arXiv cs.AI· Changzeng Fu, Songyang Wang, Chang Gao, Xinyi Zhang, Peilin Li, Mo Meng, Jiarui Wu, Mingze Li, Hongwei Ding, Shiqi Zhao, Yong Li, Lang He·· 1 小时前AI 评分32
InertiaMPDD：基于情绪惯性动力学建模的多模态个性化抑郁检测
InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling
AI 导读
新方法 InertiaMPDD 受情绪惯性启发，用世界模型式隐变量预测器学习健康参照下的下一状态模式，进行多模态抑郁筛查。它提取参照偏离、残差衰减率和 Jacobian 谱描述子作为候选代理生物标记物。在四个数据集五个队列上，融合模型在 D-Vlog 达 98.41% F1、LMVD 达 84.98%；独立描述子在 MPDD 上优于固定加性融合，但在 AVEC2014 上判别力较弱。
正文 · 原文
Authors:Changzeng Fu, Songyang Wang, Chang Gao, Xinyi Zhang, Peilin Li, Mo Meng, Jiarui Wu, Mingze Li, Hongwei Ding, Shiqi Zhao, Yong Li, Lang He
Abstract:Multimodal depression screening estimates risk from speech, visual behavior and language. Current methods mainly predict labels, with limited evidence of departures from a non-depressed reference. Recording-level supervision also leaves fine-grained emotional dynamics unannotated. Motivated by emotional inertia, the persistence of affect, InertiaMPDD learns healthy next-state patterns using a world-model-inspired latent predictor. Using pretrained multimodal representations, it predicts from observed history and context. Reference deviation, residual decay rate and a Jacobian spectral descriptor form reference-derived emotional dynamics descriptors, evaluated as candidate proxy biomarkers for standalone screening and personalized decision correction. Across five cohorts from four datasets, fusion reaches 98.41% F1 on D-Vlog and 84.98% on LMVD. Standalone descriptors outperform fixed additive fusion on MPDD but discriminate weakly on AVEC2014. These findings distinguish reference informativeness from fusion benefit and reveal context-dependent utility.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16647 [cs.AI] |
| (or arXiv:2611.16647v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16647 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Changzeng Fu [view email]
[v1]
Thu, 12 Nov 2026 11:22:19 UTC (12,985 KB)
来源：arXiv cs.AI · arxiv.org