用简单融合方法实现92%情感分类准确率，适合资源受限场景
Rethinking Multimodal Sentiment Analysis: A High-Accuracy, Simplified Fusion Architecture
- 采用全连接层+丢弃的模态专用编码器，模块化设计
- 在IEMOCAP数据集上达到92%准确率，六类情绪分类
- 无需复杂注意力机制，轻量高效，适合部署
多模态情感分析是情感计算中的关键任务，旨在通过语言、音频和视觉信号融合理解人类情绪。尽管近期方法普遍使用复杂的注意力机制与层次结构，本文提出一种轻量级但高效的基于融合的深度学习模型，用于话语级情绪分类。基于基准数据集IEMOCAP（包含对齐的文本、音频数值特征和视觉描述符），我们设计了使用全连接层与丢弃正则化的模态专用编码器。各模态表示通过简单拼接融合，再经密集融合层捕捉跨模态交互。该简化架构避免了计算开销，同时保持性能，在六类情绪分类中达到92%的准确率。结果表明，通过精心的特征工程与模块化设计，更简单的融合策略可超越或媲美复杂模型，尤其适用于资源受限环境。
原文摘要 · Abstract (English)
Multimodal sentiment analysis, a pivotal task in affective computing, seeks to understand human emotions by integrating cues from language, audio, and visual signals. While many recent approaches leverage complex attention mechanisms and hierarchical architectures, we propose a lightweight, yet effective fusion-based deep learning model tailored for utterance-level emotion classification. Using the benchmark IEMOCAP dataset, which includes aligned text, audio-derived numeric features, and visual descriptors, we design a modality-specific encoder using fully connected layers followed by dropout regularization. The modality-specific representations are then fused using simple concatenation and passed through a dense fusion layer to capture cross-modal interactions. This streamlined architecture avoids computational overhead while preserving performance, achieving a classification accuracy of 92% across six emotion categories. Our approach demonstrates that with careful feature engineering and modular design, simpler fusion strategies can outperform or match more complex models, particularly in resource-constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。