Multi-feature fusion siamese network for real-time object tracking

doi:10.1145/3297156.3297259

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 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, Lijun 1; Li, Hongyun 1; Zhang, Jianlin 2
	2018-12-08
会议日期	December 8, 2018 - December 10, 2018
会议地点	Shenzhen, China
关键词	Benchmarking Multilayer neural networks Multimedia systems Semantics
DOI	10.1145/3297156.3297259
页码	478-481
英文摘要	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.
会议录	ACM International Conference Proceeding Series
文献子类	C
语种	英语
内容类型	会议论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9122]
专题	光电技术研究所_光电探测与信号处理研究室（五室）
作者单位	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
推荐引用方式 GB/T 7714	Zhou, Lijun,Li, Hongyun,Zhang, Jianlin. Multi-feature fusion siamese network for real-time object tracking[C]. 见:. Shenzhen, China. December 8, 2018 - December 10, 2018.