Is there a state-of-the-art deep learning paper that uses center point regression instead of bounding box regression, for object tracking?

Question

Almost all deep learning based object tracking methods perform bounding box regression. Siamese-based networks which are very popular for object tracking also perform bounding box regression most of the time, although SiamFC type exceptions exist. And some other networks use a detection + tracking mechanism using the center points of the objects, however, what I am looking for is whether any Siamese based networks that predict the center of the object rather than the bounding box exist. I searched the literature but couldn't find any, I would appreciate any guidance.

Answer 1

I know that some bounding box models like yolo has output of 4 channels: hight-center, width-center,hight-size, width. and with they constract the bounding box, so you can modify those models to use only the first 2 channels.