Deep Learning of Appearance Models for Online Object Tracking

Mengyao Zhai, Lei Chen, Greg Mori, Mehrsan Javan Roshtkhari

ECCVW 2018 pp. 681-686

doi:10.1007/978-3-030-11018-5_57 /eccvw/2018/zhai2018eccvw-deep/

Abstract

This paper introduces a deep learning based approach for vision based single target tracking. We address this problem by proposing a network architecture which takes the input video frames and directly computes the tracking score for any candidate target location by estimating the probability distributions of the positive and negative examples. An online fine-tuning step is carried out at every frame to learn the appearance of the target. The tracker has been tested on the standard tracking benchmark and the results indicate that the proposed solution achieves state-of-the-art tracking results.

PDF ECCVW Semantic Scholar

Cite

Text

Zhai et al. "Deep Learning of Appearance Models for Online Object Tracking." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11018-5_57

Markdown

[Zhai et al. "Deep Learning of Appearance Models for Online Object Tracking." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/zhai2018eccvw-deep/) doi:10.1007/978-3-030-11018-5_57

BibTeX

@inproceedings{zhai2018eccvw-deep,
  title     = {{Deep Learning of Appearance Models for Online Object Tracking}},
  author    = {Zhai, Mengyao and Chen, Lei and Mori, Greg and Roshtkhari, Mehrsan Javan},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {681-686},
  doi       = {10.1007/978-3-030-11018-5_57},
  url       = {https://mlanthology.org/eccvw/2018/zhai2018eccvw-deep/}
}