PeopleofSuperintelligence

Researcher

Simone Marinai

Simone Marinai is a researcher in pattern recognition and machine learning whose work focuses on extracting information from documents. He earned an electronic engineering degree in 1993 and a PhD in 1996 at the University of Florence, where he worked as a researcher from 2000 to 2019. His work uses neural networks to count records in historical handwriting, creates synthetic documents for training, applies graph networks to document understanding and grounds answers with bounding boxes. He led IAPR committees, became an IAPR Fellow in 2026, and as of October 2026 is an associate professor in the University of Florence's Department of Information Engineering.

Works
145
Citations
1,998
h-index
24
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1993–1996

    Electronic engineering and a PhD

    He graduates in electronic engineering at the University of Florence in 1993 and earns a PhD in computer and automation engineering there in 1996.

  2. 2000–2019

    Researcher at the University of Florence

    He works as a University Researcher in the Department of Systems and Informatics at the University of Florence from 2000 to 2019.

  3. 2004–2008

    Chair of IAPR's neural networks committee

    From 2004 to 2008, he chairs IAPR Technical Committee TC3 on Neural Networks and Computational Intelligence.

  4. 2014–2020

    IAPR executive leadership

    He serves as IAPR's second vice-president from 2014 to 2016, president from 2016 to 2018, and past president from 2018 to 2020.

  5. 2016–2023

    CNNs, DocEmul and Doc2Graph

    In 2016, he coauthors *Record Counting in Historical Handwritten Documents with Convolutional Neural Networks*, which uses CNNs to count records in historical handwritten documents. In 2017, he coauthors *DocEmul*, a toolkit that generates synthetic documents for training document-analysis systems. He also coauthors the 2022 Doc2Graph preprint; its 2023 ECCV workshop paper presents a graph-neural-network framework evaluated on key-information extraction, invoice-layout analysis and table detection.

  6. 2025

    Bounding boxes for document answers

    In 2025, he coauthors *Towards Reliable and Interpretable Document Question Answering via VLMs*, which introduces DocExplainerV0, a plug-and-play module that predicts bounding boxes to locate generated answers in documents.

  7. 2026

    An IAPR Fellowship

    The IAPR names him a Fellow in 2026 for contributions to document recognition and retrieval and service through leadership positions.

  8. As of October 2026

    Associate professor at Florence

    As of October 2026, he is an associate professor in the Department of Information Engineering at the University of Florence. His research focuses on pattern recognition and machine learning for information extraction from digital-born and digitized documents.

Career

  1. Since 2000University of FlorenceUniversity Researcher
  2. 2004–2020International Association for Pattern RecognitionChair, Second Vice-President

Education

  1. 1996University of FlorencePhD
  2. 1993University of FlorenceElectronic engineering degree

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of Florence. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes University of Florence. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Florence. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Simone Marinai yet. Send us a free-licensed photo.

  1. Marinai Simone | Scheda personale | CercaChi - UniFI cercachi.unifi.it. Checked 20 October 2026.
  2. [1610.07393] Record Counting in Historical Handwritten Documents with Convolutional Neural Networks arxiv.org. Checked 20 October 2026.
  3. [1710.03474] DocEmul: a Toolkit to Generate Structured Historical Documents arxiv.org. Checked 20 October 2026.
  4. [2208.11168] Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks arxiv.org. Checked 20 October 2026.
  5. [2509.10129] Towards Reliable and Interpretable Document Question Answering via VLMs arxiv.org. Checked 20 October 2026.
  6. Chronological List of IAPR Fellows – International Association for Pattern Recognition iapr.org. Checked 20 October 2026.