Abstract
Multimodal Sentiment Analysis (MSA) seeks to infer human emotions by integrating textual, acoustic, and visual cues. However, existing approaches often rely on all modalities are completeness, whereas real-world applications frequently encounter noise, hardware failures, or privacy restrictions that result in missing modalities. There exists a significant feature misalignment between incomplete and complete modalities, and directly fusing them may even distort the well-learned representations of the intact modalities. To this end, we propose PRLF, a Progressive Representation Learning Framework designed for MSA under uncertain missing-modality conditions. PRLF introduces an Adaptive Modality Reliability Estimator (AMRE), which dynamically quantifies the reliability of each modality using recognition confidence and Fisher information to determine the dominant modality. In addition, the Progressive Interaction (ProgInteract) module iteratively aligns the other modalities with the dominant one, thereby enhancing cross-modal consistency while suppressing noise. Extensive experiments on CMU-MOSI, CMU-MOSEI, and SIMS verify that PRLF outperforms state-of-the-art methods across both inter- and intra-modality missing scenarios, demonstrating its robustness and generalization capability.
Abstract (translated)
多模态情感分析(MSA)旨在通过整合文本、音频和视觉线索来推断人类情绪。然而,现有的方法通常依赖于所有模式的完整性,而在现实世界的应用中,由于噪声、硬件故障或隐私限制等问题,往往会出现缺失模式的情况。不完整模式与完整模式之间存在显著的功能偏差,直接融合它们甚至可能扭曲了完好模式的良好学习表示。为此,我们提出了PRLF(渐进式表征学习框架),旨在解决不确定的缺失模式情况下的多模态情感分析问题。 该框架引入了一个自适应模式可靠性估计器(AMRE),它根据识别置信度和费雪信息动态量化每个模式的可靠性,并确定主导模式。此外,逐步交互模块(ProgInteract)通过迭代地将其他模式与主导模式对齐来增强跨模态一致性并抑制噪声。 在CMU-MOSI、CMU-MOSEI和SIMS数据集上的广泛实验表明,在不同缺失情况(包括跨模式和内模式缺失)下,PRLF优于最先进的方法,展示了其鲁棒性和泛化能力。
URL
https://arxiv.org/abs/2603.09111