Sanja Fidler
I am currently a postdoc with Prof. Sven Dickinson at University of Toronto. I finished my PhD in 2010 at University of Ljubljana in the group of Prof. Ales Leonardis. In 2010, I was visiting
Prof. Trevor Darrell's group at the International Computer Science Institue (ICSI) as well as at UC Berkeley. For more information see my CV.
Research
During my PhD I was working on hierarchical object class recognition and detection. My main research interests are object detection, 3D object recognition, segmentation and scene understanding.
Publications
Journal papers
- S. Fidler, M. Boben, A. Leonardis. Learning a Hierarchical Compositional Shape Vocabulary for Multi-class Object Representation. Submitted.
- L. Fürst, S. Fidler, A. Leonardis, Selecting features for object detection using an AdaBoost-compatible evaluation function. Pattern Recognition Letters, Vol. 29, No. 11, pp. 1603-1612. [pdf]
- S. Fidler, D. Skocaj, A. Leonardis. Combining Reconstructive and Discriminative Subspace Methods for Robust Classification and Regression by Subsampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2006, vol. 28, no. 3, pp. 337-350. [pdf][code]
Book chapter
- S. Fidler, M. Boben, A. Leonardis. Learning Hierarchical Compositional Representations of Object Structure. In: Object Categorization: Computer and Human Vision Perspectives, Editors: S. Dickinson, A. Leonardis, B. Schiele and M. J. Tarr, Cambridge university press, 2009. In press. [link to book]
- M. Fritz, M. Andriluka, S. Fidler, M. Stark, A. Leonardis, B. Schiele: Categorial Perception, In Henrik I. Christensen and Geert-Jan Kruijff and Aaron Sloman and Jeremy Wyatt, editors, Cognitive Systems, Springer, to appear.
Conference papers
- J. Yao, S. Fidler, R. Urtasun. Describing the Scene as a Whole: Joint Object Detection, Scene Classification and Semantic Segmentation. CVPR'12, to appear.
- Z. Zhang, S. Fidler, J. W. Waggoner, Y. Cao, J. M. Siskind, S. Dickinson, W. Wang. Super-edge grouping for object localization by combining appearance and shape information. CVPR'12, to appear.
- A. Barbu, A. Bridge, Z. Burchill, D. Coroian, S. Dickinson, S. Fidler, A. Michaux, S. Mussman, S. Narayanaswamy, D. Salvi, L. Schmidt, J. Shangguan, J. Siskind, J. Waggoner, S. Wang, J. Wei, Y. Yin, and Z. Zhang. Video In Sentences Out. Conference on Uncertainty in Artificial Intelligence (UAI), 2012.
[pdf]
- W. May, S. Fidler, A. Fazly, S. Stevenson, and S. Dickinson. Unsupervised Disambiguation of Image Captions. First Joint Conference on Lexical and Computational Semantics (*SEM), 2012.
- T. Lee, S. Fidler, A. Levinshtein, and S. Dickinson. Learning Categorical Shape from Captioned Images. Canadian Conference on Computer and Robot Vision (CRV), Toronto, ON, May 2012
- S. Karayev, M. Fritz, S. Fidler, T. Darrell. A Probabilistic Model for Recursive Factorized Image Features. CVPR'11.
- S. Fidler, M. Boben, A. Leonardis. A coarse-to-fine Taxonomy of Constellations for Fast Multi-class Object Detection. ECCV 2010. [pdf]
- S. Fidler, M. Boben, A. Leonardis. Evaluating multi-class learning strategies in a generative hierarchical framework for object detection. NIPS 2009 [pdf]
- S. Fidler, M. Boben, A. Leonardis. Optimization framework for learning a hierarchical shape vocabulary for object class detection. BMVC 2009.
- S. Fidler, M. Boben, A. Leonardis. Similarity-based cross-layered hierarchical representation for object categorization. CVPR 2008. [pdf]
- A. Leonardis and S. Fidler. Learning hierarchical representations of object categories for robot vision. 13th International Symposium of Robotics Research (ISRR), 2007. Invited paper. [pdf]
- S. Fidler and A. Leonardis. Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts. CVPR 2007. [pdf]
- S. Fidler, G. Berginc, A. Leonardis. Hierarchical Statistical Learning of Generic Parts of Object Structure. CVPR 2006, pp. 182-189. [pdf]
- D. Skocaj, A. Leonardis, S. Fidler. Robust estimation of canonical correlation coefficients. 28th workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR), 2004, pp. 15-22. [pdf]
- S. Fidler, A. Leonardis. Robust LDA classification by subsampling. In: Workshop in Statistical Analysis in Computer Vision in conjunction with CVPR, 2003.
- S. Fidler, A. Leonardis. Robust LDA classification. 27th workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR) 2003, pp. 119-126. Best paper award.
Abstracts
- A. Leonardis and S. Fidler. A hierarchical computational model of statistical learning of two-dimensional visual shapes. 32nd European Conference on Visual Perception (ECVP), 2009.
- S. Fidler, M. Boben, A. Leonardis. A bottom-up and top-down optimization framework for learning a compositional hierarchy of object classes. Extended abstract at the First Workshop on Stochastic Image Grammars (SIG), in conjunction with CVPR’09.
Thesis
- S. Fidler. Independent Component Analysis. Diploma thesis. Faculty of mathematics and physics, University of Ljubljana, 2002. Student thesis award.