Challenge Details

Data and Protocol

The AI4PAIN 2025 dataset includes a total of 65 participants, carefully partitioned to ensure a robust evaluation framework. The AI4Pain dataset is divided into three subsets: training (41 participants), validation (12 participants), and testing (12 participants). Unlike the training and validation sets, which will be made available early in the challenge, the test set will consist of new, unseen data to ensure fair and unbiased evaluation.  

This year’s challenge focuses on multimodal pain classification, leveraging physiological signals such as Electrodermal Activity (EDA), Blood Volume Pulse (BVP), Respiratory (RESP), and Peripheral Oxygen Saturation (SpO₂). The task is to classify each sample into one of three categories: No Pain (NP), Low Pain (LP), or High Pain (HP). Labeled training and validation sets will be released by 14 April 2025, while the unlabeled test set will be provided in mid-May 2025. 

Participants have the flexibility to use any combination of available modalities, as there are no separate modality-specific challenges. They are encouraged to explore various feature extraction techniques, machine learning models, and deep learning architectures. However, they must strictly adhere to the predefined training, validation, and testing partitions, as test set labels will remain undisclosed. While papers can report results from the training and validation sets, only test set performance will be considered for the final Grand Challenge ranking.

During the testing phase (12 May – 16 June 2025), participants will submit predicted labels for the test set, allowing organisers to compute and share classification results. Each team will be allowed up to five test label submissions. Additionally, participants are required to write and submit a paper detailing their methodologies, findings, and insights gained from the challenge, which will be presented at the AAP 2025 Workshop during the ACM ICMI 2025 conference in Canberra, Australia. For more details, please refer to the Submission page.

Use of External Data: To ensure fairness and comparability, participants are strictly prohibited from using any external datasets for training, validation, or testing. The AI4PAIN 2025 dataset is the only permitted data source for model development. 

To register your team, go to the Challenge Registration page.