PhD, Research Scientist,

Machine Learning, Deep Learning, Computer Vision

Source Code

  GitHub      FSLib Matlab File Exchange


Giorgio Roffo received a European PhD degree in computer vision and pattern recognition from the University of Verona, Italy. He was a research associate at the University of Glasgow. Previously, he was with the Italian Institute of Technology (IIT), Genoa, Italy.

His current research interests are in statistical pattern recognition and computer vision, mainly in deep learning (supervised/

self-supervised learning), feature selection and attention models. On these topics, he has published several papers in prestigious journals and conferences.

He acts as an Associate Editor of the ICPR 2020, the premier world conference in Pattern Recognition.

He is a reviewer for the premier journal of the field IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

He has been awarded the CVPR 2019 Outstanding Reviewers Award (cvpr2019.thecvf.com).

He is in the technical program committee of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), the IEEE International Conference on Computer Vision (ICCV), IEEE European Conference on Computer Vision (ECCV), International Joint Conferences on Artificial Intelligence (IJCAI). 

His publishing track record shows one or more A* papers (top 1% of the SCImago SJR index) per annum while being associated with different institutions. 


  • Infinite Feature Selection: A Graph-based Feature Filtering Approach. G. Roffo, S. Melzi, U. Castellani, A. Vinciarelli, and M. Cristani.  In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2020), DOI 10.1109/TPAMI.2020.3002843.[pdf][arXiv]

  • Automating the Administration and Analysis of Psychiatric Tests: The Case of Attachment in School-Age Children. G.Roffo, D.-B.Vo, A.Sorrentino, M.Rooksby, M.Tayarani, S. Di Folco, H. Minnis, S.Brewster and A.Vinciarelli. In ACM CHI Conference on Human Factors in Computing Systems, (ACM CHI 2019) [pdf][bibtex]
  • Discrete-time evolution process descriptor for shape analysis and matching. Melzi, S., Ovsjanikov, M., Roffo, G., Cristani, M. and Castellani, U. ACM Transactions on Graphics, (TOG 2018). [pdf][bibtex]
  • Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach. G. Roffo, S. Melzi, U. Castellani, and A. Vinciarelli. In Conf. IEEE International Conference on Computer Vision (ICCV 2017). [pdf][bibtex]
  • Infinite Feature Selection. G. Roffo, S. Melzi and M. Cristani. In Conf. IEEE International Conference on Computer Vision (ICCV 2015). [pdf][bibtex]
  • Online Feature Selection for Visual Tracking. G. Roffo, S. Melzi. In Conf. The British Machine Vision Conference (BMVC 2016). [pdf][bibtex]



                      SICSA PECE Grant 2019

                      July 2019

Awarded a SICSA Postdoctoral and Early Career Researcher Exchanges (PECE). 

                     MATLAB Central Coin 2016

                     April 10, 2017

Matlab FileExchange - Recognition for Outstanding Contributions (2016) in Feature Selection. The  Feature Selection Library (FSLib) received more than 3,000 unique downloads in 2016, avg. ~300 downloads pcm (see FSLib online).

CVPR 2019 Reviewer Award

December 2019

 CVPR 2019 Outstanding Reviewers Award


I'm used to post news and updates also on:

Fast Downloads

Copyright 2016-2019 @ All Rights Reserved