Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search. (arXiv:2205.09676v1 [cs.CV])

Existing trackers usually select a location or proposal with the maximum
score as tracking result for each frame. However, such greedy search scheme
maybe not the optimal choice, especially when encountering challenging tracking
scenarios like heavy occlusions and fast motion. Since the accumulated errors
would make response scores not reliable anymore. In this paper, we propose a
novel multi-agent reinforcement learning based beam search strategy (termed
BeamTracking) to address this issue. Specifically, we formulate the tracking as
a sample selection …

arxiv cv learning reinforcement reinforcement learning search tracking