Simultaneous Video Retrieval and Alignment

With the growth of the video streaming industry, video retrieval and video alignment are facing high levels of demand. Several studies have demonstrated the feasibility of these methods for various problems related to video retrieval and alignment independently, but testing in a unified framework has never been done. However, in real-world applications, it is also simultaneously necessary not only to find which video pairs are similar (video retrieval), but also to align the positions of the pairs that are related (video alignment). In this paper, we present a novel task: simultaneous video retrieval and alignment. As a solution to this task, a Simultaneous video Retrieval and Alignment framework, abbreviated as SRA, is proposed, which is a two-stage approach consisting of a foreground proposal stage and a downstream stage to efficiently process untrimmed videos. Furthermore, two criteria are suggested to support the new task: a metric mAP@J assessing how highly related videos are ranked and how well relevant positions are assigned in those videos, and a dataset FIVR+A that includes video-level relationships and hierarchical segment-level annotations. Finally, we conduct multi-pronged analyses to assess how our approach handles the new task in various experiments.