首页|Investigators at Nanchang Institute of Technology Report Findings in Intelligent Systems (Exploiting Multi-scale Hierarchical Feature Representation for Visual Tracking)
Investigators at Nanchang Institute of Technology Report Findings in Intelligent Systems (Exploiting Multi-scale Hierarchical Feature Representation for Visual Tracking)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning - Intelligent Systems.According to news reporting originating in Nanchang,People's Republic of China,by NewsRx journalists,research stated,"Convolutional neural networks (CNNs) have been the dominant architectures for feature extraction tasks,but CNNs do not look for and focus on some specific im age features.Correlation operations play an important role in visual tracking." Financial supporters for this research include National Natural Science Foundati on of China (NSFC),National Natural Science Foundation of China (NSFC).The news reporters obtained a quote from the research from the Nanchang Institut e of Technology,"However,the correlation operation reserves a large amount of unfavorable background information.In this paper,we propose an effective featu re recognizer including channel and spatial attention modules to focus on import ant object feature information.Thus,the representation power of the feature ex traction network is improved.Further,we design a multi-scale feature fusion ne twork.The fusion network performs feature fusion on template feature and encode d feature branches to establish connections between features at different scales .Experiments on six benchmarks demonstrate that the proposed tracker outperform s the state-of-the-art trackers."
NanchangPeople's Republic of ChinaAs iaIntelligent SystemsMachine LearningNanchang Institute of Technology
NETL
NSTL
