Once for All: a Two-flow Convolutional Neural Network for Visual Tracking

Understand

One of the main challenges of visual object tracking comes from the arbitrary appearance of objects.

• Most existing algorithms try to resolve this problem as an object-specific task, i.e., the model is trained to regenerate or classify a specific object.
• As a result, the model need to be initialized and retrained for different objects.
• In this paper, we propose a more generic approach utilizing a novel two-flow convolutional neural network (named YCNN).