SLShengwu Li

Shengwu Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shengwu Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:

  • Chenjing Ning

    School of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi'an Shaanxi China

    1 shared publication
  • Jing Xiong

    School of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi'an Shaanxi China

    1 shared publication
  • Mingke Zhang

    School of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi'an Shaanxi China

    1 shared publication
  • Xuande Zhang

    School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710021, China

    1 shared publication

Latest Publications

  • Open Access

    Learning spatial self‐attention information for visual tracking

    by Shengwu Li, Xuande Zhang, Jing Xiong, Chenjing Ning, Mingke Zhang

    Visual object tracking has been a fundamental topic in computer vision and many convolutional neural network (CNN) based trackers proposed in recent years have achieved state‐of‐the‐art performance, multi‐domain convolutional neural network (MDNet) is one of the most representative CNN‐based algorithms with high performance. In order to significantly improve the robustness and accuracy of the MDNet algorithm, a multi‐domain convolutional neural network based on spatial self‐attention information learning (SAMDNet) is proposed in this study. The authors use the spatial self‐attention module for the spatial information learning of the model. The spatial self‐attention module selectively aggregates the feature at each position by a weighted sum of the features at all positions. Under the control of self‐learning parameters in this module, spatial attention information can be flexibly acquired. The authors also propose a novel interval loss term to solve the problem of different classes with the same semantics in the training data. Finally, an anomaly detection module is carefully designed for relocation after the algorithm completely lost the target. Extensive experiments on the object tracking benchmark (OTB) and the visual object tracking challenge (VOT) benchmarks show that the proposed tracker outperforming most of the state‐of‐art trackers.