个人简介(简历) 王永芳,女,2007年7月于上海交通大学通信与信息处理专业获博士学位,同年到上海大学工作,长期从事多媒体智能处理和分析,视觉计算,机器学习,AI驱动的2D/3D/VR视频编码及传输等方面的研究,作为项目负责人主持的项目包括国家自然科学基金项目,上海市自然科学基金,上海市教育委员会科研创新项目等十余项。作为主研人员参与完成国家自然基金重点项目和上海市科委重点项目等多项。发表论文60余篇,其中被SCI/EI检索的论文有40余篇;申请发明专利24项,授权9项;提交MPEG国际标准化提案2项;出版著作1部;2011年获上海市科技进步二等奖。2013年获上海大学翔英教师奖,获得ICME2018最佳学生论文奖,获ChinaMM2008最佳论文海报奖。 科研方向 智能多媒体处理及分析;视觉感知模型;机器学习;AI驱动的2D/3D/VR编码等。 本科生教学 信号与系统A(1)、 信号与系统A(2)、 多媒体编码与通信A、 超高清与智能3D技术(高年级研讨课)、计算机视觉 每年招收毕业设计6名、优秀本科生5-10名 研究生培养 研究生课程:信号处理技术(2)、多媒体信息处理与编码 每年招收博士研究生、硕士研究生3-5名 承担或参与的科研项目 1. 国家自然基金,QoE驱动下的基于内容分析的3D视频感知编码研究,2017.1-2020.12,主持 2. 国家自然基金,面向高清/超高清的感知3D视频稀疏编码理论与技术研究, 2014.1-2016.12,主持 3. 国家自然基金,基于视觉感知的多视点视频编码,2010.1-2012.12,主持 4. 上海自然科学基金,基于人眼视觉的压缩感知3D视频编码研究,2013.6-2016.6,主持 5. 重点实验室开放课题,人眼感知融合深度的高清3D视频编码的研究,2015-2016,主持 6. 上海市教委科研创新项目,基于H.264可分级的多视点视频编码的研究,主持 7. 上海高校优秀青年教师科研专项基金项目,面向网络的多视点视频编解码究,主持 8. 上海大学创新基金项目, 基于H.264的多视点视频编码的研究,主持 9. 国家自然科学基金重点项目,自由视点多视视频编码及3D立体显示基础理论与关键技术,2009.1-2012.12 主研 10. 上海市科委重点项目,上海世博会中国馆3D自由视点电视应用系统,主研 11. 上海市科委重点项目,基于深度的双目视频编码与真实场景重现,2010.11-2013.6,主研 12. 上海市科委重点项目,3D内容制作专业技术服务平台建设,产学研,2012,2016,主研 学术论文及授权发明专利 1. Yongfang Wang, Yuan Shuai, Yun Zhu , Jian Zhang, Ping An, “Jointly Learning Perceptually Heterogeneous Features for Blind 3D Video Quality Assessment”, Neurocomputing, 332(2019)298-304. 2. Junjie Lian, yongfang wang and chuang wang,” Dual-Streams Global Guided Learning for High Dynamic Range Image Reconstruction,” IEEE International Conference on Visual Communications and Image Processing 2019 (VCIP2019) Sydney, Australia. Dec 1-4, 2019 (Oral). 3. Yumeng Xia, yongfang wang and Peng Ye,“Blind Panoramic Image Quality Assessment via the Asymmetric Mechanism of Human Brain,” IEEE International Conference on Visual Communications and Image Processing 2019 (VCIP2019) Sydney, Australia. Dec 1-4, 2019. 4. Yumeng Xia, Yongfang Wang, Ye Peng, Ping An “blind panoramic image quality assessment based on project-weighted local binary pattern,” The 16th International Forum of Digital TV and Wireless Multimedia Communication (16th IFTC),Sep.19-20.Shanghai, China,2019. 5. Yongfang Wang, Yuan Shuai, Yumeng Xia,” Blind 3D Image Quality Assessment Based on Multi-Scale Feature Learning,” The 16th International Forum of Digital TV and Wireless Multimedia Communication (16th IFTC),Sep.19-20.Shanghai, China,2019 6. 叶鹏 王永芳 夏雨蒙 安平, 一种融合深度基于灰度共生矩阵的感知模型,ChinaMM2018,September 14-16, Xi an.