According to the Stimulus Organism Response (SOR) theory, for a given external stimulus, individuals may react differently according to their internal state and external contextual factors in a specific period in time. Analogously, in dyadic interactions, a broad spectrum of human facial reactions might be appropriate for responding to a specific human speaker behaviour. Following the successful organisation of the REACT 2023, REACT 2024 and REACT 2025 challenge series, a body of generative deep learning (DL) models have been investigated for the problem of multiple appropriate facial reaction generation (MAFRG). While REACT 2023 and 2024 challenges were built on human-human dyadic interaction datasets collected for other purposes, the REACT 2025 challenge provided the first natural and large-scale audio-visual Multiple Appropriate Facial Reaction Generation (MAFRG) dataset (called MARS) recording 137 human-human dyadic interactions containing a total of 3,105 interaction sessions covering five different topics. This year, we are proposing the REACT 2026 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can be used to generate multiple appropriate, diverse, realistic and synchronised human-style facial reactions expressed by human listeners in response to each input speaker behaviour expressed by the corresponding speaker. As a key of the challenge, we will continuously provide challenge participants with MARS dataset but additionally providing individual-level Big-Five personality labels and EEG recordings. This introduces a new one-to-many personalised reaction generation setting combining behavioural, affective and neurophysiological signals, which remains largely unexplored in current dyadic interaction modelling. We will then invite the challenge participating groups to submit their developed / trained ML models for evaluation, which will be benchmarked in terms of the appropriateness, diversity, realism and synchronisation of their generated facial reactions.
Launching Challenge website and call for participation poster: March 12, 2026
Registration open: March 12, 2026
Training and validation sets released: March 31, 2026
Baseline paper and code released: May 22, 2026
Model submission opening: May 26, 2026
Final result and model submission deadline: June 26, 2026
Paper submission deadline: June 30, 2026
Paper acceptance notification: July 16, 2026
Camera-ready paper submission deadline (Hard deadline): August 6, 2026
Challenge workshop: October 2026 (TBA)
The first edition of the REACT challenge was held in conjunction with the with the ACM Multimedia (ACM-MM) 2023 in Ottawa, Canada.
As result of the first edition, we released the baseline code in this GitHub repository and corresponding paper. The call for participation attracted registration of 11 teams from 6 countries, with 10 teams participating in the Offline and Online sub-challenges, respectively. The top 3 teams have successfully submitted valid models, results and papers for the challenge, with each paper submission being assigned two reviewers.
The information about the previous edition can be found on this website.
The second edition of the REACT challenge was held in conjunction with the with theIEEE International Conference on Automatic Face and Gesture Recognition (FG2024) in Istanbul, Turkey.
As result of the second edition, we released the baseline code in this GitHub repository and corresponding paper. The call for participation attracted registration of 13 teams from 6 countries, with 13 teams participating in the Offline and 12 teams in the Online sub-challenges, respectively. The top 3 teams have successfully submitted valid models, results and papers for the challenge, with each paper submission being assigned two reviewers.
The information about the previous edition can be found on this website.
The third edition of the REACT challenge was held in conjunction with the with the ACM Multimedia (ACM-MM) 2025 in Dublin, Ireland.
As result of the third edition, we released the baseline code in this GitHub repository and corresponding paper. A total of 23 teams registered for the challenge, with 21 and 20 teams participated in the offline and online subchallenges. The top 3 teams have successfully submitted valid models, results and papers for the challenge, with each paper submission being assigned two reviewers.
The information about the previous edition can be found on this website.
Given the spatio-temporal behaviours expressed by a speaker at the time period, the proposed REACT 2026 Challenge will consist of the following two sub-challenges with two specific tasks respectively whose theoretical underpinnings have been defined and detailed in this paper.
