Scholarlink

<p>Emotion fluctuations during music listening are closely tied to a listener’s current emotional state, yet most recommendation systems rely on historical behavior data, which struggle with cold-start issues and real-time adaptability. In this work, we propose IMJP-Net, a framework that leverages smart glasses IMU signals as a privacy-preserving implicit feedback channel for emotion-aware music recommendation. To resolve the non-stationarity of head-worn dynamics, the system integrates an IMU Evolution Module (IEM) for temporal inertial encoding and an IMU-Music Mutual Attentive Alignment (IMMAA) mechanism for cross-modal feature fusion. Evaluated on 1164 valid trials (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(N=30\)</EquationSource> </InlineEquation>), IMJP-Net achieves 19.6% improvement over baselines in joint prediction of music preference and post-listening emotional states. Ablation studies demonstrate that excluding IMU signals results in a 37.7% increase in mean MAE, confirming the critical contribution of inertial sensing to real-time affect inference. An in-the-wild user study (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(N=10\)</EquationSource> </InlineEquation>) validates practical utility, with participants highlighting enhanced emotional resonance, as well as privacy and non-intrusiveness. These results demonstrate the potential of IMJP-Net for pervasive emotion-aware music recommendation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

IMJP-Net: inertial–music joint prediction for emotion-aware recommendation via smart-glasses sensing

  • 期刊论文

  • 发表日期：

    2026年7月20日

查看全文
  • Ying Hao,
  • Dong She,
  • Wenba Li,
  • Shuyu Luo,
  • Yang Gao,
  • Zhanpeng Jin

摘要

Emotion fluctuations during music listening are closely tied to a listener’s current emotional state, yet most recommendation systems rely on historical behavior data, which struggle with cold-start issues and real-time adaptability. In this work, we propose IMJP-Net, a framework that leverages smart glasses IMU signals as a privacy-preserving implicit feedback channel for emotion-aware music recommendation. To resolve the non-stationarity of head-worn dynamics, the system integrates an IMU Evolution Module (IEM) for temporal inertial encoding and an IMU-Music Mutual Attentive Alignment (IMMAA) mechanism for cross-modal feature fusion. Evaluated on 1164 valid trials ( \(N=30\) ), IMJP-Net achieves 19.6% improvement over baselines in joint prediction of music preference and post-listening emotional states. Ablation studies demonstrate that excluding IMU signals results in a 37.7% increase in mean MAE, confirming the critical contribution of inertial sensing to real-time affect inference. An in-the-wild user study ( \(N=10\) ) validates practical utility, with participants highlighting enhanced emotional resonance, as well as privacy and non-intrusiveness. These results demonstrate the potential of IMJP-Net for pervasive emotion-aware music recommendation.