(ChinaMM Best Post paper) 7. Peng Ye, Yongfang Wang, Yumeng Xia,Ping An, Jian Zhang, “Enhanced Saliency Prediction Via Free Energy Principle” The 15th International Forum of Digital TV and Wireless Multimedia Communication (15th IFTC),Sep.20-21.Shanghai, China, 8. Yuan Shuai, Yongfang Wang, Ye Peng, Yumeng Xia “Accurate Image Super-Resolution Using Cascaded Multi-Column Convolutional Neural Networks,” 2018 IEEE International Conference on Multimedia and Expo (ICME 2018), pp.1-6, Jul 23-27 2018, SanDiego US.(Best student paper) 9. Yumeng Xia, Yongfang Wang, Ye Peng. “No-Reference Quality Assessment for Multiply-Distorted Images Based on Structural and Texture Features,” NCIG2018,May 11-13, Yangzhou, China 2018 10. Yongfang Wang, Kanghua Zhu, Jian Wu, Yun Zhu,Content Aware Video Quality Prediction Model for HEVC Encoded Bitstream, Multimedia Tools and Applications. vol.76, no.18, pp.19191-19209. 2017. 11. Yun Zhu, Yongfang Wang, Yuan Shuai,“blind video quality assessment based on spatio-temporal internal generative mechanism”,The International Conference on Image Processing 2017 (ICIP 2017), pp305-309., Beijing, China,Sep. 17-20, 2017. (Oral) 12. Jian Wu, Yongfang Wang, Yun Zhu,Yuan Shuai Adaptive Coding For Compressed Video Sensing, v 10667 LNCS, p 197-205, 2017, Image and Graphics - 9th International Conference, ICIG 2017, Shanghai, China, Sep.13-15 2017.(Oral) 13. Jian Wu, Yongfang Wang, Kanghua Zhu, Yun Zhu, Perceptual Sparse Representation for Compressed Sensing of Image, IEEE International Conference on Visual Communications and Image Processing 2016 (VCIP2016), Chengdu, China, Nov.27-30 2016.(Oral)(20170503316872) 14. Yongfang Wang, Kanghua Zhu, Pamela C. Cosman, “Perceptual Asymmetric Video Coding for 3D-HEVC,”The 2016 Pacific Rim Conference on Multimedia (PCM2016), Xi’an, China, Sep16-20 (Oral)(20165203184583) 15. Kanghua Zhu, Yongfang Wang, Jian Wu, Yun Zhu, Wei Zhang,“ Content Oriented Video Quality Prediction for HEVC Encoded Stream”, The 13th International Forum of Digital TV and Wireless Multimedia Communication (13th IFTC),Shanghai, China, pp.338-348,Nov.9-10.2016 (20171203487866) 16. Yubing Wang,Yongfang Wang Yawen Shi, ,“A fast CU size decision algorithm for 3D-HEVC,” 2016 International Seminar on Applied Physics, Optoelectronics and Photonics (APOP2016),Shanghai,May 28-29,2016. (20164302931465) 17. WANG Yong-fang, WANG Yu-bing, SHI Ya-wen,LUO Li-dong, ZHANG Zhao-yang,“Perceptually Adaptive Loop Filter Aimed at 3D-HEVC,” JOURNAL OF APPLIED SCIENCES, VOL.34, no.2 Mar.2016 18. Xiwu Shang, Yongfang Wang, Lidong Luo, Yifan Zuo, Zhaoyang Zhang “Fast mode decision for multiview video coding based on just noticeable distortion profile,” Circuits, Systems & Signal Processing Volume 34,no. 1 , pp. 301-320. 