ML Anthology

Channel Pruning for Visual Tracking

Manqiang Che, Runling Wang, Yan Lu, Yan Li, Hui Zhi, Changzhen Xiong
ECCVW 2018 pp. 70-82
doi:10.1007/978-3-030-11009-3_3 /eccvw/2018/che2018eccvw-channel/

Abstract

Deep convolutional feature based Correlation Filter trackers have achieved record-breaking accuracy, but the huge computational complexity limits their application. In this paper, we derive the efficient convolution operators (ECO) tracker which obtains the top rank on VOT-2016. Firstly, we introduce a channel pruned VGG16 model to fast extract most representative channels for deep features. Then an Average Feature Energy Ratio method is put forward to select advantageous convolution channels, and an adaptive iterative strategy is designed to optimize object location. Finally, extensive experimental results on four benchmarks OTB-2013, OTB-2015, VOT-2016 and VOT-2017, demonstrate that our tracker performs favorably against the state-of-the-art methods.

PDF ECCVW Semantic Scholar

Cite

Text

Che et al. "Channel Pruning for Visual Tracking." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11009-3_3

Markdown

[Che et al. "Channel Pruning for Visual Tracking." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/che2018eccvw-channel/) doi:10.1007/978-3-030-11009-3_3

BibTeX

@inproceedings{che2018eccvw-channel,
  title     = {{Channel Pruning for Visual Tracking}},
  author    = {Che, Manqiang and Wang, Runling and Lu, Yan and Li, Yan and Zhi, Hui and Xiong, Changzhen},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {70-82},
  doi       = {10.1007/978-3-030-11009-3_3},
  url       = {https://mlanthology.org/eccvw/2018/che2018eccvw-channel/}
}