Objectification in Films as a New Video Interpretation Task for AI

mercredi 12 novembre 2025, 11:15 à 12:00

Lieu
Terminal de croisières de Québec
84 Rue Dalhousie, Québec, QC G1K 4C4
Salle
Salle RDVIAQ

In this talk, I will present the approach we have taken, as AI experts, to contribute to a goal of social justice with AI. The goal is to progress towards fairer gender representation on screen, and we consider detecting complex forms of bias in visual media. I will describe the pipeline we follow from problem spotting, task definition, data creation, model design, evaluation and socio-technical implementation. I will present the MObyGaze dataset we have introduced to the multimedia community, and discuss the design of models to learn from this unique dataset, tying multimodal explanations to an interpretive task label. We will specifically focus on multimodal trustworthiness and the design of explainable concept-based models suited to such interpretative tasks.

Lucile Sassatelli
Lucile Sassatelli
Professeure des Universités
Université Côte d'Azur
Lucile Sassatelli is a Full Professor in computer science at Université Côte…
Lucile Sassatelli is a Full Professor in computer science at Université Côte d'Azur, France. She held a research chair with Institut Universitaire de France. Since 2022, she serves as the scientific director of EFELIA Côte d'Azur, a multi-partner project to generalize AI training in all domains. Her research interests are in AI/ML to tackle social inequalities. She is the PI of a national ANR project involving 6 laboratories in computer and social sciences, to study gender representation in films with computer vision approaches.