Siamese networks with distractor-reduction method for long-term visual object tracking. (April 2021)

• Record Type: Journal Article
• Authors: Xuan, Shiyu; Li, Shengyang; Zhao, Zifei; Kou, Longxuan; Zhou, Zhuang; Xia, Gui-Song
• Is Part Of: Pattern recognition. Volume 112(2021)
• Publication Date: 2021-04
• Subjects: Long-term object trakcing -- Siamese network -- Deep learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107698
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: 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 sub-networks. (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.