The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
This work addresses the problem of limited research resources for AI-assisted video editing tasks for researchers and developers, though it is incremental as it builds on existing datasets and methods.
The authors tackled the lack of datasets for AI-assisted video editing beyond visual effects by introducing the Anatomy of Video Editing dataset and benchmark, which includes over 1.5 million tags from 196,176 movie shots and establishes competitive baselines for tasks like automatic footage organization.
Machine learning is transforming the video editing industry. Recent advances in computer vision have leveled-up video editing tasks such as intelligent reframing, rotoscoping, color grading, or applying digital makeups. However, most of the solutions have focused on video manipulation and VFX. This work introduces the Anatomy of Video Editing, a dataset, and benchmark, to foster research in AI-assisted video editing. Our benchmark suite focuses on video editing tasks, beyond visual effects, such as automatic footage organization and assisted video assembling. To enable research on these fronts, we annotate more than 1.5M tags, with relevant concepts to cinematography, from 196176 shots sampled from movie scenes. We establish competitive baseline methods and detailed analyses for each of the tasks. We hope our work sparks innovative research towards underexplored areas of AI-assisted video editing.