Siamese networks with distractor-reduction method for long-term visual object tracking

Many trackers which divide the tracking process into two stages have recently been proposed to solve the problem of long-term tracking. Their outstanding performance makes them become one of the mainstream algorithms of long-term tracking. To further improve the performance of two-stage tracking algorithms, some improvements are proposed in this paper. (a) A hard negative mining method is proposed. It can optimize the training process of the verification network and bridge the gap between the two subnetworks. (b) The architecture of the verification network is designed as a Siamese structure; therefore, the semantic ambiguity in classification can be alleviated. Extensive experiments performed on benchmarks demonstrate that the proposed approach significantly outperforms the state-of-the-art methods, yielding 7% relative gain in the VOT2018-LT dataset and 14.2% relative gain in the OxUvA dataset. (C) 2020 The Authors. Published by Elsevier Ltd.

Automated summary

This paper proposes improvements for two-stage tracking algorithms, including hard negative mining and Siamese network architecture design. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art methods, showing substantial relative gains in benchmark datasets.