Abstract
In this paper, we present our solutions to the two sub-challenges of Affective Behavior Analysis in the wild (ABAW) 2023: the Emotional Reaction Intensity (ERI) Estimation Challenge and Expression (Expr) Classification Challenge. ABAW 2023 focuses on the problem of affective behavior analysis in the wild, with the goal of creating machines and robots that have the ability to understand human feelings, emotions and behaviors, which can effectively contribute to the advent of a more intelligent future. In our work, we use different models and tools for the Hume-Reaction dataset to extract features of various aspects, such as audio features, video features, etc. By analyzing, combining, and studying these multimodal features, we effectively improve the accuracy of the model for multimodal sentiment prediction. For the Emotional Reaction Intensity (ERI) Estimation Challenge, our method shows excellent results with a Pearson coefficient on the validation dataset, exceeding the baseline method by 84 percent.
Abstract (translated)
在本文中,我们介绍了我们对在野外进行的Affective Behavior Analysis两个子挑战的解决方案:情感反应强度(ERI)估计挑战和表达(Expr)分类挑战。ABAW 2023重点探讨在野外进行情感行为分析的问题,旨在创造能够理解人类情感、情绪和行为的机器和机器人,从而有效地为更智能的未来做出贡献。在我们的工作中,我们使用 Hume-反应数据集的不同模型和工具提取不同方面的特征,例如音频特征、视频特征等。通过分析、组合和研究这些多模式特征,我们有效地提高了多模式情感预测模型的精度。对于情感反应强度(ERI)估计挑战,我们的方法和验证数据集上的Pearson系数显示出非常好的结果,超过基准方法的84%。
URL
https://arxiv.org/abs/2303.09164
