arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15418cs.CV
收藏

计数时间:类不可知论的视频重复计数在野外

Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

Google Research(谷歌研究院);DeepMind

Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

摘要:

我们提出了一种方法,用于估计在视频中重复的动作的周期。该方法的关键在于限制周期预测模块使用时间自相似性作为中间表示瓶颈,允许泛化到野外视频中看不见的重复。我们用一个合成数据集来训练这个称为Repnet的模型,该数据集是通过对不同长度的短片段进行采样并以不同的周期和计数重复它们而从一个大型未标记的视频集合中生成的。这种合成数据和一个强大但受约束的模型的组合,使我们能够以一种与类别无关的方式预测周期。我们的模型大大超过了现有的周期性(PERTUBE)和重复计数(QUVA)基准的最先进的性能。我们还收集了一个新的具有挑战性的数据集,称为Countix(比现有数据集大90倍),它捕捉了现实世界视频中重复计数的挑战。项目网页:https://sites.google.com/view/repnet。

英文摘要:

We present an approach for estimating the period with which an action is repeated in a video. The crux of the approach lies in constraining the period prediction module to use temporal self-similarity as an intermediate representation bottleneck that allows generalization to unseen repetitions in videos in the wild. We train this model, called Repnet, with a synthetic dataset that is generated from a large unlabeled video collection by sampling short clips of varying lengths and repeating them with different periods and counts. This combination of synthetic data and a powerful yet constrained model, allows us to predict periods in a class-agnostic fashion. Our model substantially exceeds the state of the art performance on existing periodicity (PERTUBE) and repetition counting (QUVA) benchmarks. We also collect a new challenging dataset called Countix (~90 times larger than existing datasets) which captures the challenges of repetition counting in real-world videos. Project webpage: https://sites.google.com/view/repnet .

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。

↑