Task 1: Offline Generic Appropriate Facial Reaction Generation
Task 2: Online Generic Appropriate Facial Reaction Generation
Task 1: Offline Personalised Appropriate Facial Reaction Generation
Task 2: Online Personalised Appropriate Facial Reaction Generation
The REACT 2026 challenge builds upon the Multi-modal Multiple Appropriate Reaction in Social Dyads (MARS) dataset, which was originally introduced in REACT 2025 and is specifically designed for Multiple Appropriate Facial Reaction Generation (MAFRG) tasks. Compared to previous editions, REACT 2026 extends the dataset with individual-level personality annotations and neurophysiological signals (EEG), enabling the study of personalised AFR generation driven by both observable behaviour and latent internal states.
The dataset comprises 137 human–human dyadic interaction recordings involving 23 speakers and 137 listeners, resulting in 270 multi-modal recordings and 3,105 interaction sessions. Each recording contains synchronised audio, facial video, and EEG signals captured during remote conversations conducted via Microsoft Teams. Sessions cover five structured conversational topics, including cultural discussions, movie sharing, policy debates, quizzes and games, and scenario-based interviews, ensuring a controlled semantic context while maintaining naturalistic interaction dynamics.
During data collection, speakers and listeners were located in separate rooms and interacted remotely to reduce physical co-presence bias while preserving conversational realism. Two volunteers supervised the recording process to ensure adherence to the experimental protocol and to handle potential interruptions. The recordings range from approximately 20 to 35 minutes, capturing diverse behavioural patterns across participants and interaction contexts.
The introduction of EEG signals and personality labels introduces several new research challenges compared to previous REACT datasets. First, the dataset exhibits substantial inter-subject variability in AFR style, reflecting differences in personality traits and internal states. Second, multi-modal synchronisation between audio-visual behaviours and EEG signals raises challenges related to temporal alignment and noise robustness. Third, the presence of multiple AFRs for the same speaker behaviour introduces inherent ambiguity, requiring models to learn probabilistic rather than deterministic mappings.
Participants should use the training and validation set to develop their facial reaction models, and submit the final models via email to s.song@exeter.ac.uk. The final results will be evaluated by organizers on the test set. All participants will be ranked based on the results on the test set.
The challenge participants will be invited to submit a workshop-style paper describing their ML solutions and results on the dataset -- these will be peer-reviewed and once accepted, will appear in the ACM Multimedia 2026 Challenge/Workshop Proceedings. The format of the paper follows the same requirements as the main conference of the ACM-MM 2026 (4 pages excluding the references). The paper length is 6 pages + up to 2 additional pages for references only. Grand Challenge papers will be included in the main conference proceedings. At least one main-conference full registration is required for each accepted paper.
Presentation policy: ACM Multimedia 2026 is an on-site event only. This means that all papers and contributions must be presented by a physical person on-site; remote presentations will not be hosted or allowed. Papers and contributions not presented on-site will be considered a no-show and removed from the proceedings of the conference. More details will be provided to handle unfortunate situations in which none of the authors would be able to attend the conference physically
Launching Challenge website and call for participation poster: March 15, 2026
Registration open: March 15, 2026
Training and validation sets released: April 10, 2026
Baseline paper and code released: May 25, 2026
Model submission opening: June 1, 2026
Final result and model submission deadline: June 28, 2026
Paper submission deadline: June 30, 2026
Paper acceptance notification: July 16, 2026
Camera-ready paper submission deadline: August 06, 2026
Challenge workshop: November 2026 (TBD)
Dr Siyang Song, University of Exeter, Exeter, United Kingdom
Dr Micol Spitale, Politecnico di Milano, Milan, Italy
Zijian Wu, Nanjing University of Science and Technology, China
Xiangyu Kong, University of Exeter, Exeter, United Kingdom
Cheng Luo, King Abdullah University of Science and Technology, Saudi Arabia
Dr Cristina Palmero, King’s College London, London, United Kingdom
German Barquero, Universitat de Barcelona, Barcelona, Spain
Prof Sergio Escalera, Universitat de Barcelona, Barcelona, Spain
Prof Michel Valstar, University of Nottingham, Nottingham, United Kingdom
Prof Mohamed Daoudi, IMT Nord Europe, Villeneuve d’Ascq, France
Dr Fabien Ringeval, Université Grenoble Alpes, Grenoble, France
Prof Andrew Howes, University of Exeter, Exeter, United Kingdom
Prof Elisabeth Andrè, University of Augsburg, Augsburg, Germany
Prof Hatice Gunes, University of Cambridge, Cambridge, United Kingdom
Feel free to contact us at this email: s.song@exeter.ac.uk and micol.spitale@polimi.it
[1] Song, S., Spitale, M., Luo, Y., Bal, B., and Gunes, H. "Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?." arXiv preprint arXiv:2302.06514 (2023).
