联系方式

E-mail:jing@whu.edu.cn

办公电话:

办公地点:本科生院大楼南7楼

肖晶

武汉大学计算机学院 人工智能系 国家多媒体软件工程技术研究中心 副教授 (硕导)

 肖晶

  • 姓名:肖晶

  • 主页:

  • 性别:

  • 职称:副教授 (硕导)

  • 学历学位:博士

  • 电话:

  • 办公地点:本科生院大楼南7楼

  • E-mail:jing ▇ whu.edu.cn 请手工替换符号

  • 领域:多媒体技术与大数据分析,多媒体信号处理,计算机视觉,模式识别,人工智能

  • 招生信息:2018年度招收硕士2名,招收方向:计算机科学与技术(学硕),软件工程(学硕),通信与信息工程(学硕)。 招收博士0名,招收方向:。

研究方向

主要研究方向包括计算机视觉,人工智能,图像/视频编码与传输、多媒体大数据处理与分析等


教育背景

2008/12-2013/05,荷兰屯特大学,Computer Vision and Photogrammetry

2006/09-2008/06,武汉大学,地理信息系统,硕士

2002/09-2006/06,武汉大学,地理信息系统,学士


工作经验

2017/01-至今,武汉大学计算机学院,副教授

2019/04-2020/05,日本国立信息学研究所,访问学者

2016/09-2016/12,武汉大学计算机学院,讲师

2013/08-2016/08,武汉大学计算机学院,博士后


教授课程

并行计算,专业选修,研究生课程

通信系统与原理,专业必修,研究生课程

计算机组成原理,专业必修,本科生课程

计算机图形学,专业必修,本科生课程

数字媒介传播,专业选修,本科生课程


发表论文

TIP, TMM, TCSVT, JSTSP, CVPR, ECCV, AAAI, ACM MM等国际期刊和会议上共发表学术论文70余篇

[1] Liang Liao, Jing Xiao*, Zheng Wang, Chia-Wen Lin, and Shin'ichi Satoh. “Image Inpainting Guided by Coherence Priors of Semantics and Textures”. The 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021.


[2] Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, and Shin'ichi Satoh. “Capturing Small, Fast-Moving Objects: Frame Interpolation via Recurrent Motion Enhancement”. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2021.

[3] Liang Liao, Jing Xiao*, Zheng Wang, Chia-Wen Lin, and Shin'ichi Satoh. “Uncertainty-Aware Semantic Guidance and Estimation for Image Inpainting”. IEEE Journal Selected Topics in Signal Processing (JSTSP). 2021, 15(2): 310-323.

[4] Liang Liao, Jing Xiao*, Zheng Wang, Chia-Wen Lin, and Shin'ichi Satoh. “Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes”. The 2020 European Conference on Computer Vision (ECCV), 2020, pp. 683-700.

[5] Fan Yang, Zheng Wang, Jing Xiao, and Shin’ichi Satoh. “Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval”. 2020 AAAI Conference on Artificial Intelligence (AAAI), 2020, pp. 12589-12596.


[6] Jing Xiao, Liang Liao, Qiegen Liu, Ruimin Hu, “CISI-net: Explicit latent content inference and imitated style rendering for image inpainting,” 2019 AAAI Conference on Artificial Intelligence (AAAI), 2019, pp. 354-362.

[7] Mengshun Hu, Liang Liao, Jing Xiao*, Lin Gu, Shin'ichi Satoh, “Motion Feedback Design for Video Frame Interpolation,” The 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 4347-4351

[8] Dongmei Peng, Jing Xiao, Rong Zhu, and Ge Gao, “Ts-Fen: Probing Feature Selection Strategy for Face Anti-Spoofing,” The 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 2942-2946.

[9] Liang Liao, Jing Xiao*, Yating Li, Mi Wang, and Ruimin Hu. “Learned Representation of Satellite Image Series for Data Compression”. Remote Sensing, 2020, 12(3): 497.

[10] Xu Wang, Ruimin Hu, Zhongyuan Wang, Jing Xiao, and Shin'ichi Satoh. “Long-Term Background Redundancy Reduction for Earth Observatory Video Coding”. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2020, 30(11): 4309-4320.

[11]    Sanqian Li, Binjie Qin, Jing Xiao, Qiegen Liu, Yuhao Wang, and Dong Liang. “Multi-Channel and Multi-Model-Based Autoencoding Prior for Grayscale Image Restoration”. IEEE Transactions on Image Processing (TIP). 2020, 29: 142-156.

[12] Qingnan Li, Ruimin Hu, Jing Xiao, Zhongyuan Wang, and Yu Chen. “Learning latent geometric consistency for 6D object pose estimation in heavily cluttered scenes”. Journal of Visual Communication and Image Representation (JVCIR), 2020, 70: 102790.

