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:
- Bidirectional Human-robot action reading, Alessandra Sciutti, Oscar Palinko, Laura Patanè, Francesco Rea, Francesco Nori, Nicoletta Noceti, Francesca Odone, Alessandro Verri, Giulio Sandini, 7th International Workshop on Human-Friendly Robotics (HFR 2014), 2014
- Structured multi-class feature selection with an application to face recognition, Luca Zini, Nicoletta Noceti, Giovanni Fusco, Francesca Odone, Pattern Recognition letters, 2014
- Ask the image: supervised pooling to preserve feature locality, Sean Ryan Fanello, Nicoletta Noceti, Carlo Ciliberto, Giorgio Metta, Francesca Odone, IEEE Conference on Computer Vision and Pattern Recognition, 2014
- Semi-supervised learning of sparse representations to recognize people spatial orientation, Nicoletta Noceti, Francesca Odone, International Conference on Image Processing, 2014
- A spectral graph kernel and its application to collective activities classification, Nicoletta Noceti, Francesca Odone, International Conference on Pattern Recognition, 2014