Video Visual Relation Detection

Video Visual Relation Detection (VidVRD) aims to detect instances of visual relations of interest in a video, where a visual relation instance is represented by a relation triplet <subject, predicate, object> with the trajectories of the subject and object. As compared to still images, videos provide a more natural set of features for detecting visual relations, such as the dynamic relations like “A-follow-B” and “A-towards-B”, and temporally changing relations like “A-chase-B” followed by “A-hold-B”. Yet, VidVRD is technically more challenging than ImgVRD due to the difficulties in accurate object tracking and diverse relation appearances in the video domain.

<span class="description-source">Source: ImageNet-VidVRD Video Visual Relation Dataset</span>