[13]  Yu Chen, Ruimin Hu, Jing Xiao, and Zhongyuan Wang, “Multisource surveillance video coding with synthetic reference frame”. Journal of Visual Communication and Image Representation (JVCIR), 2019, 65.

[14] Jing Xiao, Rong Zhu, Ruimin Hu, Mi Wang, Ying Zhu, Dan Chen, and Deren Li. “Towards Real-Time Service from Remote Sensing: Compression of Earth Observatory Video Data via Long-Term Background Referencing”. Remote Sensing, 2018, 10(6): 876.

[15] Jing Xiao, Ruimin Hu, Liang Liao, Yu Chen, Zhongyuan Wang and Zixiang Xiong, “Knowledge-based Coding of Objects for Multi-source Surveillance Video Data,” IEEE Transactions on Multimedia (TMM), vol. 18, no. 9, pp. 1691-1706, Sept. 2016.

[16] Jing Xiao, Liang Liao, Jinhui Hu, Yu Chen, and Ruimin Hu, “Exploiting global redundancy in big surveillance video data for efficient coding,” Cluster Computing, vol. 18, no. 2, pp. 531-540, Feb. 2015.

[17] Markus Gerke, Jing Xiao, “Fusion of airborne laserscanning point clouds and images for supervised and unsupervised scene classification”. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87: 78-92.

[18] Jing Xiao, Markus Gerke, George Vosselman, “Building extraction from oblique airborne imagery based on robust façade detection”. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 68: 56-68.

[19] Liang Liao, Ruimin Hu, Jing Xiao, Zhongyuan Wang, “Edge-Aware Context Encoder for Image Inpainting,” The 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 3156-3160.

[20] Jing Xiao, Yu Chen, Liang Liao, Jinhui Hu, Ruimin Hu, “Global Coding of Multi-source Surveillance Video Data,” Data Compression Conference (DCC), 2015, pp. 33-42


科研课题

近年来,主持完成图像/视频表达与压缩相关的国家自然科学基金1 项、省厅级基金2 项、国家博士后基金1 项、武汉大学校级及国家重点实验室开放基金4 项,并作为项目骨干多次参与国家重点研发计划项目、自然科学基金重大项目集成项目、欧盟第七框架合作项目和公安部重点项目,其中多个课题围绕卫星在轨处理、视频压缩、视频信息处理技术及其应用的主题

主要项目如下:

[1] 国家自然科学基金青年项目“欠覆盖环境下城市多源监控视频大数据高效编码方法研究”,61502348,主持

[2] 中国博士后科学基金“基于三维可变部件模型的车辆品牌与型号识别”, 2014M562058, 主持

[3] 留学回国人员科研启动基金“互遮挡情况下监控视频车辆跟踪技术研究”,[2014]1685,主持

[4] 中央高校自主科研青年教师资助项目“基于CAD模型的车辆跟踪和车型识别技术研究”,2042014kf0025,主持

[5] 国家自然科学基金项目,“大尺度时空视频数据表达及巡航无人机视频高效编码技术”,61671336,参与

[6] 欧盟第七框架项目,“Quality-of-Experience Improvement for Mobile Multimedia across Heterogeneous Wireless Networks”,PIRSES-GA-2013-612652,参与

[7] 湖北省技术创新专项重大项目 “智能可信辨识技术及在城市安全领域的应用”,2018AAA062,参与

[8] 湖北省自然科学基金面上项目“面向大范围动态场景的嫌疑目标轨迹排查关键技术研究”,2014CFB712,参与

[9] 公安部技术研究计划 “嫌疑目标自动排查关键技术研究”,2014JSYJA016,参与


研究团队

研究团队包含博士4人,硕士10人,在多媒体视频监控领域做了大量相关研究工作,包括监控视频背景建模,前景对象编码,多视点安防监控视频编码,无人机视频编码,卫星视频编码等方面的研究,并已取得了大量研究成果,在视频编解码技术领域打下了扎实的理论基础和研究基础,同时本团队在目标跟踪,图像修复,深度学习等领域也有一定研究基础


知识产权

申请发明专利25 项,其中已授权10 项。


学术服务

组织并参加 IEEE MIPR 2021 Tutorial "Human-centric media processing and analysis"

组织并承办Asia Multimedia 2021 Workshop “Scene Understanding under Bad Weather Conditions”

担任IEEE TIP, IEEE TMM, IEEE TCSVT, CVPR, ICCV, ECCV, AAAI, ICMR, ICME等国际权威期刊/会议的审稿人.


成果展示


其他