[2] Song, S., Spitale, M., Luo, C., Barquero, G., Palmero, C., Escalera, S., ... & Gunes, H. (2023, October). REACT2023: The First Multiple Appropriate Facial Reaction Generation Challenge. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 9620-9624).
[3] Song, Siyang, et al. "REACT2023: the first Multi-modal Multiple Appropriate Facial Reaction Generation Challenge." arXiv preprint arXiv:2306.06583 (2023).
[4] Luo, Cheng, et al. "ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions." IEEE Transactions on Visualization and Computer Graphics (2024).
[5] Song, Siyang, et al. "React 2024: the second multiple appropriate facial reaction generation challenge." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[6] Nguyen, Minh-Duc, et al. "Vector quantized diffusion models for multiple appropriate reactions generation." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[7] Zhu, Hengde, et al. "Perfrdiff: Personalised weight editing for multiple appropriate facial reaction generation." Proceedings of the 32nd ACM International Conference on Multimedia. 2024.
[8] Nguyen, Dang-Khanh, et al. "Multiple facial reaction generation using gaussian mixture of models and multimodal bottleneck transformer." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[9] Hoque, Ximi, et al. "Beamer: Behavioral encoder to generate multiple appropriate facial reactions." Proceedings of the 31st ACM International Conference on Multimedia. 2023.
[10] Yu, Jun, et al. "Leveraging the latent diffusion models for offline facial multiple appropriate reactions generation." Proceedings of the 31st ACM International Conference on Multimedia. 2023.
[11] Liu, Zhenjie, et al. "One-to-many appropriate reaction mapping modeling with discrete latent variable." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[12] Xu, Tong, et al. "Reversible graph neural network-based reaction distribution learning for multiple appropriate facial reactions generation." IEEE Transactions on Affective Computing 2026.
[13] Li, Jiaming, et al. "Reactdiff: Latent diffusion for facial reaction generation." Neural Networks 2025.
[14] Dam, Quang Tien, et al. "Finite scalar quantization as facial tokenizer for dyadic reaction generation." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[15] Song et al., "REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge." 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2024.
[16] Song et al., "REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[17] Mao, Qirong, et al. "Scattering-Conditioned Diffusion Models for Multiple Appropriate Facial Reaction Generation." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[18] Luo, Cheng, et al. "ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[19] Nguyen, Minh-Duc, et al. "Latent behavior diffusion for sequential reaction generation in dyadic setting." International Conference on Pattern Recognition. Cham: Springer Nature Switzerland, 2024.
[20] Lv, Qincheng, et al. "Hierarchical multimodal decoupling-fusion framework for offline multiple appropriate facial reaction generation." ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025.
[21] Huang, Jiajian, and Zitong Yu. "Multiple Appropriate Facial Reaction Generation Based on Multi-View Transformation of Speaker Video." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[22] Wang, Peng, et al. "Explaining Listener Reactions: Personality-Guided Facial Response Generation with Cross-Modal Attention." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[23] Xie, Weicheng, et al. "Smooth Online Multiple Appropriate Facial Reaction Generation." Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
[24] Huang, Jiajian, et al. "Online Emotion-Driven Generation of Multiple Appropriate Facial Reactions." Chinese Conference on Biometric Recognition. Singapore: Springer Nature Singapore, 2025.