From Sparse Representations to Behavioral Insights for Multimodal Depression Assessment
In this work, we introduce BehavDep, a sparse factor-based framework that decomposes multimodal behavioral representations into sparse latent factors and associates them with behaviorally meaningful concepts through a semantic bridge.
ProofPaper ↗
Key points
- Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression.
- However, existing methods often rely on dense and opaque multimodal representations, making it difficult to interpret the behavioral patterns underlying their predictions.
- To address the mismatch between user-level annotations and heterogeneous video-level behaviors, BehavDep further learns video-level depression tendency scores under weak supervision and aggregates information across multiple observations for user-level assessment.
- These results show that BehavDep provides a structured and interpretable approach to analyzing multimodal behavioral representations for depression assessment.
Sources (1)
- [1]From Sparse Representations to Behavioral Insights for Multimodal Depression AssessmentarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 12:03 PM
In this work, we introduce BehavDep, a sparse factor-based framework that decomposes multimodal behavioral representations into sparse latent factors and associates them with behaviorally meaningful concepts through a semantic bridge.
Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression.
Extractive summary: sentences quoted from the sources.