Alert button
Picture for Peng Zou

Peng Zou

Alert button

Spatial-temporal Transformer for Affective Behavior Analysis

Mar 19, 2023
Peng Zou, Rui Wang, Kehua Wen, Yasi Peng, Xiao Sun

Figure 1 for Spatial-temporal Transformer for Affective Behavior Analysis
Figure 2 for Spatial-temporal Transformer for Affective Behavior Analysis

The in-the-wild affective behavior analysis has been an important study. In this paper, we submit our solutions for the 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), which includes V-A Estimation, Facial Expression Classification and AU Detection Sub-challenges. We propose a Transformer Encoder with Multi-Head Attention framework to learn the distribution of both the spatial and temporal features. Besides, there are virious effective data augmentation strategies employed to alleviate the problems of sample imbalance during model training. The results fully demonstrate the effectiveness of our proposed model based on the Aff-Wild2 dataset.

Viaarxiv icon

Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis

Aug 12, 2022
Jia Li, Ziyang Zhang, Junjie Lang, Yueqi Jiang, Liuwei An, Peng Zou, Yangyang Xu, Sheng Gao, Jie Lin, Chunxiao Fan, Xiao Sun, Meng Wang

Figure 1 for Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
Figure 2 for Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
Figure 3 for Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
Figure 4 for Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis

In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges. The MuSe 2022 focuses on humor detection, emotional reactions and multimodal emotional stress utilizing different modalities and data sets. In our work, different kinds of multimodal features are extracted, including acoustic, visual, text and biological features. These features are fused by TEMMA and GRU with self-attention mechanism frameworks. In this paper, 1) several new audio features, facial expression features and paragraph-level text embeddings are extracted for accuracy improvement. 2) we substantially improve the accuracy and reliability of multimodal sentiment prediction by mining and blending the multimodal features. 3) effective data augmentation strategies are applied in model training to alleviate the problem of sample imbalance and prevent the model from learning biased subject characters. For the MuSe-Humor sub-challenge, our model obtains the AUC score of 0.8932. For the MuSe-Reaction sub-challenge, the Pearson's Correlations Coefficient of our approach on the test set is 0.3879, which outperforms all other participants. For the MuSe-Stress sub-challenge, our approach outperforms the baseline in both arousal and valence on the test dataset, reaching a final combined result of 0.5151.

* 8 pages, 2 figures, to appear in MuSe 2022 (ACM MM2022 co-located workshop) 
Viaarxiv icon