Introduced by Matej Kristan et al. in The Visual Object Tracking VOT2016 Challenge Results

VOT2016 is a video dataset for visual object tracking. It contains 60 video clips and 21,646 corresponding ground truth maps with pixel-wise annotation of salient objects.

Source: Video Saliency Detection by 3D Convolutional Neural Networks


Paper Code Results Date Stars

Dataset Loaders


Similar Datasets