3 papers
cs.CV2026
SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches
Tores Julie, Sun Rémy, Sassatelli Lucile +3
Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task performance but little transparen…
cs.CV2025
MObyGaze: a film dataset of multimodal objectification densely annotated by experts
Julie Tores, Elisa Ancarani, Lucile Sassatelli +10
Characterizing and quantifying gender representation disparities in audiovisual storytelling contents is necessary to grasp how stereotypes may perpetuate on screen. In this articl…
cs.CV2025
Leveraging multimodal explanatory annotations for video interpretation with Modality Specific Dataset
Elisa Ancarani, Julie Tores, Lucile Sassatelli +3
We examine the impact of concept-informed supervision on multimodal video interpretation models using MOByGaze, a dataset containing human-annotated explanatory concepts. We introd…