2015 19. Yawen Shi,Yongfang Wang,Yubing Wang,“A perceptual preprocess method for 3D-HEVC”,2015 International Conference on Optical Instrument and Technology(OIT‘2015),Beijing. May,17-20.2015.(EI: 20154101375907) 20. Lidong Luo, Yongfang Wang, Xiwu Shang, Ping Yang, Zhaoyang Zhang,”A low complexity adaptive loop filter algorithm for multi-view video coding,” Journal of Optoelectronics.Laser, pp. 336-342 ,vol.25, No.2,Feb.2014. 21. Yongfang Wang, Xiwu Shang, “JND assisted fast mode decision for multiview video,” in Processing International Conference on Audio, Language and Image 2014(ICALIP 2014), July 2014. 22. Yongfang Wang, W. Zhang, Z.Y.Zhang, and P. An “A low complexity deblocking filtering for multiview video coding,” IEEE Trans. on Consumer Electronics, vol.59. pp. 666-671, Aug. 2013. 23. Xiwu Shang, Yongfang Wang, Lidong Luo, Zhaoyang Zhang “Perceptual multiview video coding based on foveated just noticeable distortion profile in DCT domain,” The International Conference on Image Processing 2013 (ICIP 2013), pp.1914-1917, Melbourne, Australia, Sep. 15-18, 2013. 24. YongfangWang, Zhaoyang Zhang, Ping An, Wei Zhang, “Perceptually deblocking filtering algorithm in multiview video decoding,” Multimedia Information Networking and Security (MINES 2012), 2012 Fourth International Conference on: pp.311-314, 2012.11, Nanjing, China. 25. Yongfang Wang , Wei Zhang, Ping An , Zhaoyang Zhang, “ Deblocking filtering based on view correlation for multiview video decoding,” The 9th International Forum of Digital TV and Wireless Multimedia Communication (IFTC 2012),pp.258-263, 2012.11, Shanghai, China. 26. Yongfang Wang, Yundong Song, Xiwu Shang, Zhaoyang Zhang , “Compressive sensing image coding with perceptual weighting measuring matrix,” The 9th International Forum of Digital TV and Wireless Multimedia Communication(IFTC 2012), 264-270, 2012.11, Shanghai, China. 27. Zhang Wei, Wu Q.M. Jonathan; Wang Guanghui; You Xinge; Yongfang Wang, “Image matching using enclosed region detector,” Journal of Visual Communication and Image Representation, vol. 21, no. 4, pp. 271-282, 2010. 28. Ying Fu, Yongfang Wang,Zhaoyang Zhang, “An efficient deblocking filter algorithm in multi-view video coding,”2010 International Conference on Audio, Language and Image Processing(ICALIP 2010), pp.329-332, Shanghai, November 23-25, 2010, China. 29. Yongfang Wang, Songyu Yu Zhaoyang Zhang,“Unequal decoding power allocation for efficient video transmission” Journal of Shanghai University (English editior) ,2010,14(1):60-66. 30. Liu Zhi, Yan Hongbo, Shen Liquan, Yongfang Wang, Zhang Zhaoyang, “A motion attention model based rate control algorithm for H.264/AVC,” 8th IEEE/ACIS International Conference on Computer and Information Science(ICIS 2009),pp.568-573,June, 2009. 