PainFormer: A Vision Foundation Model for Automatic Pain Assessment
Year: 2025
Type: article
Abstract: Pain is a manifold condition that impacts a significant percentage of the population. Accurate and reliable pain evaluation for the people suffering is crucial to developing effective and advanced pain management protocols. Automatic pain assessment systems provide continuous monitoring and support decision-making processes, ultimately aiming to alleviate distress and prevent functionality decline. This study introducesPainFormer, a vision foundation model based on multi-task learning principles trained simultaneously on14tasks/datasets with a total of10.9million samples. Functioning as an embedding extractor for various input modalities, the foundation model provides feature representations to theEmbedding-Mixer, a transformer-based module that performs the final pain assessment. Extensive experiments employing behavioral modalities–including RGB, synthetic thermal, and estimated depth videos–and physiological modalities such as ECG, EMG, GSR, and fNIRS revealed thatPainFormereffectively extracts high-quality embeddings from diverse input modalities. The proposed framework is evaluated on two pain datasets,BioVidandAI4Pain, and directly compared to75different methodologies documented in the literature. Experiments conducted in unimodal and multimodal settings demonstrate state-of-the-art performances across modalities and pave the way toward general-purpose models for automatic pain assessment.The foundation model's architecture (code) and weights are available athttps://github.com/GkikasStefanos/PainFormer.
Institutions: Hellenic Mediterranean University, University of Canberra
Language: English
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
Estimated APC paid: $2,645
OpenAlex ID: W4413967117