The automatic estimation of pain is essential in designing an optimal pain management system offering reliable assessment and reducing the suffering of patients. In this study, we present a novel full transformer-based framework consisting of a Transformer in Transformer (TNT) model and a Transformer leveraging cross-attention and self-attention blocks. Elaborating on videos from the BioVid database, we demonstrate state-of-the-art performances, showing the efficacy, efficiency, and generalization capability across all the primary pain estimation tasks.

翻译：自动疼痛评估对于设计能够提供可靠评估并减轻患者痛苦的最佳疼痛管理系统至关重要。本研究提出了一种新颖的全Transformer框架，该框架由Transformer in Transformer (TNT)模型以及一个利用交叉注意力与自注意力模块的Transformer组成。基于BioVid数据库中的视频数据，我们在所有主要的疼痛评估任务上均展示了最先进的性能，证明了该框架的有效性、高效性以及泛化能力。