Peixia Li

TL;DR: The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.

TL;DR: The background of deep visual tracking is introduced, including the fundamental concepts of visual tracking and related deep learning algorithms, and the existing deep-learning-based trackers are categorize into three classes according to network structure, network function and network training.

TL;DR: In this paper, a gradient-guided siamese network is proposed to exploit the discriminative information in gradients and update the template in the Siamese networks through feed-forward and backward operations.

TL;DR: This work modifications the original deep deterministic policy gradient algorithm to effectively train the ‘Actor-Critic’ model for the tracking task and demonstrates that the proposed tracker performs favorably against many state-of-the-art methods, with real-time performance.

TL;DR: A novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations and a template generalization training method is proposed to better use gradient information and avoid overfitting.