Hey! đź‘‹

I am an assistant professor at the University of Bozen-Bolzano - Faculty of Engineering, and an academic researcher at the ETH ZĂĽrich - Institute for Machine Learning. Prior to that, I was a postdoctoral research fellow at ETH ZĂĽrich and Ca' Foscari University of Venice. I am specialized in theoretically grounded methodologies for computer vision. I am currently working at the intersection of several topics including model robustness assessment and representation learning.

Interests
  • Machine Learning
  • Computer Vision
  • Deep Learning
  • Game Theory
Education

  • Ph.D. in Computer Science, 2021

    Ca' Foscari University of Venice

  • M.sc. Degree in Computer Science, 2016

    Ca' Foscari University of Venice

  • B.Sc. Degree in Computer Science, 2014

    Ca' Foscari University of Venice

Skills

Python
NumPy/PyTorch
R/Statistics
Satellite Imagery
Music

Featured Publications

The Group Loss++: A Deeper Look Into Group Loss For Deep Metric Learning
We adjust Group Loss, and propose Group Loss++, providing a unified framework for retrieval and re-identification
Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixé
Cite DOI
The Group Loss++: A Deeper Look Into Group Loss For Deep Metric Learning
The Group Loss for Deep Metric Embedding
We propose Group Loss, a new loss for deep metric learning tasks, that takes into account all the observations in a mini-batch at the same time
Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixé
Cite DOI
The Group Loss for Deep Metric Embedding
Unsupervised Domain Adaptation Using Graph Transduction Games
We extend a previously proposed graph transduction method to perform unsupervised domain adaptation on image datasets for object recognition
Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich, Twan Van Laarhoven, Elena Marchiori, Marcello Pelillo
Cite DOI
Unsupervised Domain Adaptation Using Graph Transduction Games
Transductive Label Augmentation For Improved Deep Network Learning
We present a technique to automatic label unlabeled images, through the use of a graph transductive algorithm
Ismail Elezi, Alessandro Torcinovich, Sebastiano Vascon, Marcello Pelillo
Cite DOI
Transductive Label Augmentation For Improved Deep Network Learning

Recent Publications

Quickly discover relevant content by filtering publications.
Antonio Emanuele CinĂ , Alessandro Torcinovich, Marcello Pelillo (2022). A Black-Box Adversarial Attack for Poisoning Clustering. In PR.

Cite

Marina Khoroshiltseva, Ben Vardi, Alessandro Torcinovich, Arianna Traviglia, Ohad Ben-Shahar, Marcello Pelillo (2021). Jigsaw Puzzle Solving as a Consistent Labeling Problem. In CAIP.

Alessandro Torcinovich, Marco Fratton, Marcello Pelillo, Alberto Pravato, Alessandro Roncato (2017). A Computer Vision System for Monitoring Ice-Cream Freezers. In ICIAP.

Cite DOI

Marco Fiorucci, Alessandro Torcinovich, Manuel Curado, Francisco Escolano, Marcello Pelillo (2017). On the Interplay between Strong Regularity and Graph Densification. In GbRPR.

Cite DOI

Projects

*
All Deep Learning Other
Example Project
An example of using the in-built project page.
Slides Follow
Example Project

Recent Posts

Popular Topics

Adversarial Learning Artificial Intelligence Black-Box Clustering Commute time Consistent Labeling Deep Learning Deep Metric Learning Derivative-Free Edge detection Game Theory Genetic Algorithms Graph algorithms Graph densification Graph Transduction Ice-cream freezers Image Clustering Image Retrieval Linguistics OS

Contact