Improving Valence-Arousal Estimation with Spatiotemporal Relationship Learning and Multimodal Fusion

Jun Yu,Gongpeng Zhao,Yongqi Wang,Zhihong Wei,Zerui Zhang,Zhongpeng Cai,Guochen Xie,Jichao Zhu,Wangyuan Zhu,Shuoping Yang,Yang Zheng,Qingsong Liu,Jiaen Liang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 7878-7885

This paper presents our approach for the VA (Valence-Arousal) estimation task in the ABAW6 competition. We devised a comprehensive model by preprocessing video frames and audio segments to extract visual and audio features. Through the utilization of Temporal Convolutional Network (TCN) module we effectively captured the temporal and spatial correlations between these features. Subsequently we employed a Transformer encoder structure to learn long-range dependencies thereby enhancing the model's performance and generalization ability. Additionally we proposed the LA-SE module to better capture local image information and enhance channel selection and suppression. Our method leverages a multimodal data fusion approach integrating pre-trained audio and video backbones for feature extraction followed by TCN-based spatiotemporal encoding and Transformer-based temporal information capture. Experimental results demonstrate the effectiveness of our approach achieving competitive performance in VA estimation on the AffWild2 dataset.