返回全部动态
EMMA：事件驱动多模态记忆与多智能体检索系统
原标题：EMMA: Event-Driven Multimodal Memory System with Multi-Agent Retrieval
AI 摘要
该论文提出 EMMA，一种事件驱动的多模态记忆系统，用于长视频理解。它通过融合视觉语义漂移与语音章节转换的双流检测器自适应定位事件边界，构建原始视频、片段级记忆和事件级记忆的三级层次结构，并采用多智能体框架进行查询分解、分层搜索、证据验证和答案生成。在三个长视频基准上，EMMA 相比最强基线分别提升 4.3、3.2、2.8 分，同时减少检索轮次。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
EMMA: Event-Driven Multimodal Memory System with Multi-Agent Retrieval Abstract Long video understanding requires reasoning over hours of content that far exceed the context window of multimodal large language models (MLLMs). Existing approaches compress video into fixed-length clips, yet events are fragmented and unrelated content is merged, yielding noisy retrieval. To overcome this challenge, we propose EMMA, an Event-driven Multimodal Memory system with Multi-Agent retrieval, which organize
发布时间：2026-10-20 12:00
抓取时间：2026-10-20 12:55
来源机构：arXiv