31. Yi liu, Yongfang Wang, Zhaoyang Zhang,“Color correction method based on histogram segmentation for multiview Video,” IET International Communication Conference on Wireless Mobile and Computing,(CCWMC 2009), pp.539-542 Shanghai, China Dec. 2009. 32. Yongfang Wang, Zhaoyang Zhang, “Optimized bit allocation scheme for joint source and channel coding,” in Processing International Conference on Audio, Language and Image 2008(ICALIP 2008), pp.1502 -1506, 7-9 July 2008. 33. Yongfang Wang, Zhaoyang Zhang, Zhi liu, “Performance analysis of region of interest video transmission system,” Proceedings of IET International Communication Conference on Wireless Mobile & Sensor Networks 2007(CCWMSN 2007), pp. 857-860, Shanghai, China Dec. 2007. 34. Yongfang Wang, Yu Songyu, Yang Xiaokang Daowen Zou, Zhijun Fang “H infinity -optimal model for VBR video traffic prediction,” IEEE Transactions on Consumer Electronics, vol.52, no.3, pp.1078-1083, Aug.2006. 35. Yongfang Wang, Yu Songyu, Yang Xiaokang “Unequal iterative decoding for power efficient video transmission,” 2006 IEEE International Conference on Multimedia and Expo (ICME 2006), pp.613-616, Jul 9-12 2006, Toronto Canada. 36. Yongfang Wang, Yu songyu, Yang Xiaokang, “Robust transmission of prioritized video over LSTC_OFDM_LDPC system,”25th PCS Proceedings: Picture Coding Symposium 2006(PCS2006),vol. 2006,Apr. 24-26 2006, Beijing, China 37. Yongfang Wang, Yu songyu, Yang xiaokang, “Unequal error protection for robust wireless video transmission using LDPC codes,”25th PCS Proceedings: Picture Coding Symposium 2006(PCS2006), vol. 2006, Apr. 24-26 2006, Beijing, China 38. Yongfang Wang,Yu songyu, Yang xiaokang, “Unequal decoding protection scheme for H.264 using turbo code,” Journal of Data Acquisition and Processing, vol.21, no.3, pp.350-353, September 2006 39. Yongfang Wang, Songyu Yu, Xiaokang Yang, “H infinity -optimal traffic predicting for VBR video,” First international conference on communications and network in China (CHINACOM 2006), Beijing, China, October 2006. 40. Yongfang Wang, Songyu Yu ,“Unequal error protection scheme for H.264 based on LDPC,” Systems Engineering and Electronics, vol.28, no.11, pp.1637-1640, Nov.2006. 41. KONG Wei-jian,WEI Jian-ming, WANG Yong-fang, ZHANG Hong-guang,“Diabetes diet nutrition optimization based on particle swarm optimization algorithm” Journal of Chongqing University English Edition, vol.16, No.4 December, 2017. 42. 王永芳,王宇兵 石亚文 罗丽冬 张兆杨, “面向3D-HEVC的感知自适应环路滤波,”应用科学学报。VOL.34, no.2 Mar.2016 43. 