Abstract: The human visual system naturally prioritizes unique and salient objects within a scene. In computer vision, visual saliency refers to the property that makes specific regions stand out in ...
Abstract: The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results