EditDuet：一种用于视频非线性编辑的多智能体系统
EditDuet: A Multi-Agent System for Video Non-Linear Editing
AI总结：
针对现有视频编辑工具自动化程度不足的问题，提出多智能体系统EditDuet，通过编辑与评审智能体协作完成语言驱动的非线性视频编辑，实验验证其在多指标上优于现有方法。
摘要：
视频编辑与剪辑自动化工具可应用于影视制作、广告以及社交媒体内容创作等多个领域。此前的视频编辑研究主要聚焦于素材检索或用户界面设计，实际的编辑操作仍需用户自行完成。与之不同，我们提出将视频编辑的核心任务自动化，并将其建模为序列决策过程。我们采用多智能体方法，设计了Editor（编辑）智能体和Critic（评审）智能体。Editor智能体以一组视频片段和自然语言指令为输入，借助视频编辑软件中常见的工具生成编辑后的视频序列；Critic智能体则基于生成的序列向Editor提供自然语言反馈，若序列符合要求则进行渲染输出。我们提出了一种基于学习的方法，以实现各专业智能体之间的有效协作，从而解决语言驱动的视频编辑任务。最后，我们探索了一种LLM-as-a-judge（大语言模型作为评审）指标用于评估视频编辑系统的质量，并将其与通用人类偏好进行对比。我们通过用户研究从定性和定量两方面评估了系统输出的视频序列，结果表明，本系统在内容覆盖度、时间约束满足度以及人类偏好方面均大幅优于现有方法。
英文摘要：
Automated tools for video editing and assembly have applications ranging from filmmaking and advertisement to content creation for social media. Previous video editing work has mainly focused on either retrieval or user interfaces, leaving actual editing to the user. In contrast, we propose to automate the core task of video editing, formulating it as sequential decision making process. Ours is a multi-agent approach. We design an Editor agent and a Critic agent. The Editor takes as input a collection of video clips together with natural language instructions and uses tools commonly found in video editing software to produce an edited sequence. On the other hand, the Critic gives natural language feedback to the editor based on the produced sequence or renders it if it is satisfactory. We introduce a learning-based approach for enabling effective communication across specialized agents to address the language-driven video editing task. Finally, we explore an LLM-as-a-judge metric for evaluating the quality of video editing system and compare it with general human preference. We evaluate our system's output video sequences qualitatively and quantitatively through a user study and find that our system vastly outperforms existing approaches in terms of coverage, time constraint satisfaction, and human preference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
