On the use of Deep Reinforcement Learning for Visual Tracking: a Survey

This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep learning (DRL) is an emerging area combining recent progress and It showing interesting computer vision and, recently, it has been applied to problem yielding rapid development novel strategies. After providing introduction learning, this compares approaches based on Analysis state-of-the-art suggests that allows modeling varying parts system including target bounding box regression, appearance model selection, hyper-parameter optimization. The DRL framework elegant intriguing, most DRL-based trackers achieve results.