Faculty: Francesca Odone
Description: We explore the multifaceted world of image and scene understanding and reconstruction combining computer vision and statistical learning ingredients. Computer vision methods are used to extract information from the visual signals, while we resort to statistical learning to model variability, and to gain robustness and flexibility.
Within this framework we are pursuing research on:
- Learning Behavioral Patterns of Time Series for Video-Surveillance, Francesca Odone, Nicoletta Noceti, Matteo Santoro, Machine Learning for Vision-Based Motion Analysis, 2011
- A Regularized Framework for Feature Selection in Face Detection and Authentication, A. Destrero, C. De Mol, F. Odone, A. Verri, International Journal on Computer Vision, 2009
- A sparsity-enforcing method for learning face features., A. Destrero, C. De Mol, F. Odone, A. Verri, IEEE Transactions on Image Processing, 2009
- Spatio-temporal constraints for on-line 3D object recognition in videos, N. Noceti, E. Delponte, F. Odone, Computer Vision and Image Understanding, 2009
- Building kernels from binary strings for image matching, Francesca Odone, Annalisa Barla, Alessandro Verri, Image Processing, IEEE Transaction on, 2005