Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking. (arXiv:2007.01864v4 [cs.CV] UPDATED)

Most existing trackers are based on using a classifier and multi-scale
estimation to estimate the target state. Consequently, and as expected,
trackers have become more stable while tracking accuracy has stagnated. While
trackers adopt a maximum overlap method based on an intersection-over-union
(IoU) loss to mitigate this problem, there are defects in the IoU loss itself,
that make it impossible to continue to optimize the objective function when a
given bounding box is completely contained within/without another bounding box;
this …

arxiv cv regression tracking