EmoThinker：通过结构化词元选择与思维链推理推进视觉-声学情感分析
EmoThinker: Advancing Visual-Acoustic Emotion Analysis via Structural Token Selection and Chain-of-Thought Reasoning
其结构化词元选择机制可迁移到任意视觉-语言任务中做显著区域筛选与背景上下文精炼，而构建的思维链标注范式为多模态推理数据构造提供了可复用模板。
原文依据 introduces a structural token selection mechanism to concentrate on pivotal facial regions while refining background context
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态情感分析（MEA）对于以人为本的人工智能至关重要，然而现有方法面临两个核心挑战：情感线索在跨模态上的稀疏性，以及其固有的时序异步性。现有方法往往依赖隐式融合，因而导致显著特征被稀释、表征相互纠缠。为解决这一问题，我们提出 EmoThinker，一个通过显式结构化推理推进 MEA 的新框架。该方法引入结构化词元选择机制，聚焦于关键面部区域并精炼背景上下文，从而提升视觉显著性与效率。在音频方面，音频证据提取器将关键的副语言特征聚合为紧凑且情感信息丰富的词元。更重要的是，我们通过构建思维链情感数据集实现逐步推理，该数据集提供细粒度标注，用于解耦异步线索并化解模态间冲突。通过将证据获取与推理过程解耦，EmoThinker 实现了更具可解释性与鲁棒性的情感分析。在多个基准上的大量实验表明，该框架达到了新的最优性能。
英文原文摘要 1227 字符
Multimodal Emotion Analysis (MEA) is crucial for human-centric AI, yet current methods struggle with two core challenges: the sparse nature of emotional cues across modalities and their inherent temporal asynchrony. Existing approaches, which often rely on implicit fusion, consequently suffer from diluted salient features and entangled representations. To address this issue, we propose EmoThinker, a new framework that advances MEA through explicit, structured reasoning. Our method introduces a structural token selection mechanism to concentrate on pivotal facial regions while refining background context, enhancing visual saliency and efficiency. For audio, an audio evidence extractor aggregates critical paralinguistic features into compact, emotion-rich tokens. More importantly, we enable step-by-step reasoning by constructing a Chain-of-Emotion-Thought dataset, which provides fine-grained annotations for disentangling asynchronous cues and resolving inter-modal conflicts. By decoupling evidence acquisition from reasoning, EmoThinker achieves a more interpretable and robust emotion analysis. Extensive experiments on multiple benchmarks demonstrate that our framework achieves new state-of-the-art performance.