Challenge Results

The AI4Pain Grand Challenge 2024 saw great participation from the global research community, with 12 teams competing to advance automated pain detection through AI using fNIRS and facial video data. The challenge, held in conjunction with the 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), brought forward cutting-edge models that have the potential to transform pain assessment in clinical settings.

The top two teams are:

1. Team lead by Pooja Prajod from University of Augsburg, Germany took first place with their transfer learning approach, achieving an accuracy of 49.3%. Link to their paper: [PDF]

2. Team lead by Stefanos Gkikas from Hellenic Mediterranean University, Greece secured the runner-up position with a transformer-based model, reaching an accuracy of 46.6%. Link to their paper: [PDF]

We extend our deepest thanks to all participants for their incredible efforts and innovative contributions. Their work has pushed the boundaries of AI-driven pain assessment, showcasing the potential of multimodal fNIRS and video analysis in healthcare applications.

For more details on the challenge and the methodologies, please refer to the paper: 

The AI4Pain Grand Challenge 2024: Advancing Pain Assessment with Multimodal fNIRS and Facial Video Analysis by Raul Fernandez-Rojas, Calvin Joseph, Niraj Hirachan, Ben Seymour, and Roland Goecke, published in the 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW).