Efficient Pain Recognition via Respiration Signals: A Single Cross-Attention Transformer Multi-Window Fusion Pipeline

TL;DR

This paper presents a novel, efficient transformer-based pipeline that uses respiration signals for automatic pain assessment, demonstrating strong performance with a multi-window fusion strategy.

Contribution

It introduces a cross-attention transformer with multi-window fusion for pain recognition from respiration signals, highlighting the modality's effectiveness and model efficiency.

Findings

Respiration signals are valuable for pain assessment.

Compact models can outperform larger ones when optimized.

Multi-window strategy captures diverse temporal features.

Abstract

Pain is a complex condition that affects a large portion of the population. Accurate and consistent evaluation is essential for individuals experiencing pain and supports the development of effective and advanced management strategies. Automatic pain assessment systems provide continuous monitoring, aid clinical decision-making, and aim to reduce distress while preventing functional decline. This study has been submitted to the Second Multimodal Sensing Grand Challenge for Next-Gen Pain Assessment (AI4PAIN). The proposed method introduces a pipeline that employs respiration as the input signal and integrates a highly efficient cross-attention transformer with a multi-windowing strategy. Extensive experiments demonstrate that respiration serves as a valuable physiological modality for pain assessment. Furthermore, results show that compact and efficient models, when properly optimized, can deliver strong performance, often surpassing larger counterparts. The proposed multi-window strategy effectively captures short-term and long-term features, along with global characteristics, enhancing the model's representational capacity.