Improving ADNet for Robust Tracking

Tiansa Zhang, Bo Wang, Zhiqiang Zhou, Zhe An

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

By taking advantages of the multi-domain structure and efficient searching strategy, ADNet (Action Decision Network) outperforms other approaches. However, its precision is limited due to the lack of detail feature caused by the improper network structure and other issues. Through our improvements, the proposed approach is more accurate than ADNet. Experiments demonstrate the advantages of our method.

源语言英语
主期刊名Proceedings of the 31st Chinese Control and Decision Conference, CCDC 2019
出版商Institute of Electrical and Electronics Engineers Inc.
3347-3351
页数5
ISBN(电子版)9781728101057
DOI
出版状态已出版 - 6月 2019
活动31st Chinese Control and Decision Conference, CCDC 2019 - Nanchang, 中国
期限: 3 6月 20195 6月 2019

出版系列

姓名Proceedings of the 31st Chinese Control and Decision Conference, CCDC 2019

会议

会议31st Chinese Control and Decision Conference, CCDC 2019
国家/地区中国
Nanchang
时期3/06/195/06/19

指纹

探究 'Improving ADNet for Robust Tracking' 的科研主题。它们共同构成独一无二的指纹。

引用此