Saved in:
Bibliographic Details
Main Authors: Yu, Jun, Wang, Yongqi, Wang, Lei, Zheng, Yang, Xu, Shengfan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915196287582208
author Yu, Jun
Wang, Yongqi
Wang, Lei
Zheng, Yang
Xu, Shengfan
author_facet Yu, Jun
Wang, Yongqi
Wang, Lei
Zheng, Yang
Xu, Shengfan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10523
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interactive Multimodal Fusion with Temporal Modeling
Yu, Jun
Wang, Yongqi
Wang, Lei
Zheng, Yang
Xu, Shengfan
Computer Vision and Pattern Recognition
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.
title Interactive Multimodal Fusion with Temporal Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.10523