发表机构
Honda Research Institute Japan; Sapienza University of Rome; University of Canberra（本田研究所日本分所; 罗马第一大学; 堪培拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对疼痛识别问题，引入异构3D模态统一词元化框架，该框架可跨行为和脑活动3D数据进行单一处理，保留多种结构并映射到共享空间，实验证明其能有效处理相关数据，在基准数据集上性能先进且效率高可实时评估。
AI 中文摘要
疼痛是一种复杂且普遍的现象，准确评估对有效临床管理和干预至关重要。计算疼痛识别系统能实现持续监测等。本研究介绍了一种用于疼痛识别的异构3D模态统一词元化框架，提供跨行为和脑活动3D数据的单一处理管道，无需为每种模态设单独架构。该框架保留多种结构并映射到共享词元空间。实验表明其能有效处理面部视频和fNIRS数据，在AI4Pain基准数据集上达到先进性能，兼具高计算效率并能实时评估。
英文摘要
Pain is a complex and pervasive phenomenon affecting a large percentage of the population, and accurate assessment is essential for effective clinical management and intervention. Computational pain recognition systems enable continuous monitoring, support clinical decision-making, and help mitigate pain-related distress and functional decline. This study introduces a unified tokenization framework for heterogeneous 3D modalities in pain recognition that provides a single processing pipeline across behavioral and brain-activity 3D data, without requiring separate architectures for each modality or handcrafted inductive biases. The framework preserves spatial, temporal, and time--frequency structure while mapping diverse inputs into a shared token space. Extensive experiments show that the proposed approach effectively processes facial videos and fNIRS data in both raw-signal and spectrogram-based representations. On the AI4Pain benchmark dataset, the proposed framework achieves state-of-the-art performance while maintaining high computational efficiency and enabling real-time assessment on both GPU and CPU hardware.
CommentsAccepted at the 28th ACM International Conference on Multimodal Interaction (ICMI 2026)
