无需训练，通过事件链实现多模态摘要生成
Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
- 基于分层事件图构建事件链，显式建模跨模态关联
- 在8个数据集上平均提升3.04 ROUGE、9.51 CIDEr
- 适合需要可解释性和跨域泛化的摘要应用
多模态摘要（MMS）旨在理解并融合视频、字幕和图像中的信息，生成简洁文本摘要。现有方法仍面临三大挑战：依赖特定领域标注、跨模态对齐弱、时间建模扁平化。为此，我们提出无需训练的CoE框架，通过由分层事件图（HEG）引导的事件链进行结构化推理。HEG将文本语义编码为显式的事件层次结构，支撑跨模态对齐与时间推理。在此结构引导下，CoE定位关键视觉线索，建模事件演变与因果转换，并通过轻量级风格适配实现领域对齐。在8个多样数据集上的实验表明，CoE持续优于现有视频思维链基线，平均提升3.04 ROUGE、9.51 CIDEr、1.88 BERTScore，凸显其鲁棒性、可解释性与跨域泛化能力。
原文摘要 · Abstract (English)
Multimodal Summarization (MMS) aims to generate concise textual summaries by understanding and integrating information across videos, transcripts, and images. However, existing approaches still suffer from three main challenges: (1) reliance on domain-specific supervision, (2) implicit fusion with weak cross-modal grounding, and (3) flat temporal modeling without event transitions. To address these issues, we introduce **CoE**, a training-free MMS framework that performs structured reasoning through a **Chain-of-Events** guided by a Hierarchical Event Graph (HEG). The HEG encodes textual semantics into an explicit event hierarchy that scaffolds cross-modal grounding and temporal reasoning. Guided by this structure, **CoE** localizes key visual cues, models event evolution and causal transitions, and refines outputs via lightweight style adaptation for domain alignment. Extensive experiments on eight diverse datasets demonstrate that **CoE** consistently outperforms state-of-the-art video CoT baselines, achieving average gains of **+3.04 ROUGE**, **+9.51 CIDEr**, and **+1.88 BERTScore**, highlighting its robustness, interpretability, and cross-domain generalization. Our code is available at https://github.com/youxiaoxing/CoE.
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。