The full benchmark contains 100 sequences from recent literatures.
The sequence names are in CamelCase without any blanks or underscores (_).
When there exist multiple targets each target is identified as dot+id_number (e.g. Jogging.1 and Jogging.2).
Each row in the ground-truth files represents the bounding box of the target in that frame,
(x, y, box-width, box-height).
In most sequences the first row corresponds to the first frame and the last row to the last frame, except the following sequences:
David(300:770), Football1(1:74), Freeman3(1:460), Freeman4(1:283).
This folder provides our produced "Peking University and Peng Cheng Laboratory 8K (PP8K)" video dataset, including "8K Common Raw Format Video (PP8K-CRFV) sequences" and "8K Video Salient Object Detection (PP8K-VSOD) sequences".