arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.03327cs.CVcs.AI
收藏

YouTube-VOS:一个大规模视频对象分割基准

YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

Adobe Research(奥多比研究院);Snapchat Research(Snapchat研究院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Ning Xu, Linjie Yang, Yuchen Fan, Dingcheng Yue, Yuchen Liang, Jianchao Yang, Thomas Huang

摘要:

学习长期的时空特征是许多视频分析任务的关键。然而,现有的视频分割方法主要依赖于静态图像分割技术,并且捕获用于分割的时间依赖性的方法必须依赖于预先训练的光流模型,导致问题的次优解决方案。探索用于视频分割的时空特征的端到端顺序学习在很大程度上受到可用视频分割数据集的规模的限制,即,即使最大的视频分割数据集也仅包含90个短视频剪辑。为了解决这个问题,我们构建了一个新的大规模视频对象分割数据集,称为YouTube视频对象分割数据集(YouTube-VOS)。我们的数据集包含4,453个YouTube视频剪辑和94个对象类别。这是迄今为止我们所知的最大的视频对象分割数据集,已在http://youtube-vos.org上发布。我们进一步评估了该数据集上现有的几种最先进的视频对象分割算法,旨在为未来新算法的开发建立基线。

英文摘要:

Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for segmentation have to depend on pretrained optical flow models, leading to suboptimal solutions for the problem. End-to-end sequential learning to explore spatialtemporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.e., even the largest video segmentation dataset only contains 90 short video clips. To solve this problem, we build a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS). Our dataset contains 4,453 YouTube video clips and 94 object categories. This is by far the largest video object segmentation dataset to our knowledge and has been released at http://youtube-vos.org. We further evaluate several existing state-of-the-art video object segmentation algorithms on this dataset which aims to establish baselines for the development of new algorithms in the future.

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。

↑