Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search. (arXiv:2205.09676v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2205.09676

To track the target in a video, current visual trackers usually adopt greedy
search for target object localization in each frame, that is, the candidate
region with the maximum response score will be selected as the tracking result
of each frame. However, we found that this may be not an optimal choice,
especially when encountering challenging tracking scenarios such as heavy
occlusion and fast motion. To address this issue, we propose to maintain
multiple tracking trajectories and apply beam search …

arxiv cv learning reinforcement reinforcement learning search tracking