個人簡介

研究偏向：自然圖像處理、醫學圖像分析

教育及事情經曆：

2021.06至今，深圳技術大學，康健與環境工程學院，助理教授；

2019.09——2021.05，香港科技大學，電子與計算機工程學系，博士後研究員；

2017.09——2018.01，倫敦大學學院，統計科學系，訪問學者；

2014.09——2019.07，清華大學，信息與通信工程，工學博士；

2009.08——2014.07，清華大學，電子信息科學與技術，工學學士。

基金項目：

1、国家自然科学基金委员会,青年科学基金项目, 62301332,基于小波交织注意力机制的单幅图像可变光圈散焦增强研究, 2024-01-01至2026-12-31, 30万元,在研,主持

2、深圳技术大学,新引进高端人才财政补助科研启动项目, GDRC202117,基于深度学习的乳腺癌患者生存风险预测与分析, 2022-01-01至2024-12-31, 270万元,在研,主持

3、国家自然科学基金委员会,面上项目, 62373259,基于双气囊稳定性增强的经支气管手术机械人自主介入机理与精准调控要领, 2024-01-01至2027-12-31, 50万元,在研,加入

4、香港科技创新署,创新及科技支援计划,ITS/480/18FP,利用图像数据和基因组数据预测乳腺癌治疗后的转移, 2019-08-01至2022-05-31, 700万元（港币）,已结题,加入

5、国家自然科学基金委员会,面上项目, 61771276,基于局部视图的超高分辨率RGB-D全景图像的融合与生成, 2018-01-01至2021-12-31, 62万元,已结题,加入

6、深圳市科技创新委员会,基础研究项目, JCYJ20140417115840272,基于全景视图和局部视图的超高清分辨率图像融合与生成, 2014-10-22至2016-10-22, 30万元,已结题,加入

學術論文：

主要從事自然圖像和醫學圖像的分析和處理，具體研究偏向包罗多聚焦圖像融合、單幅圖像散焦估計及其應用、病理學組織切片圖像分析、CT/MRI圖像分析等。已發表論文16篇（其中第一作者或唯一通訊作者論文13篇），論文主要發表在IEEE TIP、IEEE TMM、Pattern Recognition、Pattern Recognition Letters、ICME、MICCAI、EMBC、ISBI等期刊或會議。部门論文如下（#爲配合一作，*爲通訊作者）：

1、Shaojun Liu, Fei Zhou* and Qingmin Liao, Defocus Map Estimation From a Single Image Based on Two-Parameter Defocus Model,IEEE Transactions on Image Processing(IF=4.828 for 2016), vol. 25, no. 12, pp. 5943-5956, December 2016. (SCI,中科院一区TOP, CCF-A)

2、Shaojun Liu, Qingmin Liao, Jing-Hao Xue and Fei Zhou*, Defocus Map Estimation From a Single Image Using Improved Likelihood Feature and Edge-Based Basis,Pattern Recognition(IF=7.740 for 2020), pp. 107485, November 2020. (SCI,中科院一区TOP, CCF-B)

3、Haoyu Ma#,Shaojun Liu#, Qingmin Liao*, Juncheng Zhang and Jing-Hao Xue, Defocus Image Deblurring Network with Defocus Map Estimation as Auxiliary Task,IEEE Transactions on Image Processing(IF=11.041 for 2021), vol. 31, pp. 216-226,December2021. (SCI,中科院一区TOP, CCF-A)

4、Haoyu Ma, Qingmin Liao, Juncheng Zhang,Shaojiu Liu* and Jing-Hao Xue, An alpha-Matte Boundary Defocus Model-Based Cascaded Network for Multi-Focus Image Fusion,IEEE Transactions on Image Processing(IF=10.856 for 2020), vol. 29, pp. 8668-8679, August 2020. (SCI,中科院一区TOP, CCF-A)

5、Juncheng Zhang, Qingmin Liao,Shaojun Liu*, Haoyu Ma, Wenming Yang and Jing-Hao Xue, Real-MFF: A large realistic multi-focus image dataset with ground truth,Pattern Recognition Letters(IF=3.756 for 2020), vol. 138, pp. 370-377, October 2020. (SCI,中科院三区,CCF-C)

6、Juncheng Zhang, Qingmin Liao, Haoyu Ma, Jing-Hao Xue, Wenming Yang andShaojun Liu*, Exploit the Best of Both End-to-End and Map-Based Methods for Multi-Focus Image Fusion,IEEE Transactions on Multimedia(IF=7.3 for now), vol. 26, pp. 6411-6423,January2024. (SCI,中科院一区TOP, CCF-B)

7、Haoyu Ma, Juncheng Zhang,Shaojun Liu* and Qingmin Liao, Boundary Aware Multi-focus Image Fusion Using Deep Neural Network,2019 IEEE International Conference on Multimedia and Expo (ICME), 2019, pp. 1150-1155. (EI, poster, CCF-B)

8、Kuayue Zhang, Qingmin Liao, Juncheng Zhang,Shaojun Liu*, Haoyu Ma and Jing-Hao Xue, EFRNet: A Lightweight Network with Efficient Feature Fusion and Refinement for Real-Time Semantic Segmentation,2021 IEEE International Conference on Multimedia and Expo (ICME), 2021. (EI, oral, CCF-B)

9、Yi Liu#, Juncheng Zhang#, Qingmin Liao, Haoyu Ma andShaojun Liu*, Feature Pyramid Boosting Network For Rendering Natural Bokeh,2022 IEEE International Conference on Multimedia and Expo (ICME), 2022. (EI, poster,CCF-B)

10、Shoujin Huang#, Jingyu Li#, Lifeng Mei, Tan Zhang, Ziran Chen, Yu Dong, Linzheng Dong,Shaojun Liu*and Mengye Lyu*,Accurate Multi-contrast MRI Super-Resolution via a Dual Cross-Attention Transformer Network,26^thInternational Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI),2023, pp. 313-322. (EI, poster, CCF-B)

11、Tianzhao Zhong,Huaishui Yang, Jihao Li, Mengye Lyu andShaojun Liu*, WaveU3S: A Lightweight Wavelet Dual-Attention Unet for 3D Medical Image Segmentation,21^stInternational Symposium on Biomedical Imaging (ISBI), 2024. (EI, poster, to appear)

12、Jincai Huang, Jianyuan Zeng, Jinfeng Peng, Mengye Lyu andShaojun Liu*, Endoscopic colorectal polyp detection based on improved YOLOv8,46^thAnnual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2024. (EI, poster, to appear)

13、ShiyueYan#, Xiaoshi Qiu#, Qingmin Liao, Jing-Hao Xue andShaojun Liu*,Reschedule Diffusion-based Bokeh Rendering,33^rdInternational Joint Conference on Artificial Intelligence(IJCAI), 2024. (EI, to appear, CCF-A)

專利：

1、劉少軍,黃金財,曾健源,彭錦峰,一種基于改進YOLOv8與VGG19模型的內窺鏡圖像檢測要领,CN202311352017.9,實質審查中

2、劉少軍,王霁元,徐童,一種基于1D和2D跨維度雙路並行的心電圖信號分類要领,CN202311479478.2,實質審查中

3、劉少軍,鍾天兆,一種基于小波雙注意力的輕量級3D醫學圖像支解要领,CN202410015380.X,申請中

學生獲獎：

1、2023年指導2021級智能醫學工程專業本科生黃金財、曾健源、彭錦峰獲第八屆全國大學生生物醫學工程創新設計競賽，獲國賽二等獎

聯系方式：

郵箱：liusj14@tsinghua.org.cn；liushaojun@ffjwd.com

Google Scholar主页：https://scholar.google.com/citations?user=u9cbGYQAAAAJ

ORCID主頁：https://orcid.org/0000-0002-9201-9301

招聘信息：

歡迎對圖像處理感興趣的各類專業配景（電子信息、計算機、智能醫學工程、自動化、生物醫學工程等）本科生和研究生加入本課題組學習，實習和交換。