1. Introduction
Video Moment Retrieval (VMR) has been explored to find relevant fragments of videos (i.e. video moments) based on a user's textual query [10], [15]. Most existing VMR systems [10], [22], [38], [39], [42] cast the problem of finding video moments into a ranking problem. For evaluating ranked lists of video moments, R@K, is widely adopted in the literature [10]. R@K, for a query is defined as 1 if at least one relevant video moment in the top of the ranked list has an Intersection over Union (IoU) larger than with the ground truth for .