SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking

Peng, Jinlong; Jiang, Zhengkai; Gu, Yueyang; Wu, Yang; Wang, Yabiao; Tai, Ying; Wang, Chengjie; Lin, Weiyao

doi:10.24963/ijcai.2021/132

SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking

Jinlong Peng, Zhengkai Jiang, Yueyang Gu, Yang Wu, Yabiao Wang, Ying Tai, Chengjie Wang, Weiyao Lin

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 952-958.

https://doi.org/10.24963/ijcai.2021/132

Keywords

Computer Vision: Motion and Tracking
Computer Vision: Video: Events, Activities and Surveillance

Abstract

Recently, most siamese network based trackers locate targets via object classification and bounding-box regression. Generally, they select the bounding-box with maximum classification confidence as the final prediction. This strategy may miss the right result due to the accuracy misalignment between classification and regression. In this paper, we propose a novel siamese tracking algorithm called SiamRCR, addressing this problem with a simple, light and effective solution. It builds reciprocal links between classification and regression branches, which can dynamically re-weight their losses for each positive sample. In addition, we add a localization branch to predict the localization accuracy, so that it can work as the replacement of the regression assistance link during inference. This branch makes the training and inference more consistent. Extensive experimental results demonstrate the effectiveness of SiamRCR and its superiority over the state-of-the-art competitors on GOT-10k, LaSOT, TrackingNet, OTB-2015, VOT-2018 and VOT-2019. Moreover, our SiamRCR runs at 65 FPS, far above the real-time requirement.

Jinlong Peng, Zhengkai Jiang, Yueyang Gu, Yang Wu, Yabiao Wang, Ying Tai, Chengjie Wang, and Weiyao Lin. 2021. SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 952–958. https://doi.org/10.24963/ijcai.2021/132

@inproceedings{ijcai2021p132,
  title     = {SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking},
  author    = {Peng, Jinlong and Jiang, Zhengkai and Gu, Yueyang and Wu, Yang and Wang, Yabiao and Tai, Ying and Wang, Chengjie and Lin, Weiyao},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {952--958},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/132},
  url       = {https://doi.org/10.24963/ijcai.2021/132},
}

TY  - CPAPER
TI  - SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking
AU  - Peng, Jinlong
AU  - Jiang, Zhengkai
AU  - Gu, Yueyang
AU  - Wu, Yang
AU  - Wang, Yabiao
AU  - Tai, Ying
AU  - Wang, Chengjie
AU  - Lin, Weiyao
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 952
EP  - 958
DO  - 10.24963/ijcai.2021/132
UR  - https://doi.org/10.24963/ijcai.2021/132
ER  -