This paper presents our method for the estimation of valence-arousal (VA) in the 8th Affective Behavior Analysis in-the-Wild (ABAW) competition. Our approach integrates visual and audio information through a multimodal framework. The visual branch uses a pre-trained ResNet model to extract spatial features from facial images. The audio branches employ pre-trained VGG models to extract VGGish and LogMel features from speech signals. These features undergo temporal modeling using Temporal Convolutional Networks (TCNs). We then apply cross-modal attention mechanisms, where visual features interact with audio features through query-key-value attention structures. Finally, the features are concatenated and passed through a regression layer to predict valence and arousal. Our method achieves competitive performance on the Aff-Wild2 dataset, demonstrating effective multimodal fusion for VA estimation in-the-wild.
View on arXiv@article{yu2025_2503.10523,
title={ Interactive Multimodal Fusion with Temporal Modeling },
author={ Jun Yu and Yongqi Wang and Lei Wang and Yang Zheng and Shengfan Xu },
journal={arXiv preprint arXiv:2503.10523},
year={ 2025 }
}