Segmentation, the task of delineating and isolating distinct objects, is a fundamental problem in computer vision. Much of the current approaches are supervised, relying on expensive manual annotations.

In the top left, we have the distribution of the number of frames in each video.

In order to provide more information and explanation about our training data and evaluation benchmark, we introduce our synthetic samples with respect to the length and density of point trajectory.

First, the point trajectories generated by these approaches only reflect the possible locations at certain moments instead of real motion trends because the frame-to-frame correspondence is temporally discrete and lacks enough inter-frame information to describe continuous point motion.

Segmentation, the task of delineating and isolating distinct objects, is a fundamental problem in computer vision. Much of the current approaches are supervised, relying on expensive manual annotations.

In the top left, we have the distribution of the number of frames in each video.

In order to provide more information and explanation about our training data and evaluation benchmark, we introduce our synthetic samples with respect to the length and density of point trajectory.