arXiv：cs.CL· Guimin Hu, Zihao Song, Jiachen Luo, Jiayuan Xie, Ruichu Cai·· 4 小时前
BehavDep：从稀疏表征到行为洞察的多模态抑郁评估框架
From Sparse Representations to Behavioral Insights for Multimodal Depression Assessment
AI 导读
BehavDep 是一个基于稀疏因子的框架，将多模态行为表征分解为稀疏潜在因子，并通过语义桥与行为概念关联。它利用弱监督学习视频级抑郁倾向分数，再聚合多次观测信息实现用户级评估，实验取得最佳整体评估表现。该框架还揭示了不同模态的互补贡献、跨观测的异质行为模式以及对概念级编辑的预测响应。
正文
Abstract: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. 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. 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. Extensive experiments demonstrate that BehavDep achieves the best overall assessment performance while revealing complementary modality contributions, heterogeneous behavioral patterns across observations, and prediction responses to concept-level editing. These results show that BehavDep provides a structured and interpretable approach to analyzing multimodal behavioral representations for depression assessment.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.11787 [cs.CL] |
| (or arXiv:2610.11787v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11787 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Guimin Hu [view email]
[v1]
Thu, 8 Oct 2026 12:03:06 UTC (1,705 KB)
来源：arXiv：cs.CL · arxiv.org