SMART: Joint Sampling and Regression for Visual Tracking

Junyu Gao, Tianzhu Zhang, Changsheng Xu

Abstract

Most existing trackers are either sampling-based or regression-based methods. Sampling-based methods estimate the target state by sampling many target candidates. Although these methods achieve significant performance, they often suffer from a high computational burden. Regression-based methods often learn a computationally efficient regression function to directly predict the geometric distortion between frames. However, most of these methods require large-scale external training videos and are still not very impressive in terms of accuracy. To make both types of methods enhance and complement each other, in this paper, we propose a joint sampling and regression scheme for visual tracking, which leverages the region proposal network by a novel design. Specifically, our method can jointly exploit discriminative target proposal generation and structural target regression to predict target location in a simple feedforward propagation. We evaluate the proposed method on five challenging benchmarks, and extensive experimental results demonstrate that our method performs favorably compared with state-of-the-art trackers with respect to both accuracy and speed.
BibTeX
@article{gao2019smart,
  author = {Junyu Gao and Tianzhu Zhang and Changsheng Xu},
  title = {{SMART: Joint Sampling and Regression for Visual Tracking}},
  journal = {IEEE Trans. Image Process.},
  year = {2019},
  url = {https://openreview.net/forum?id=3xE9I-mMIZa},
}

Loading related content...

Figure