个人简介

教学工作 本科：大学计算机基础，web应用基础； 研究生：知识挖掘与数据工程 教育背景 2001年毕业于北京交通大学电子与信息技术专业获工学学士学位，2008年毕业于北京交通大学信号与信息处理专业获博士学位。2008年7月留校工作。 09/2003–07/2008 Beijing Jiaotong University, Signal and Information Processing Doctor degree 09/2001–07/2003 Beijing Jiaotong University, Signal and Information Processing Master degree, (Top 1 in the major, advanced for doctor degree in Sept. 2003) 09/1997–07/2001 Beijing Jiaotong University, Electronic Engineering，Bachelor degree 工作经历 12/2015-today Beijing Jiaotong University, Beijing, China. Position: Professor, Research on 3D Video Processing and Compression 07/2011-11/2015 Beijing Jiaotong University, Beijing, China. Position: Associate Professor, Research on 3D Video Processing and Compression 01/2010-07/2010 Microsoft Research Asia, Beijing, China. Position: Visitor researcher, Research on Distributed Video Coding and Compressive Sensing 07/2008-07/2011 Beijing Jiaotong University, Beijing, China. Position: Lecturer, Research on Multiple Description Image/Video Coding

研究领域

电子与通信工程（专业学位） 软件工程（专业学位） 人工智能技术（专业学位） 数字媒体信息处理与智能分析 模式识别与智能系统 人工智能与智能融合 物联网与边缘计算

专利 [P1] 赵耀，白慧慧, Multiple description video codec based on adaptive temporal sub-sampling, 澳大利亚创新专利，授权号：2012100851. [P2] 赵耀、白慧慧, 基于多描述视频编码、解码方法、装置及系统, PCT/CN2012/084204. [P3] 赵耀、林春雨、白慧慧, 一种基于旋转的多描述视频编码解码方法、装置及系统, PCT/CN2012/084216. [P4] 赵耀，白慧慧，一种基于自适应时域亚采样的多描述视频编解码方法。国家发明专利，授权：200710119031.9 [P5] 白慧慧，赵耀， 一种立体编码、解码装置及系统, 国家发明专利，国家发明专利，授权：201210055895.X. [P6] 张萌萌，白慧慧，对H.264 视频数据进行分层信道编码的方法，国家发明专利，授权号：ZL201110062540.9 [P7] 赵耀，白慧慧，基于多描述视频编码、解码方法、装置及系统，国家发明专利，申请号：201210091619.9. [P8] 白慧慧，周文帅，刘美琴，林春雨，赵耀，一种基于人类视觉系统的多描述视频编码方法，国家发明专利，申请号：201310413810.5. [P9] 白慧慧，高静，刘美琴，林春雨，赵耀，一种基于压缩感知的自适应深度图像编码方法，国家发明专利，申请号：201310414049.7. [P10] 白慧慧，陶文君，刘美琴，林春雨，赵耀，一种基于SIFT特征的二阶段三维图像压缩编码方法，申请号：201310500171.6. [P11] 林春雨，赵耀，白慧慧，一种基于旋转的多描述视频编解码方法、装置及系统，国家发明专利，申请号：201110444699.7. [P12] 赵耀，黄晗，林春雨，白慧慧， 一种HEVC帧内编码的快速模式决策算法及其应用，国家发明专利，申请号：201310353998.9 [P13] 张萌萌，白慧慧，基于HEVC 标准的自适应空间可伸缩编码，国家发明专利，申请号： 201210239938.X [P14] 张萌萌，白慧慧，曲建峰，用于HEVC 的基于方向矢量的帧内预测模式决策，国家发明专利，申请号： 201210138806.8 [P15] 张萌萌，白慧慧，赵川，用于HEVC 的自适应快速帧内预测模式决策，国家发明专利，申请号： 201210138816.1 [P16] 张萌萌，白慧慧，基于HEVC 标准率失真优化的质量可伸缩编码算法，国家发明专利，申请号： 201210239936.0 科研项目 国家自然科学基金“面上”：云环境下结合视觉特征的图像视频集编码与传输 国家自然科学基金“面上”：云计算环境下基于相关性优化的三维视频编码，主持 国家自然科学基金"青年基金"：异构网络下基于相关性优化准则的多描述视频编码的研究，主持 基本科研业务费：复合屏幕内容的高分辨率视频编码研究，主持 北京市自然基金“面上”：基于相关性优化准则的多描述视频编码及网络适应性研究，主持 博士点基金：基于相关性优化准则的多描述视频编码，主持 校科技基金：复杂网络环境下多描述图像视频编码的研究，主持 科技部“973”：跨媒体数据统一表示和建模机制，参加 国际科技合作计划：鲁棒的可伸缩视频编码及其在异构网络中的传输，参加国家自然科学基金“面上”：国家自然科学基金“面上”

