Emotional Reaction Intensity Estimation Based on Multimodal Data

Shangfei Wang; Jiaqiang Wu; Feiyi Zheng; Xin Li; Xuewei Li; Suwen Wang; Yi Wu; Yanan Chang; Xiangyu Miao

Emotional Reaction Intensity Estimation Based on Multimodal Data

Computer Vision and Pattern Recognition 2023-03-17 v1 Artificial Intelligence

Authors: Shangfei Wang , Jiaqiang Wu , Feiyi Zheng , Xin Li , Xuewei Li , Suwen Wang , Yi Wu , Yanan Chang , Xiangyu Miao

View on arXiv ↗ PDF ↗

Abstract

This paper introduces our method for the Emotional Reaction Intensity (ERI) Estimation Challenge, in CVPR 2023: 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW). Based on the multimodal data provided by the originazers, we extract acoustic and visual features with different pretrained models. The multimodal features are mixed together by Transformer Encoders with cross-modal attention mechnism. In this paper, 1. better features are extracted with the SOTA pretrained models. 2. Compared with the baseline, we improve the Pearson's Correlations Coefficient a lot. 3. We process the data with some special skills to enhance performance ability of our model.

Keywords

multimodal emotion recognition speech emotion recognition affective computing

Cite

@article{arxiv.2303.09167,
  title  = {Emotional Reaction Intensity Estimation Based on Multimodal Data},
  author = {Shangfei Wang and Jiaqiang Wu and Feiyi Zheng and Xin Li and Xuewei Li and Suwen Wang and Yi Wu and Yanan Chang and Xiangyu Miao},
  journal= {arXiv preprint arXiv:2303.09167},
  year   = {2023}
}

Emotional Reaction Intensity Estimation Based on Multimodal Data

Abstract

Keywords

Cite

Related papers