This is the authors' abstract. We don't add key points for this paper.
Concept-based models have been proposed as a new line of research for explainable by-design deep learning models. However, those models show their whole power when applied to benchmarks where the concepts are well defined and the concepts' attributes easily extractable from the raw data. In this paper, we challenge the most recent concept-based model initially developed for image classification, on more complex interpretative tasks from a recently proposed video benchmark where they perform poorly. We conduct a root cause analysis of the poor performances of state-of-the-art explainable concept-based models for these multimodal interpretative tasks, and propose adaptations to design robust explainable models for detecting character objectification in this novel challenging video benchmark. We show that the optimal architectural choice may vary depending on the modality setting, thereby showing that designing multimodal concept-based approaches remains an open challenge and calls for further investigation.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Tores et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: