从海洋中同步：从大规模数据集中检索可对齐视频
Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets
AI总结：
本文将时间视频对齐重新定义为可对齐视频检索（AVR）任务，提出DRAQ可对齐性指标、帧级特征设计和循环一致性评估协议，并在大规模数据集上验证了从视频集合中检索并同步可对齐视频的有效性。
摘要：
时间视频对齐旨在同步两个视频中的关键事件，例如物体交互或动作阶段转换。这类方法可以有益于各种视频编辑、处理和理解任务。然而，现有方法都在一个限制性假设下运行，即已经给定一对适合对齐的视频，这显著限制了它们的更广泛应用。为了解决这一问题，我们将时间对齐重新表述为一个搜索问题，并引入了可对齐视频检索（AVR）任务。给定一个查询视频，我们的方法能够从大量视频片段集合中识别出可良好对齐的视频，并将它们在时间上与查询视频同步。为了实现这一目标，我们做出了三项关键贡献：1）我们引入了DRAQ，一种视频可对齐性指标，用于从候选集中识别并重新排序最佳可对齐视频；2）我们提出了一种有效且可泛化的帧级视频特征设计，以提升多种现成特征表示的对齐性能；3）我们提出了一种新的AVR基准和评估协议，使用循环一致性度量。我们在3个数据集上进行了实验，包括大规模Kinetics700，证明了我们的方法在从多样化数据集中识别可对齐视频对方面的有效性。项目页面：https://daveishan.github.io/avr-webpage/。
英文摘要：
Temporal video alignment aims to synchronize the key events like object interactions or action phase transitions in two videos. Such methods could benefit various video editing, processing, and understanding tasks. However, existing approaches operate under the restrictive assumption that a suitable video pair for alignment is given, significantly limiting their broader applicability. To address this, we re-pose temporal alignment as a search problem and introduce the task of Alignable Video Retrieval (AVR). Given a query video, our approach can identify well-alignable videos from a large collection of clips and temporally synchronize them to the query. To achieve this, we make three key contributions: 1) we introduce DRAQ, a video alignability indicator to identify and re-rank the best alignable video from a set of candidates; 2) we propose an effective and generalizable frame-level video feature design to improve the alignment performance of several off-the-shelf feature representations, and 3) we propose a novel benchmark and evaluation protocol for AVR using cycle-consistency metrics. Our experiments on 3 datasets, including large-scale Kinetics700, demonstrate the effectiveness of our approach in identifying alignable video pairs from diverse datasets. Project Page: https://daveishan.github.io/avr-webpage/.
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。
