittwoch, 21.10.2009, 11-13 Uhr, Raum FR 6046 |
Weitere Termine und Raum |
Nach Absprache |
verantwortlich |
|
Ansprechtpartner(in) |
|
Sprechzeiten |
nach Vereinbarung |
Themen
Das Blockseminar wird Artikel der Machine Learning Methoden fuer die Aufgaben in Computer Vision besprechen.
- image representations including higher-order features and attributes
- object and scene categorization
- object detection and localization
- image segmentation
- large margin classifiers including multiple kernel learning
- conditional random fields and topic models
- learning (with) taxonomies
- active learning and user feedback
Literatur und Links
object and scene categorization
G. Csurka, C. Bray, C. Dance, and L. Fan, “Visual categorization with bags of keypoints,”in Workshop on Statistical Learning in Computer Vision, ECCV, Prague, Czech Republic, May 2004, pp. 1–22.
http://www.cs.utexas.edu/~grauman/courses/spring2007/395T/papers/csurka_dance_bags_keypoints.pdf
Betreuer:
S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, New York, USA, June 2006, pp. 2169–2178.
http://people.cs.ubc.ca/~lowe/525/lazebnik06.pdf
Betreuer:
M. Varma and D. Ray, “Learning the discriminative power-invariance trade-off,” in Proceedings of the IEEE 11th International Conference on Computer Vision (ICCV ’07), 2007, pp. 1–8.
http://dx.doi.org/10.1109/ICCV.2007.4408875
Betreuer:
image representations including higher-order features and attributes
object detection and localization
image segmentation
J. Shi and J. Malik, "Normalized Cuts and Image Segmentation", IEEE Transactions on Pattern Analysis and Machine Intel ligence, 22(8):888–905, August 2000.
http://people.csail.mit.edu/torralba/courses/6.870/papers/shi00.pdf
Betreuer:
large margin classifiers including multiple kernel learning
G. R. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui, and M. I. Jordan, "Learning the kernel matrix with semidefinite programming", JMLR, 5:27–72, 2004.
Betreuer:
conditional random fields and topic models
learning (with) taxonomies
active learning and user feedback
other topics