Z
Zhengxia Zou
Researcher at University of Michigan
Publications - 78
Citations - 2763
Zhengxia Zou is an academic researcher from University of Michigan. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 15, co-authored 50 publications receiving 1215 citations. Previous affiliations of Zhengxia Zou include Beihang University.
Papers
More filters
Posted Content
Object Detection in 20 Years: A Survey
TL;DR: This paper extensively reviews 400+ papers of object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019), and makes an in-deep analysis of their challenges as well as technical improvements in recent years.
Journal ArticleDOI
Ship Detection in Spaceborne Optical Image With SVD Networks
Zhengxia Zou,Zhenwei Shi +1 more
TL;DR: A novel ship detection method called SVD Networks (SVDNet), which is fast, robust, and structurally compact, designed based on the recent popular convolutional neural networks and the singular value decompensation algorithm is proposed.
Journal ArticleDOI
Super-Resolution for Remote Sensing Images via Local–Global Combined Network
Sen Lei,Zhenwei Shi,Zhengxia Zou +2 more
TL;DR: This letter proposes a new single-image super-resolution algorithm named local–global combined networks (LGCNet) for remote sensing images based on the deep CNNs, elaborately designed with its “multifork” structure to learn multilevel representations ofRemote sensing images including both local details and global environmental priors.
Journal ArticleDOI
Random Access Memories: A New Paradigm for Target Detection in High Resolution Aerial Remote Sensing Images
Zhengxia Zou,Zhenwei Shi +1 more
TL;DR: Experimental results on a public remote sensing target detection data set show the proposed new paradigm “random access memories (RAM)” outperforms several other state of the art methods.
Journal ArticleDOI
Can a Machine Generate Humanlike Language Descriptions for a Remote Sensing Image
Zhenwei Shi,Zhengxia Zou +1 more
TL;DR: This paper has proposed a remote sensing image captioning framework by leveraging the techniques of the recent fast development of deep learning and fully convolutional networks and demonstrates that the proposed method is able to generate robust and comprehensive sentence description with desirable speed performance.