arXiv 2606.079352026-06-06cs.CV

REACT 2026：第四届多适切面部反应生成挑战赛：个性化MAFRG与适切脑电反应预测

REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction

University of Exeter（埃克塞特大学）；Politecnico di Milano（米兰理工大学）；Nanjing University of Science and Technology（南京理工大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；King's College London（伦敦国王学院）；Universitat de Barcelona（巴塞罗那大学）；University of Nottingham（诺丁汉大学）；IMT Nord Europe（IMT 北欧欧洲）；Université Grenoble Alpes（格勒诺布尔-阿尔卑斯大学）；University of Augsburg（奥格斯堡大学）；University of Cambridge（剑桥大学）

Siyang Song, Micol Spitale, Zijian Wu, Xiangyu Kong, Cheng Luo, Cristina Palmero, German Barquero, Sergio Escalera, Michel Valstar, Mohamed Daoudi, Fabien Ringe… 展开作者

Siyang Song, Micol Spitale, Zijian Wu, Xiangyu Kong, Cheng Luo, Cristina Palmero, German Barquero, Sergio Escalera, Michel Valstar, Mohamed Daoudi, Fabien Ringeval, Andrew Howes, Elisabeth Andre, Hatice Gunes

备注：: arXiv admin note: text overlap with arXiv:2505.17223

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出REACT 2026挑战赛，鼓励开发机器学习模型，用于生成个性化、适切、多样、真实且同步的人类面部反应，并引入个性标签和脑电记录，探索新的一对多个性化面部反应生成设置。

摘要：

在二元交互中，多种人类面部反应可能适合回应每个说话者行为。继REACT 2023、2024和2025挑战系列成功举办后，针对多适切面部反应生成（MAFRG）问题，已开发了一系列生成式深度学习模型。今年，我们提出REACT 2026挑战赛，鼓励开发和基准测试机器学习（ML）模型，这些模型能够生成由特定人类倾听者表达的多个个性化、适切、多样、真实且同步的人类风格面部反应，以回应每个给定的说话者行为。作为挑战的关键，我们持续向挑战参与者提供REACT 2025引入的MARS数据集，并额外提供个体层面的五大人格标签和脑电记录。这引入了一种新的结合人类表达行为、情感和神经生理信号的一对多个性化面部反应生成设置，这在当前的二元交互建模中仍很大程度上未被探索。本文还介绍了挑战指南和四个提议的子挑战的新基线：离线通用和个性化MAFRG，以及在线通用和个性化MAFRG，这些基线公开于https://github.com/reactmultimodalchallenge/baseline_react2026。

英文摘要：

In dyadic interactions, various human facial reactions could be appropriate for responding to each human speaker behaviour. Following the successful organisation of the REACT 2023, 2024 and 2025 challenge series, a body of generative deep learning (DL) models have been developed for the problem of multiple appropriate facial reaction generation (MAFRG). This year, we propose the REACT 2026 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can generate multiple personalised, appropriate, diverse, realistic and synchronised human-style facial reactions expressed by a specific human listener for responding to each given speaker behaviour. As a key of the challenge, we continuously provide challenge participants with MARS dataset introduced by REACT 2025 but additionally provide individual-level Big-Five personality labels and EEG recordings. This introduces a new one-to-many personalised facial reaction generation setting combining human expressive behavioural, affective and neurophysiological signals, which remains largely unexplored in current dyadic interaction modelling. This paper also presents the challenge guidelines and new baselines on the four proposed sub-challenges: Offline generic and personalised MAFRG as well as Online generic and personalised MAFRG, respectively, which are publicly available at https://github.com/reactmultimodalchallenge/baseline_react2026.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。