PeopleofSuperintelligence

Researcher

Marco Cristani

Marco Cristani is a computer vision researcher whose AI work analyzes social behavior in images and produces fashion images from sketch-and-text prompts. He earned a computer science PhD at Verona after research at USC, then coauthored work on F-formations, group analysis, and visual social distancing. In 2025, he coauthored LOTS, which uses localized sketch and text cues to guide diffusion-based fashion image generation. IAPR named him a Fellow in 2022; as of October 2026, he is a full professor at Verona and leads INTELLIGO Labs' Machine Learning and Computer Vision team.

Timeline

  1. 2004–2006

    A PhD and USC research

    He earns a PhD in computer science at the University of Verona's Department of Computer Science in 2006. From 2004 to 2005, he works as a Research Scholar at the University of Southern California under Ram Nevatia.

  2. 2011

    Social interaction discovery

    At BMVC in 2011, he coauthors “Social interaction discovery by statistical analysis of F-formations,” which uses Hough voting to find F-formation centers. His paper is a reference for IIT's CoffeeBreak dataset, which tests methods for detecting social interactions.

  3. 2015

    Detecting conversational groups

    In 2015, he coauthors “F-Formation Detection: Individuating Free-Standing Conversational Groups in Images,” which uses graph cuts to group people in still images.

  4. 2017

    Group analysis and clothing

    In 2017, he coauthors the book Group and Crowd Behavior for Computer Vision, which covers computer-vision methods for group and crowd analysis. He also coauthors “Clothing and People,” a position paper on how clothing carries social signals people send and perceive.

  5. 2020

    Visual social distancing

    In 2020, with four coauthors, he introduces The Visual Social Distancing Problem, which defines estimating interpersonal distances from images and characterizing groups. The paper connects the task to Social Signal Processing and computer vision.

  6. 2022

    An IAPR Fellowship

    In 2022, IAPR names him a Fellow for contributions to pattern-recognition methods for social signal processing.

  7. 2025

    Fashion image generation

    In 2025, he coauthors LOTS, which combines localized text and sketches to guide a diffusion model in fashion image generation.

  8. As of October 2026

    Professor at Verona

    As of October 2026, he is a full professor in the Department of Engineering for Innovation Medicine at the University of Verona. He leads the Machine Learning and Computer Vision team at INTELLIGO Labs and is an Associate Member of the National Research Council and an External Collaborator at the Italian Institute of Technology (IIT). In the 2025/2026 PhD programme, he teaches Generative AI (part I).

Career

  1. NowUniversity of VeronaFull Professor
  2. NowNational Research CouncilAssociate Member
  3. NowItalian Institute of TechnologyExternal Collaborator
  4. 2004–2005University of Southern CaliforniaResearch Scholar

Education

  1. 2006University of VeronaPhD in computer science

From the biography.

  1. The United States employs an estimated 48% of people shaping AIIncludes Italian Institute of Technology. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes National Research Council. 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. Google has the highest combined h-index among AI organizationsIncludes National Research Council. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes National Research Council. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.

Colleagues

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

Sources and credits

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

  1. Group and Crowd Behavior for Computer Vision - 1st Edition | Elsevier Shop shop.elsevier.com. Checked 21 October 2026.
  2. Social interaction discovery by statistical analysis of F-formations bmva-archive.org.uk. Checked 21 October 2026.
  3. F-Formation Detection: Individuating Free-Standing Conversational Groups in Images | PLOS One journals.plos.org. Checked 21 October 2026.
  4. CoffeeBreak Dataset - Pattern Analysis and Computer Vision - IIT pavis.iit.it. Checked 21 October 2026.
  5. [1704.02231] Clothing and People - A Social Signal Processing Perspective arxiv.org. Checked 21 October 2026.
  6. [2005.04813] The Visual Social Distancing Problem arxiv.org. Checked 21 October 2026.
  7. Chronological List of IAPR Fellows – International Association for Pattern Recognition iapr.org. Checked 21 October 2026.
  8. LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing openaccess.thecvf.com. Checked 21 October 2026.
  9. Marco Cristani-Dep.Department of Engineering for Innovation Medicine-University of Verona dimi.univr.it. Checked 21 October 2026.
  10. Marco Cristani – Intelligo Labs intelligolabs.net. Checked 21 October 2026.