Xiaoyun Li

Mrs. Xiaoyun Li

China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
25 August 2020 in Electronics
Verified
Journal Article
Open access
PDF file
RFRuiqin Fan
Ruiqin Fan
XLXiaoyun Li
Xiaoyun Li
SLSanghyuk Lee
Sanghyuk Lee
TLTongliang Li
Tongliang Li
Haolan ZhangHaolan Zhang
Haolan Zhang
As technologies for image processing, image enhancement can provide more effective information for later data mining and image compression can reduce storage space. In this paper, a smart enhancement scheme during decompression, which combined a novel two-dimensional F-shift (TDFS) transformation and a non-standard two-dimensional wavelet transform (NSTW), is proposed. During the decompression, the first coefficient s00 of the wavelet synopsis was used to adaptively adjust the global gray level of the reconstructed image. Next, the contrast-limited adaptive histogram equalization (CLAHE) was used to achieve the enhancement effect. To avoid a blocking effect, CLAHE was used when the synopsis was decompressed to the second-to-last level. At this time, we only enhanced the low-frequency component and did not change the high-frequency component. Lastly, we used CLAHE again after the image reconstruction. Through experiments, the effectiveness of our scheme was verified. Compared with the existing methods, the compression properties were preserved and the image details and contrast could also be enhanced. The experimental results showed that the image contrast, information entropy, and average gradient were greatly improved compared with the existing methods.

18 May 2021 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
TYTan Yu
Tan Yu
XLXiaoyun Li
Xiaoyun Li
PLPing Li
Ping Li
Bilinear pooling has achieved an excellent performance in many computer vision tasks such as fine-grained classification, scene recognition and texture recognition. However, the high-dimension features from bilinear pooling can sometimes be inefficient and prone to over-fitting. Random Maclaurin (RM) is a widely used GPU-friendly approximation method to reduce the dimensionality of bilinear features. However, to achieve good performance, large projection matrices are usually required in practice, making it costly in computation and memory. In this paper, we propose a Shifted Random Maclaurin (SRM) strategy for fast and compact bilinear pooling. With merely negligible extra computational cost, the proposed SRM provides an estimator with a provably smaller variance than RM, which benefits accurate kernel approximation and thus the learning performance. Using a small projection matrix, the proposed SRM achieves a comparable estimation performance as RM based on a large projection matrix, and thus boosts the efficiency. Furthermore, we upgrade the proposed SRM to SRM+ to further improve the efficiency and make the compact bilinear pooling compatible with fast matrix normalization. Fast and Compact Bilinear Network (FCBN) built upon the proposed SRM+ is devised, achieving an end-to-end training. Systematic experiments conducted on four public datasets demonstrate the effectiveness and efficiency of the proposed FCBN.

24 July 2019 in Health Information Science and Systems
Verified
Journal Article
Closed access
PDF file
XLXiaoyun Li
Xiaoyun Li
TLTongliang Li
Tongliang Li
HZHuanyu Zhao
Huanyu Zhao
YDYuwei Dou
Yuwei Dou
CPChaoyi Pang
Chaoyi Pang

1 January 2021 in World Wide Web
Verified
Journal Article
Closed access
PDF file
XGXueyan Guo
Xueyan Guo
TLTongliang Li
Tongliang Li
XLXiaoyun Li
Xiaoyun Li
HZHuanyu Zhao
Huanyu Zhao
SWSuzhen Wang
Suzhen Wang
CPChaoyi Pang
Chaoyi Pang

2 February 2020
Verified
Book Chapter
Closed access
PDF file
RFRuiqin Fan
Ruiqin Fan
XLXiaoyun Li
Xiaoyun Li
HZHuanyu Zhao
Huanyu Zhao
Haolan ZhangHaolan Zhang
Haolan Zhang
CPChaoyi Pang
Chaoyi Pang
JWJunhu Wang
Junhu Wang