YouMVOS: An Actor-centric Multi-shot Video Object Segmentation Dataset

Many video understanding tasks require analyzing multi-shot videos, but existing datasets for video object segmentation (VOS) only consider single-shot videos. To address this challenge, we collected a new dataset-YouMVOS-of 200 popular YouTube videos spanning ten genres, where each video is on average five minutes long and with 75 shots. We selected recurring actors and annotated 431K segmentation masks at a frame rate of six, exceeding previous datasets in average video duration, object variation, and narrative structure complexity. We incorporated good practices of model architecture design, memory management, and multi-shot tracking into an existing video segmentation method to build competitive baseline methods. Through error analysis, we found that these baselines still fail to cope with cross-shot appearance variation on our YouMVOS dataset. Thus, our dataset poses new challenges in multi-shot segmentation towards better video analysis. Data, code, and pre-trained models are available at https://donglaiw.github.io/proj/youMVOS

Automated summary

Existing datasets for video object segmentation cannot meet the requirements of analyzing multi-shot videos. Therefore, we collected a new dataset called YouMVOS, which includes 200 popular YouTube videos. Our dataset surpasses previous datasets in terms of video duration, object variation, and narrative structure complexity, and provides competitive baseline methods.