近期论文

查看导师新发文章 （温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

论文/期刊 Selected Journal papers [1] Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao, Multiple Description Convolutional Neural Networks for Image Compression, IEEE Transactions on Circuits and Systems for Video Technology, DOI: 10.1109/tcsvt.2018.2867067, online 2018. [2] Lijun Zhao, Huihui Bai, Jie Liang, Bing Zeng, Anhong Wang, Yao Zhao: Simultaneous color-depth super-resolution with conditional generative adversarial networks. Pattern Recognition 88: 356-369 (2019) [3] Lijun Zhao, Huihui Bai, Jie Liang, Anhong Wang, Bing Zeng, Yao Zhao: Local activity-driven structural-preserving filtering for noise removal and image smoothing. Signal Processing 157: 62-72 (2019) [4] Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao:Iterative range-domain weighted filter for structural preserving image smoothing and de-noising. Multimedia Tools Appl. 78(1): 47-74 (2019) [5] Huihui Bai, Weisi Lin, Mengmeng Zhang, Anhong Wang, Yao Zhao, Multiple Description Video Coding Based on Human Visual System Characteristics, IEEE Transactions on Circuits and Systems for Video Technology,24(8):1390-1394 2014. [6] Feng Li, Huihui Bai, Lijun Zhao, Yao Zhao: Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution. IEEE Access 6: 33421-33431 (2018) [7] Ting Zhang, Huihui Bai, Mengmeng Zhang, Yao Zhao: Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks. IEICE Transactions 101-D(10): 2543-2546 (2018) [8]Huihui Bai, Ce Zhu, Yao Zhao: Optimized Multiple Description Lattice Vector Quantization for Wavelet Image Coding. IEEE Transactions on Circuits and Systems for Video Technology, 17(7): 912-917, 2007. [9]Huihui Bai, Mengmeng Zhang, Anhong Wang, Yao Zhao, Multiple Description Video Coding Using Correlation Optimized Temporal Sampling, SCIENCE CHINA Information Sciences, DOI: 10.1007/s11432-013-4861-2, 2014. [10]Huihui Bai, Mengmeng Zhang, Anhong Wang, Meiqin Liu, Yao Zhao, Multiple Description Video Coding Using Inter- and Intra-Description Correlation at Macro Block Level, IEICE Trans. Information and Systems, Vol.E97-D,No.2, Feb. 2014, pp.384-487. [11]Huihui Bai，Yao Zhao and Mengmeng Zhang, Standard-Compliant Multiple Description Video Coding over Packet Loss Network, EURASIP Journal on Advances in Signal Processing，vol.2010, Article ID 987164, 9 pages, 2010. [12]Huihui Bai, Yao Zhao, Ce Zhu, Anhong Wang, Multiple Description Video Coding Using Joint Frame Duplication/Interpolation，Computing and Informatics, vol. 29, no.6, pp.1267-1282, 2010. Selected Conference Papers [1] Lijun Zhao, Jie Liang, Huihui Bai, Anhong Wang, Yao Zhao: Convolutional neural network-based depth image artifact removal. ICIP 2017: 2438-2442 [2] Lijun Zhao, Huihui Bai, Jie Liang, Anhong Wang, Yao Zhao: Single depth image super-resolution with multiple residual dictionary learning and refinement. ICME 2017: 739-744 [3] Feng Li, Huihui Bai, Yao Zhao: Visual attention guided eye movements for 360 degree images. APSIPA 2017: 506-511 [4] Hai Ren, Huihui Bai, Chunyu Lin, Mengmeng Zhang, Yao Zhao: Just Noticeable Difference Based Fast Coding Unit Partition in 3D-HEVC Intra Coding. DCC 2016: 629 [5] Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao: Joint iterative guidance filtering for compressed depth images. VCIP 2016: 1-4 [6] Huihui Bai, Mengmeng Zhang, Meiqin Liu, Anhong Wang, Yao Zhao: Multiple Description Video Coding Using Macro Block Level Correlation of Inter-/Intra-Descriptions. DCC 2012: 389 [7] Huihui Bai, Mengmeng Zhang, Anhong Wang, Yao Zhao: Stereo video coding using distributed compressive sensing with joint dictionary. ICIP 2012: 889-892 [8] Huihui Bai, Anhong Wang, Mengmeng Zhang, Xiaoming Guo: Joint Temporal-Spatial Error Concealment for Multiple Description Video Coding. CASoN 2010: 638-641 (Best Paper Award) [9] Huihui Bai, Yao Zhao, Ce Zhu: Priority Encoding Transmission Based Multiple Description Video Coding over Packet Loss Network. DCC 2008: 504 [10] Huihui Bai, Yao Zhao, Ce Zhu: Multiple Description Video Coding using Adaptive Temporal Sub-Sampling. ICME 2007: 1331-1334 [11] Huihui Bai, Yao Zhao, Ce Zhu: Multiple Description Shifted Lattice Vector Quantization for Progressive Wavelet Image Coding. ICIP 2006: 797-800 [12] Huihui Bai, Yao Zhao, Ce Zhu: Optimized multiple description image coding using lattice vector quantization. ISCAS (4) 2005: 4038-4041 专著/译著 白慧慧，王安红,赵耀,Pan,Abraham.Distributed Multiple Description Coding: Principles, Algorithms and Systems[M]。国外:Springer，2011-11 白慧慧，张萌萌,赵耀.面向异构网络的视频编码技术[M]。国内:中国水利水电出版社，2011-03 Book [1] Huihui Bai, Anhong Wang, Yao Zhao, Jeng-Shyang Pan and Ajith Abraham, Distributed Multiple Description Coding: Principles, Algorithm and Systems, Springer, ISBN: 978-1-4471-2247-0, 2011.