Xiangyu Ji

Xiangyu Ji

Auto-generated profile, based on publicly available information

Xiangyu Ji

KlingAI, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
JGJingpeng Gao
Jingpeng Gao
XJXiangyu Ji
Xiangyu Ji
FYFang Ye
Fang Ye
GCGeng Chen
Geng Chen

14 December 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
JGJingpeng Gao
Jingpeng Gao
XJXiangyu Ji
Xiangyu Ji
GCGeng Chen
Geng Chen
RGRuitong Guo
Ruitong Guo
Due to their spatial and spectral information, hyperspectral images are frequently used in various scientific and industrial fields. Recent developments in hyperspectral image classification have revolved around the use of convolutional neural networks (CNNs) and transformers, which are capable of modeling local and global data. However, most of the backbone networks of existing methods are based on 3-D convolution, which have high complexity in network structure. Moreover, local information and global information are extracted through different modules, and the coupling relationship between the two types of information is weak. To address the above issues, we propose a method named main-sub transformer network with spectral-spatial separable convolution method (MST-SSSNet), which includes two key modules: the spectral-spatial separable convolution (SSSC) module and the main-sub transformer encoder (MST) module. The SSSC module uses the proposed spectral-spatial separable convolution, reducing network parameters and efficiently extracting local features. The MST module adds the designed sub-transformer in front of the conventional transformer encoder (main-transformer). It assists the main-transformer encoder to establish global correlation by learning local information. The WHU-Hi dataset can be used as a benchmark dataset for precise crop classification and hyperspectral image classification research. MST-SSSNet is shown to deliver better classification performance than current state-of-the-art methods on the datasets. The code will be downloaded to https://github.com/fengqinshou/MST-SSSNet .

27 April 2020 in Applied Microbiology and Biotechnology
Verified
Journal Article
Closed access
PDF file
XJXiangyu Ji
Xiangyu Ji
HZHuiwei Zhao
Huiwei Zhao
HZHua Zhu
Hua Zhu
Kun Yan ZhuKun Yan Zhu
Kun Yan Zhu
STShuang-Yan Tang
Shuang-Yan Tang
Chunbo LouChunbo Lou
Chunbo Lou

14 June 2024 in Signal Processing
Verified
Journal Article
Closed access
JGJingpeng Gao
Jingpeng Gao
SJSisi Jiang
Sisi Jiang
XJXiangyu Ji
Xiangyu Ji
CSChen Shen
Chen Shen

15 January 2025 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
JGJingpeng Gao
Jingpeng Gao
XJXiangyu Ji
Xiangyu Ji
GCGeng Chen
Geng Chen
YHYuhang Huang
Yuhang Huang
FYFang Ye
Fang Ye

31 May 2025 in Signal Processing
Verified
Journal Article
Closed access
JGJingpeng Gao
Jingpeng Gao
GCGeng Chen
Geng Chen
XJXiangyu Ji
Xiangyu Ji
CSChen Shen
Chen Shen