脚本到幻灯片接地：将脚本句子接地到幻灯片对象以实现自动教学视频生成
Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation
AI总结：
本文提出Script-to-Slide Grounding任务，利用大语言模型实现脚本与幻灯片对象的自动接地，实验显示F1分数达0.924，为自动化幻灯片视频编辑奠定基础。
摘要：
尽管带有视觉效果的幻灯片视频在教育和研究中广泛应用，但视频编辑过程，特别是将语音内容接地到幻灯片对象仍高度劳动密集。本研究旨在开发从幻灯片和相应脚本自动生成此类教学视频的系统。作为基础步骤，本文提出并定义Script-to-Slide Grounding (S2SG)任务，即将脚本句子接地到相应幻灯片对象。此外，作为初步步骤，我们提出``Text-S2SG''方法，利用大语言模型（LLM）执行此接地任务。实验表明，所提方法达到高性能（F1分数：0.924）。本文的贡献是将隐含的基于幻灯片的视频编辑过程形式化为可计算任务，从而为自动化铺平道路。
英文摘要：
While slide-based videos augmented with visual effects are widely utilized in education and research presentations, the video editing process -- particularly applying visual effects to ground spoken content to slide objects -- remains highly labor-intensive. This study aims to develop a system that automatically generates such instructional videos from slides and corresponding scripts. As a foundational step, this paper proposes and formulates Script-to-Slide Grounding (S2SG), defined as the task of grounding script sentences to their corresponding slide objects. Furthermore, as an initial step, we propose ``Text-S2SG,'' a method that utilizes a large language model (LLM) to perform this grounding task for text objects. Our experiments demonstrate that the proposed method achieves high performance (F1-score: 0.924). The contribution of this work is the formalization of a previously implicit slide-based video editing process into a computable task, thereby paving the way for its automation.
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。
