Employee

May 2012
	Mo	Tu	We	Th	Fr	Sa	Su
18	30	01	02	03	04	05	06
19	07	08	09	10	11	12	13
20	14	15	16	17	18	19	20
21	21	22	23	24	25	26	27
22	28	29	30	31	01	02	03

Gökhan BakIr

Position: Research Scientist Unit: Alumni Schölkopf

Publications

Books (1):
•	Bakir GH , Hofmann T , Schölkopf B , Smola AJ , Taskar B and Vishwanathan SVN : Predicting Structured Data, 360, MIT Press, Cambridge, MA, USA, (September-2007).
Articles (2):
•	Wu M , Schölkopf B and BakIr G (April-2006) A Direct Method for Building Sparse Kernel Learning Algorithms Journal of Machine Learning Research 7 603-624.
•	Ilg W , Bakir GH , Mezger J and Giese M (December-2004) On the representation, learning and transfer of spatio-temporal movement characteristics International Journal of Humanoid Robotics 1(4) 613-636.
Conference papers (13):
•	Nowozin S and BakIr G (July-2008) A Decoupled Approach to Exemplar-based Unsupervised Learning In: ICML 2008, 25th International Conference on Machine Learning, ACM Press, New York, NY, USA, 704-711.
•	Nowozin S , BakIr G and Tsuda K (October-2007) Discriminative Subsequence Mining for Action Classification In: ICCV 2007, 11th IEEE International Conference on Computer Vision, IEEE Computer Society, Los Alamitos, CA, USA, 1919-1923.
•	Nowozin S , Tsuda K , Uno T , Kudo T and BakIr G (June-2007) Weighted Substructure Mining for Image Analysis In: CVPR 2007, 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Los Alamitos, CA, USA, 1-8.
•	Wu M , Schölkopf B and BakIr G (August-2005) Building Sparse Large Margin Classifiers In: ICML 2005, 22nd International Conference on Machine Learning, ACM, New York, NY, USA, 996-1003.
•	Bakir GH , Bottou L and Weston J (July-2005) Breaking SVM Complexity with Cross-Training In: Advances in Neural Information Processing Systems 17, Eighteenth Annual Conference on Neural Information Processing Systems (NIPS 2004), MIT Press, Cambridge, MA, USA, 81-88.
•	Kienzle W , BakIr G , Franz M and Schölkopf B (July-2005) Face Detection: Efficient and Rank Deficient In: Advances in Neural Information Processing Systems 17, Eighteenth Annual Conference on Neural Information Processing Systems (NIPS 2004), MIT Press, Cambridge, MA, USA, 673-680.
•	Sinz F , Candela JQ , BakIr G , Rasmussen CE and Franz M (September-2004) Learning Depth From Stereo In: 26th DAGM Symposium, 26th DAGM Symposium, Springer, Berlin, Germany, 245-252.
•	BakIr G , Zien A and Tsuda K (August-2004) Learning to Find Graph Pre-Images In: Pattern Recognition, 26th DAGM Symposium, Springer, Berlin, Germany, 253-261.
•	Bakir GH , Weston J and Schölkopf B (June-2004) Learning to Find Pre-Images In: Advances in Neural Information Processing Systems 16, Seventeenth Annual Conference on Neural Information Processing Systems (NIPS 2003), MIT Press, Cambridge, MA, USA, 449-456.
•	Kienzle W , BakIr G , Franz M and Schölkopf B (2004) Efficient Approximations for Support Vector Machines in Object Detection DAGM 2004, Springer, Berlin, Germany, 54-61.
•	BakIr G , Gretton A , Franz M and Schölkopf B (2004) Multivariate Regression via Stiefel Manifold Constraints DAGM 2004, Springer, Berlin, Germany, 262-269.
•	Ilg W , Bakir GH , Mezger J and Giese MA (July-2003) On the Representation, Learning and Transfer of Spatio-Temporal Movement Characteristics Humanoids Proceedings, 0-0.
•	Ilg W , Bakir GH , Franz MO and Giese M (January-21-2003) Hierarchical Spatio-Temporal Morphable Models for Representation of complex movements for Imitation Learning 11th International Conference on Advanced Robotics, 453-458.
Contributions to books (2):
•	Weston J , Bakir GH , Bousquet O , Mann T , Noble WS and Schölkopf B : Joint Kernel Maps, 67-84. In: Predicting Structured Data, (Ed) G. H. Bakir, MIT Press, Cambridge, MA, USA, (September-2007).
•	BakIr G , Schölkopf B and Weston J : On the Pre-Image Problem in Kernel Methods, 284-302. In: Kernel Methods in Bioengineering, Signal and Image Processing, (Ed) G. Camps-Valls, Idea Group Publishing, Hershey, PA, USA, (January-2007).
Technical reports (3):
•	BakIr G , Wu M and Eichhorn J : Maximum-Margin Feature Combination for Detection and Categorization, Max Planck Institute for Biological Cybernetics, Tübingen, Germany, (2005).
•	Weston J and Bakir GH : Fast Binary and Multi-Output Reduced Set Selection, 132, (November-2004).
•	Bakir GH , Gretton A , Franz MO and Schölkopf B : Multivariate Regression with Stiefel Constraints, 128, MPI for Biological Cybernetics, Spemannstr 38, 72076, Tuebingen, (2004).
Posters (2):
•	Ilg W , Bakir GH , Franz MO and Giese M (February-2003): A Representation of Complex Movement Sequences Based on Hierarchical Spatio-Temporal Correspondence for Imitation Learning in Robotics, 6. Tübinger Wahrnehmungskonferenz (TWK 2003), Tübingen, Germany.
•	Bakir GH , Ilg W , Franz MO and Giese M (February-2003): Constraints measures and reproduction of style in robot imitation learning, 6. Tübinger Wahrnehmungskonferenz (TWK 2003), Tübingen, Germany.
Theses (1):
•	BakIr G : Extension to Kernel Dependency Estimation with Applications to Robotics, Technische Universität Berlin, Berlin, (November-2005). PhD thesis
Talks (1):
•	Wu M , Schölkopf B and BakIr G (August-2005): Building Sparse Large Margin Classifiers, The 22nd International Conference on Machine Learning (ICML 2005), Bonn, Germany.