Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable Diffusion and Imagen, generative AI has improved dramatically on video tasks. But it's hard to evaluate progress in these video tasks because there is no standard benchmark. So, we propose a new dataset for text-guided video editing (TGVE), and we run a competition at CVPR to evaluate models on our TGVE dataset. In this paper we present a retrospective on the competition and describe the winning method. The competition dataset is available at https://sites.google.com/view/loveucvpr23/track4.

翻译：人类每天观看超过十亿小时的视频。其中绝大多数视频是通过人工编辑完成的，这是一个繁琐的过程。然而，基于人工智能的视频生成与编辑技术正日益兴起。基于Stable Diffusion和Imagen等文生图模型，生成式AI在视频任务上取得了显著进步。但由于缺乏标准化基准，这些视频任务的进展评估仍然困难。为此，我们提出了一个新的文本引导视频编辑（TGVE）数据集，并在CVPR上举办了一场竞赛，以评估模型在该数据集上的表现。本文回顾了竞赛情况，并描述了获胜方法。竞赛数据集可通过https://sites.google.com/view/loveucvpr23/track4获取。