Siamese recurrent architecture for visual tracking

Xiaqing Xu, Bingpeng Ma, Hong Chang, Xilin Chen

Abstract

Treating visual tracking as a matching problem, siamese architecture has drawn increasing interest recently. In this paper, we propose a novel siamese recurrent architecture that can enhance the similarity matching by leveraging contextual information. Specifically, the multi-directional Recurrent Neural Network (RNN) is employed to memorize the long-range contextual dependencies of object parts and learn the self-structure information of the object. We test the proposed method on a challenging benchmark, and it gain promising results compared with the existing tracking algorithms.
BibTeX
@inproceedings{xu2017siamese,
  author = {Xiaqing Xu and Bingpeng Ma and Hong Chang and Xilin Chen},
  title = {{Siamese recurrent architecture for visual tracking}},
  booktitle = {ICIP},
  year = {2017},
  doi = {10.1109/icip.2017.8296462},
}

Loading related content...

Figure