Study on Deep Learning and Its Application in Visual Tracking

Dan Hu, Xingshe Zhou, Xiaohao Yu, Zhiqiang Hou

科研成果: 书/报告/会议事项章节会议稿件同行评审

4 引用 (Scopus)

摘要

Inspired by recent advances in deep learning, this paper reviews the deep learning methodologies and its applications in object tracking. To overcome the complexity and low-efficiency of existing full-connected deep learning based tracker, we use a novel convolutional deep belief network (CDBN) with convolution, weights sharing and pooling to have much fewer parameters, in addition to gain translation invariance which would benefit the tracker performance. Empirical evaluation demonstrates our CDBN based tracker outperforms several state-of-the-art methods on an open tracker benchmark.

源语言英语
主期刊名Proceedings - 2015 10th International Conference on Broadband and Wireless Computing, Communication and Applications, BWCCA 2015
编辑Leonard Barolli, Marek R. Ogiela, Fatos Xhafa, Lidia Ogiela
出版商Institute of Electrical and Electronics Engineers Inc.
240-246
页数7
ISBN(电子版)9781467383158
DOI
出版状态已出版 - 2015
已对外发布
活动10th International Conference on Broadband and Wireless Computing, Communication and Applications, BWCCA 2015 - Krakow, 波兰
期限: 4 11月 20156 11月 2015

出版系列

姓名Proceedings - 2015 10th International Conference on Broadband and Wireless Computing, Communication and Applications, BWCCA 2015

会议

会议10th International Conference on Broadband and Wireless Computing, Communication and Applications, BWCCA 2015
国家/地区波兰
Krakow
时期4/11/156/11/15

指纹

探究 'Study on Deep Learning and Its Application in Visual Tracking' 的科研主题。它们共同构成独一无二的指纹。

引用此