Real-time 'Actor-Critic' Tracking
In this work, we propose a novel tracking algorithm with real-time performance based on the âActor-Criticâ framework. This framework consists of two major components: âActorâ and âCriticâ. The âActorâ model aims to infer the optimal choice in a continuous action space, which directly makes the tracker move the bounding box to the object location in the current frame. For ofï¬ine training,theâCriticâmodelisintroducedtoformaâActor-Criticâframeworkwith reinforcement learning and outputs a Q-value to guide the learning process of both âActorâ and âCriticâ deep networks. Then, we modify the original deep deterministic policy gradient algorithm to effectively train our âActor-Criticâ model for the tracking task. For online tracking, the âActorâ model provides a dynamic search strategy to locate the tracked object efï¬ciently and the âCriticâ model acts as a veriï¬cation module to make our tracker more robust. To the best of our knowledge, this work is the ï¬rst attempt to exploit the continuous action and âActor-Criticâ framework for visual tracking. Extensive experimental results on popular benchmarks demonstrate that the proposed tracker performs favorably against many state-of-the-art methods, with real-time performance.
PDF Abstract