Department | 光电探测与信号处理研究室(五室) |
Multi-feature fusion siamese network for real-time object tracking | |
Zhou, Lijun1; Li, Hongyun1; Zhang, Jianlin2 | |
Source Publication | ACM International Conference Proceeding Series |
Pages | 478-481 |
2018-12-08 | |
Language | 英语 |
DOI | 10.1145/3297156.3297259 |
Indexed By | Ei |
EI Accession Number | 20191106628876 |
Subtype | C |
Abstract | In the multilayer neural network, the features of the low-level layers are of high resolution, which is suitable for positioning the object, while the features of the high-level layers are of rich semantics features which are suitable for the classifying the object. In order to utilize the advantage of high-level features and low-level features, we introduce a densely connected network called DSiamFc(Densely Connected Siamese Networks). Not only the low-level features and high-level features are fully integrated, but also this connection method can provide better parameter adjustment for the whole network during off-line training for the end-to-end object tracking network. The effectiveness of our proposed network is demonstrated by analyzing the backpropagation of gradient flow. Our algorithm is able to achieve real-time, and in the OTB-2013/50/100 benchmark, our algorithm has the best performance compared to other state-of-the-art real-time object tracking algorithms. © 2018 Association for Computing Machinery. |
Keyword | Benchmarking Multilayer neural networks Multimedia systems Semantics |
EI Keywords | Benchmarking ; Multilayer neural networks ; Multimedia systems ; Semantics |
Conference Name | 2nd International Conference on Computer Science and Artificial Intelligence, CSAI 2018 |
Conference Date | December 8, 2018 - December 10, 2018 |
Conference Place | Shenzhen, China |
EI Classification Number | 723.5 Computer Applications |
Citation statistics | |
Document Type | 会议论文 |
Identifier | http://ir.ioe.ac.cn/handle/181551/9122 |
Collection | 光电探测与信号处理研究室(五室) |
Affiliation | 1.Institute of Optics and Electronics, Chinese Academy of Sciences, University of Chinese, Academy of Sciences, No.1, Optoelectronic Avenue, Wenxing Town, Shuangliu District, Chengdu, China; 2.Institute of Optics and Electronics, Chinese Academy of Sciences, No.1, Optoelectronic Avenue, Wenxing Town, Shuangliu District, Chengdu, China |
Recommended Citation GB/T 7714 | Zhou, Lijun,Li, Hongyun,Zhang, Jianlin. Multi-feature fusion siamese network for real-time object tracking[C],2018:478-481. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
2018-2145.pdf(698KB) | 会议论文 | 开放获取 | CC BY-NC-SA | Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment