基本信息

薛健 男 工程科学学院 教授
电子邮件:xuejian@ucas.ac.cn
通信地址:北京玉泉路19号(甲)
邮政编码:100049

研究领域

数字图像分析与处理,计算机图形学,科学计算可视化

教育背景

2002-09--2007-07 中国科学院自动化研究所 获计算机应用技术专业工学博士学位
1998-09--2002-07 南京大学计算机科学与技术系 获计算机科学与技术专业理学学士学位

教授课程

云计算
算法概论
图形学与可视化
计算机算法设计与分析
图形学技术实践
计算机图形学
科学计算可视化理论与实践
算法设计及应用
科学计算可视化讨论课

专利与奖励

[1] 一种基于不等尺寸分块的海量数据并行体绘制方法, ZL201910091777.6
[2] 一种块体理论平衡区域图的三维可视化方法, ZL201710338255.2
[3] 分布式混合架构的海量数据处理和可视化系统及方法, ZL201410498051.1
[4] 一种基于三维纹理硬件加速的海量数据体绘制方法, ZL200710065336.6
[5] 一种实时自由臂三维超声成像系统及其方法, ZL200610011160.1


出版信息

发表论文

[1] Liping Hou, Ke Lu, Jian Xue*. Refined One-Stage Oriented Object Detection Method for Remote Sensing Images. IEEE Transactions on Image Processing. Vol. 31, pp. 1545-1558, 2022 (DOI: 10.1109/TIP.2022.3143690)

[2] Liping Hou, Ke Lu, Jian Xue*, Yuqiu Li. Shape-Adaptive Selection and Measurement for Oriented Object Detection. the 36th AAAI Conference on Artificial Intelligence (AAAI-22), Vancouver, BC, Canada, Feb. 22-Mar. 1, 2022

[3] Cong Wang, Jian Xue, Ke Lu*, Yanfu Yan. Light Attention Embedding for Facial Expression Recognition. IEEE Transactions on Circuits and Systems for Video Technology. Volume 32, Issue 4, pp. 1834-1847, Apr. 2022 (DOI: 10.1109/TCSVT.2021.3083326)

[4] Pengcheng Gao, Ke Lu, Jian Xue*, Jiayi Lyu, Ling Shao. A Facial Landmark Detection Method Based on Deep Knowledge Transfer. IEEE Transactions on Neural Networks and Learning Systems. (Early Access, DOI: 10.1109/TNNLS.2021.3105247)

[5] Pengcheng Gao, Ke Lu, Jian Xue*, Ling Shao, Jiayi Lyu. A Coarse-to-fine Facial Landmark Detection Method based on Self-attention Mechanism. IEEE Transactions on Multimedia. Vol. 23, pp. 926-938, 2021 (DOI: 10.1109/TMM.2020.2991507)

[6] Zehai Niu, Ke Lu, Jian Xue*, Haifeng Ma, Runchen Wei. Multi-view 3D Smooth Human Pose Estimation based on Heatmap Filtering and Spatio-temporal Information. the 29th ACM International Conference on Multimedia (MM’21), pp. 442-450, Chengdu, China, Oct. 20-24, 2021 (DOI: 10.1145/3474085.3475185)

[7] Chao Wei, Ke Lu, Wei Gan, Jian Xue*. Spatiotemporal Features and Local Relationship Learning for Facial Action Unit Intensity Regression. 2021 IEEE International Conference on Image Processing (ICIP), pp. 1109-1113, Anchorage, AK, USA, Sep. 19-22, 2021 (DOI: 10.1109/ICIP42928.2021.9506789)

[8] Bin Huang, Jian Xue, Ke Lu*, Yanhao Tan, and Yang Zhao. MPNet: Multi-scale Parallel Codec Net for Medical Image Segmentation. CAAI International Conference on Artificial Intelligence (CICAI 2021), LNAI 13069, pp.492-503, 2021 (DOI: 10.1007/978-3-030-93046-2_42)

[9] Pengcheng Gao, Ke Lu, Jian Xue*. EfficientFAN: Deep Knowledge Transfer for Face Alignment. 2020 International Conference on Multimedia Retrieval (ICMR '20), pp. 215–223, Dublin, Ireland, Oct. 26–29, 2020 (DOI: 10.1145/3372278.3390692)

[10] Li Hao, Liping Hou, Yuantao Song, Ke Lu, Jian Xue*. A Lightweight Gated Global Module for Global Context Modeling in Neural Networks. 2020 International Conference on Multimedia Retrieval (ICMR '20), pp. 532–539, Dublin, Ireland, Oct. 26–29, 2020 (DOI: 10.1145/3372278.3390712)

[11] Liping Hou, Ke Lu, Jian Xue*, Li Hao. Cascade Detector with Feature Fusion for Arbitrary-Oriented Objects in Remote Sensing Images. 2020 IEEE International Conference on Multimedia and Expo (ICME), London, United Kingdom, Jul. 6-10, 2020 (DOI: 10.1109/ICME46284.2020.9102807)

[12] Yanhao Tan, Ke Lu, Mohammad Muntasir Rahman, Jian Xue*. RGBD-FG: A Large-Scale RGB-D Dataset for Fine-Grained Categorization. 2020 IEEE International Conference on Multimedia and Expo (ICME), London, United Kingdom, Jul. 6-10, 2020 (10.1109/ICME46284.2020.9102848)

[13] 闫衍芙, 吕科, 薛健*, 王聪, 甘玮. 基于深度学习和表情AU参数的人脸动画方法. 计算机辅助设计与图形学学报, 31(11):1973-1980, 2019 (DOI: 10.3724/SP.J.1089.2019.17682)

[14] Cong Wang, Ke Lu, Jian Xue*, Yanfu Yan. Dense Attention Network for Facial Expression Recognition in the Wild. 2019 ACM Multimedia Asia, Beijing, China, Dec. 16-18, 2019 (DOI: 10.1145/3338533.3366568)

[15] Yanhao Tan, Ke Lu, Jian Xue*. An Automated Lung Nodule Segmentation Method Based on Nodule Detection Network and Region Growing. 2019 ACM Multimedia Asia, Beijing, China, Dec. 16-18, 2019 (10.1145/3338533.3366604)

[16] Liping Hou, Jian Xue, Ke Lu, Li Hao, Mohammad Muntasir Rahman. A Single-stage Multi-class Object Detection Method for Remote Sensing Images. 2019 IEEE International Conference on Visual Communications and Image Processing (VCIP 2019), Sydney, Australia, Dec. 1-4, 2019 (DOI: 10.1109/VCIP47243.2019.8965940)

[17] Jian Xue, Xiaoye Zhu, Ke Lu, Yutong Kou. Parallel Volume Rendering Method for Out-of-Core Non-Uniformly Partitioned Datasets. 2019 IEEE International Conference on Multimedia & Expo Workshops, ICMEW 2019, pp. 599-602, Shanghai, China, Jul. 8-12, 2019 (10.1109/ICMEW.2019.00109)

[18] Yanfu Yan, Ke Lu, Jian Xue*, Pengcheng Gao, Jiayi Lyu. FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation. 2019 IEEE International Conference on Multimedia & Expo Workshops, ICMEW 2019, pp. 96-101, Shanghai, China, Jul. 8-12, 2019 (10.1109/ICMEW.2019.0-104)

[19] Jinbao Wang, Ke Lu, Jian Xue*, Yutong Kou. Relative Depth Estimation Prior for Single Image Dehazing. 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW 2019), pp. 270-275, Shanghai, China, Jul. 8-12, 2019 (DOI: 10.1109/ICMEW.2019.00-75)

[20] Jinbao Wang, Ke Lyu, Jian Xue*, Pengcheng Gao, Yanfu Yan. A Markerless Body Motion Capture System for Character Animation Based on Multi-view Cameras. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019), pp. 8558-8562, Brighton, UK, May 12-17, 2019 (10.1109/ICASSP.2019.8683506)

[21] Jinbao Wang, Ke Lu, Jian Xue*, Ning He, Ling Shao. Single Image Dehazing Based on the Physical Model and MSRCR Algorithm. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 28, No. 9, pp. 2190-2199, Sep. 2018 (DOI: 10.1109/TCSVT.2017.2728822)

[22] Jiyang Dong, Ke Lu, Jian Xue*, Shuangfeng Dai, Rui Zhai, Weiguo Pan. Accelerated nonrigid image registration using improved Levenberg–Marquardt method. Information Sciences, Vol. 423, pp. 66-79, 2018 (DOI: 10.1016/j.ins.2017.09.059)

[23] Pengcheng Gao, Jian Xue*, Ke Lu, Yanfu Yan. A fast Cascade Shape Regression Method based on CNN-based Initialization. 24th International Conference on Pattern Recognition (ICPR 2018), pp. 3037-3042, Beijing, China, Aug. 20-24, 2018 (DOI: 10.1109/ICPR.2018.8546058)

[24] Zhi Li, Ke Lu, Jian Xue*. Joint Segmentation and Registration for 4D Lung CT Images based on Markov Random Field. International Conference on Internet Multimedia Computing and Service, ICIMCS 2018, Nanjing, China, Aug. 17-19, 2018 (DOI: 10.1145/3240876.3240892)

[25] Jiyang Dong, Jian Xue, Shuqiang Jiang, Ke Lu. A Novel Approach of Multiple Objects Segmentation based on Graph Cut. 2018 IEEE Conference on Multimedia Information Processing and Retrieval, MIPR 2018, pp. 328-333, Miami, USA, April 10-12, 2018 (DOI: 10.1109/MIPR.2018.00074)

[26] Mohammad Muntasir Rahman, Yanhao Tan, Jian Xue*, Ke Lu. RGB-D Object Recognition with Multimodal Deep Convolutional Neural Networks. 2017 IEEE International Conference on Multimedia and Expo, ICME 2017, pp. 991-996, Hong Kong, China, Jul. 10-14, 2017 (DOI: 10.1109/ICME.2017.8019538)

[27] Jian Xue, Xingxu Song, Qinghai Miao, Ke Lv, Ying Wang, Jun Xiao. 3D Graphical Visualization for Block Theory. 51st US Rock Mechanics / Geomechanics Symposium 2017, pp. 2487-2494, San Francisco, USA, Jun. 25-28, 2017

[28] Xiaolong Cheng, Ying Wang, Jian Xue*, Qinghai Miao. A New Software for Block Theory and its Applications in Rock Engineering. 51st US Rock Mechanics / Geomechanics Symposium 2017, pp. 2412-2418, San Francisco, USA, Jun. 25-28, 2017

[29] Jian Xue, Jun Yao, Ke Lu, Ling Shao, Mohammad Muntasir Rahman, Efficient Volume Rendering Methods for Out-of-Core Datasets by Semi-Adaptive Partitioning, Information Sciences, Vol. 370-371, pp. 463-475, 2016 (DOI: 10.1016/j.ins.2016.08.017)

[30] Jun Yao, Jian Xue, Ke Lv, Qinghai Miao, A Parallel Volume Rendering Method for Massive Data, 2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016, Seattle, WA, United States, Jul. 11-15, 2016 (DOI: 10.1109/ICMEW.2016.7574730)

[31] Weiguo Pan, Jian Xue, Ke Lu, Rui Zhai, Shuangfeng Dai, Hybrid Architecture for 3D Visualization of Ultrasonic Data, Information Sciences, Vol. 320, pp. 372-382, 2015 (DOI: 10.1016/j.ins.2015.03.026)

[32] Ke Lu, Ning He, Jian Xue, Jiyang Dong. Learning View-Model Joint Relevance for 3D Object Retrieval. IEEE Transactions on Image Processing, Vol. 24, No. 5, pp. 1449-1459, 2015 (DOI: 10.1109/TIP.2015.2395961)

[33] Jian Xue, Ke Lü. Volume Visualization for Out-of-core 3D Images based on Semi-adaptive Partitioning, 2015 IEEE International Conference on Image Processing (ICIP 2015), pp. 1503-1507, Quebec City, QC, Canada, Sep. 27-30, 2015 (10.1109/ICIP.2015.7351051)

[34] Ke Lu, Qian Wang, Jian Xue, Weiguo Pan. 3D Model Retrieval and Classification by Semi-Supervised Learning with Content-Based Similarity, Information Sciences. Vol. 281, pp.703-713, 2014 (DOI: 10.1016/j.ins.2014.03.079)

[35] Jianyong Li, Jian Xue, Jun Xiao, Ying Wang. Block theory on the complex combinations of free planes. Computers and Geotechnics, Vol.40, pp.127-134, 2012 (10.1016/j.compgeo.2011.10.006)

[36] J. Xue, Q. H. Miao, Y. X. Ben, J. Y. Li & Y. Wang. Modeling Method for Complex Key Block based on Nef Polyhedra. Advances in Discontinuous Numerical Methods and Applications in Geomechanics and Geoengineering, pages 227-232, 2012 (DOI: 10.1201/b11600-31)


发表著作
医学影像算法设计与平台构建 清华大学出版社 ISBN: 978-7-302-15838-7 20071101

科研活动

在研项目:

1. 非完全信息下多群体动态博弈决策理论(2018AAA0100804),国家重点研发计划科技创新2030-“新一代人工智能”重大项目“非完全信息下动态博弈决策的建模、分析与应用”课题

2. 面向胎儿心脏的心音-心动-超声多模态辅助诊断设备研制(62027827),国家自然科学基金重大科研仪器研制项目子项

3. 基于认知计算的遥感卫星下行数据即时服务的理论与方法研究(61731022),国家自然科学基金重点项目子项


已结题项目: 

1. 海量图像数据的感知驱动三维可视化关键技术研究(61671426),国家自然科学基金面上项目

2. 面向地标网络信息搜索与挖掘的数据处理和三维可视化技术(4131004),北京市自然科学基金重点项目子项

3. 四维医学图像中动态区域的分割技术研究(4182071),北京市自然基金面上项目

4. 基于数值流形的非连续工程计算和可视化理论及方法研究(60902098),国家自然科学基金青年科学基金项目

5. 多模态协同的语义理解及推理机制(2017YFB1002203),国家重点研发计划项目“大数据驱动的类人智能感知与情感交互关键技术”课题,主要参与者

6. 动态医学图像分割的关键技术研究(U1301251),国家自然科学基金-广东联合基金重点项目,主要参与者

7. 医学影像信息集成化计算和处理平台的研究与实现(60532050),国家自然科学基金重点项目,主要参与者

8. 4D超声影像处理与可视化,企业委托技术研发项目。