罗丽冬,王永芳,“基于时域相关性的自适应采样值补偿算法”,电视技术, 2015, 39(7):1-6 44. 刘颐,王永芳,张兆杨, 不同颜色空间的多视点视频颜色校正的性能分析, 电视技术, 33(11):18-21, 2009.6 45. 付瀛,王永芳,张兆杨, 相机标定中的角点检测和标定的接口程序设计, 电视技术, 35(5):92-95, 2011.3 46. 刘静,王永芳,武翠芳,张兆杨, 改进的JND模型及其在图像编码中的应用, 电视技术, 35(13):15-18, 2011.7 47. 武翠芳,王永芳,刘静, 张兆杨, 宋允东, 一种改进的基于BP的立体匹配算法, 电视技术, 35(20):28-31, 2011.10 48. 宋允东, 王永芳;商习武, 张兆杨“基于JND的压缩感知图像编码” 电视技术, 2012, 36(14), pp.15-18. 49. 孔维检,王永芳,童子磊,张红广. 糖尿病患个体化食谱营养优化建模与算法实现[J].上海大学学报(自然科学版), vol.24, No.4, pp. 583-591 .Aug.2018 50. 孔维检,魏建明,王永芳,张红广. 基于多属性决策的2型糖尿病运动项目优选算法[J].工业控制计算机,30(9):15-17.2017 51. 朱芸,王永芳,帅源,“基于IGM和深度感知的立体图像质量评价”,上海大学学报(自然科学版) 2019, 25(5): 692-700 52. 郑一欢、王永芳、叶鹏等,基于区域协方差矩阵融合深度的显著性检测方法[J]. 工业控制计算机(核心期刊, vol.9, pp.5-7.2018 53. 夏雨蒙,王永芳、叶鹏,联合结构与纹理特征的无参考图像质量评价方法,《郑州大学学报(理学版)》vol.51 No.3 Sep.2019 54. 叶鹏 王永芳 夏雨蒙 安平, 一种融合深度基于灰度共生矩阵的感知模型, 计算机科学, vol462,No.3, Mar. 2019 发明专利 [1] 王永芳,朱康华,吴健,基于恰可觉察失真模型的非对称感知视频编码系统及方法,申请号:ZL201610766137.7,授权日:2020.03.13 [2] 傅瀛,王永芳,刘静,武翠芳,多视点视频解码端去块滤波方法,中国/ 发明专利,获准专利号:ZL201110053291.7,授权日:2012.10.31. [3] 王永芳 刘静 武翠芳 宋允东 梁亮 张兆杨,“一种利用视觉特性的多视点视频编码系统” , 获准专利号:ZL201110394257.6,授权日:2013.11.20 [4] 王永芳 商习武 刘静 宋允东 张兆杨“利用视觉感知特性指导多视点视频编码量化过程的方法”, 获准专利号:ZL 201210402003.9. 授权日:2016.4.27. [5] 王永芳,商习武, 宋允东, 罗丽冬,张兆杨“基于视觉感知的多视点快速模式选择方法” ,获准专利号:ZL20131044517.5. 授权日:2017.2.1. [6] 王永芳,商习武, 宋允东, 罗丽冬, 张兆杨“一种基于压缩感知的图像自适应测量方法” ,获准专利号:ZL2013104261818.4, 授权日:2017.2.8. [7] 王永芳 王宇兵 石亚文 张兆扬, “面向3D-HEVC的编码单元尺寸快速选择算法,” 获准专利号:ZL201610068485.7,授权日:2018.8.17. [8] 王永芳 王宇兵 石亚文 罗丽冬 张兆扬,“基于恰可觉察失真模型的快速自适应环路滤波算法,” 获准专利号:ZL201510396817.X。授权日:2019.2.1. [9] 王永芳,朱康华,吴健,基于内容的HEVC码流质量预测模型,获准专利号:ZL201610928733.0。申请日:2016.11.1。授权日:2019.2.1. [10]王永芳,张兆杨 “一种不均等功耗有效控制的视频传输方法”,专利申请号:201010117567.9,公开号:101820542A. [11]王永芳,商习武, 宋允东, 罗丽冬, 张兆杨“一种快速自适应建立频域凹形恰可辨失真模型的方法” ,专利申请号:CN201310103059.9. [12]王永芳,杨萍,商习武, 宋允东, 罗丽冬, 张兆杨“一种改进的自适应权重视差匹配方法” ,专利申请号:CN201310144894.7 [13]王永芳,吴健,朱康华,朱芸,基于感知及随机置换的图像压缩感知方法,专利号:201610879363.6. 申请日:2016.10.9 [14]王永芳,吴健,朱芸,帅源,基于压缩感知的自适应3D视频压缩编解码方法,申请号:201710555070.7. 申请日:2017.7.10 [15]王永芳,朱芸,朱康华,基于内容的视频包优先级分配方法,申请号:201710503913.9. 申请号:2017.6.28 [16]王永芳,朱芸,帅源,基于双目时空内在推理机制的3D视频质量盲评估方法,申请号:201810172989.2. 申请号:2018.3.2 [17]王永芳,帅源,一种新的基于CNN的无参3D质量评估方法,申请号:201811596663.9. 申请日:2018.12.26 [18]王永芳,帅源,基于多列卷积神经网络的图像超分辨率重建方法,申请号:201811241002.4 申请日:2018.10.24 [19]王永芳,夏雨蒙,基于图像记忆性的图像质量无参评估方法,申请号:201811471755.4. 申请日:2018.12.4 [20]王永芳,夏雨蒙,一种新的全景图像盲质量评估方法,申请号:201910503670.8. 申请日:2019.6.12 [21]王永芳,叶鹏,基于方向选择性的增强显著性预测方法,申请号:201910503684.X. 申请日:2019.6.12 [22]王永芳,帅源,基于循环多列3D卷积神经网络的视频超分辨率方法,申请号: 201910849968.4 申请日:2019.9.10 [23]王永芳,王宇彤,基于非局部增强的生成对抗网络的3D图像显著性预测,申请号: 201910849986.2 申请日:2019.9.10 [24]王永芳,练俊杰,一种基于全局特征指导的高动态范围图像重建方法,申请号:201910998090.0 申请日:2019.10.21 |