arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.18552cs.MMcs.CLcs.CVcs.LGcs.SDeess.AS
收藏

基于音频-视频Transformer融合与交叉注意力的多模态情感识别

Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention

School of Computer Science and Engineering, Vellore Institute of Technology (VIT) University(计算机科学与工程学院,维洛雷理工学院(VIT大学))

Joe Dhanith P R, Shravan Venkatraman, Vigya Sharma, Santhosh Malarvannan

AI总结:

本文提出AVT-CA模型,通过音频-视频Transformer融合与交叉注意力机制,提升多模态情感识别的准确率和F1分数。

摘要:

多模态情感识别(MER)旨在通过联合建模音频和视觉线索来推断人类情绪;然而,现有方法往往在时间错位、判别力弱的特征表示以及异构模态的融合方面存在困难。为了解决这些挑战,我们提出了AVT-CA,一种带有交叉注意力的音频-视频Transformer架构,用于鲁棒的情感识别。所提出的模型引入了一种分层的视频特征表示,结合通道注意力、空间注意力和局部特征提取,以强调情感显著区域并抑制无关信息。这些优化的视觉特征通过中间基于Transformer的融合机制与音频表示相结合,捕捉跨模态的相互关联的时间依赖性。此外,一个交叉注意力模块会优先强化相互一致的音频-视觉线索,从而实现有效的特征选择和噪声感知融合。在三个基准数据集CMU-MOSEI、RAVDESS和CREMA-D上进行了广泛的实验,结果表明,AVT-CA在准确率和F1分数上均优于现有最先进的基线方法。我们的源代码在https://github.com/shravan-18/AVTCA上公开可用。

英文摘要:

Multimodal emotion recognition (MER) aims to infer human affect by jointly modeling audio and visual cues; however, existing approaches often struggle with temporal misalignment, weakly discriminative feature representations, and suboptimal fusion of heterogeneous modalities. To address these challenges, we propose AVT-CA, an Audio-Video Transformer architecture with cross attention for robust emotion recognition. The proposed model introduces a hierarchical video feature representation that combines channel attention, spatial attention, and local feature extraction to emphasize emotionally salient regions while suppressing irrelevant information. These refined visual features are integrated with audio representations through an intermediate transformer-based fusion mechanism that captures interlinked temporal dependencies across modalities. Furthermore, a cross-attention module selectively reinforces mutually consistent audio-visual cues, enabling effective feature selection and noise-aware fusion. Extensive experiments on three benchmark datasets, CMU-MOSEI, RAVDESS, and CREMA-D, demonstrate that AVT-CA consistently outperforms state-of-the-art baselines, achieving significant improvements in both accuracy and F1-score. Our source code is publicly available at https://github.com/shravan-18/AVTCA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