通过分阶段专家模型，从走路姿态预测心理特质。
MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts
- 分四阶段处理步态，用轻量专家模型提取时空特征。
- 在17项心理特质上达44.6%主体级准确率，优于现有方法。
- 结合身份、性别等辅助任务提升预测效果，适合行为分析研究者。
步态蕴含丰富的生物特征与行为信息，但利用行走方式推断心理特质仍是具挑战性且研究不足的问题。本文提出一种分层的多阶段运动专家混合模型（MoME），用于从2D姿态表示的步态序列中进行多任务心理属性预测。MoME将步行周期分为四个运动复杂度阶段，采用轻量级专家模型提取时空特征，并通过任务特定的门控模块自适应加权不同专家。在涵盖17项心理特质的PsyMo基准上评估，该方法在跑步级别达到37.47%的加权F1分数，在主体级别达到44.6%。实验表明，引入身份识别、性别预测和体重指数估计等辅助任务可进一步提升心理特质预测性能。研究结果验证了基于步态的多任务学习在心理特质推断中的可行性，为未来基于运动的心理推断研究提供了基础。
原文摘要 · Abstract (English)
Gait encodes rich biometric and behavioural information, yet leveraging the manner of walking to infer psychological traits remains a challenging and underexplored problem. We introduce a hierarchical Multi-Stage Mixture of Movement Experts (MoME) architecture for multi-task prediction of psychological attributes from gait sequences represented as 2D poses. MoME processes the walking cycle in four stages of movement complexity, employing lightweight expert models to extract spatio-temporal features and task-specific gating modules to adaptively weight experts across traits and stages. Evaluated on the PsyMo benchmark covering 17 psychological traits, our method outperforms state-of-the-art gait analysis models, achieving a 37.47% weighted F1 score at the run level and 44.6% at the subject level. Our experiments show that integrating auxiliary tasks such as identity recognition, gender prediction, and BMI estimation further improves psychological trait estimation. Our findings demonstrate the viability of multi-task gait-based learning for psychological trait estimation and provide a foundation for future research on movement-informed psychological inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。