Matteo Stefanini

Matteo Stefanini

PhD Candidate in Artificial Intelligence - TEDx Organizer


University of Modena and Reggio Emilia


Hi there!

Currently I am PhD Candidate in Artificial Intelligence, studying Deep Learning and Computer Vision at AImagelab, UniMoRe. Working to connect Vision and Language under the supervision of Rita Cucchiara and Lorenzo Baraldi.

I aim to couple my passion for learning and my drive to motivate people around me. I believe AI will push human life and medical fields to new universal missions.

I’m also a TEDx Organizer in the biomedical valley of Mirandola (MO). Join us!


  • Artificial Intelligence and Deep Learning
  • Computer Vision and Language
  • Connecting AI with Genomics and Biomedical fields
  • Startup and Management


  • PhD in Artificial Intelligence, 2019 - present

    University of Modena and Reggio Emilia

  • MEng in Computer Science Engineering - Laurea Magistrale in Ingengeria Informatica, 2018

    University of Modena and Reggio Emilia

  • MSc in Management of Innovation and Entrepreneurship - (Laurea Magistrale), 2016

    University of Milan

  • BEng in Management Engineering - Laurea in Ingegneria Gestionale, 2013

    University of Bologna Alma Mater Studiorum


TEDx Mirandola

Ideas worth spreading. Matters of Life 2021. CALL TO ACTION!

Recent & Upcoming Talks

Learning to Learn in the Artificial Intelligent era

I didn’t want to study when I was younger, and now I’m here trying to motivate young people to do it. There are unprecedented opportunities of Artificial Intelligence in our times. LEARN MORE

Recent Publications

Learning to Select:A Fully Attentive Approach for Novel Object Captioning

ACM International Conference on Multimedia Retrieval - ICMR 2021

A Novel Attention-based Aggregation Function to Combine Vision and Language

International Conference on Pattern Recognition - ICPR 2020

Meshed-Memory Transformer for Image Captioning

IEEE/CVF Conference on Computer Vision and Pattern Recognition - CVPR 2020

Explaining digital humanities by aligning images and textual descriptions

Pattern Recognition Letters - PRL 2019

Artpedia: A New Visual-Semantic Dataset with Visual and Contextual Sentences

International Conference on Image Analysis and Processing - ICIAP 2019