葛永新 男，1981年生，博士，重庆大学大数据与软件学院副教授，硕士研究生导师。
CPS教育部重点实验室大数据智能研究所，副所长。
主要研究方向:计算机视觉、机器学习、大数据智能等。
Email: yongxinge@cqu.edu.cn
教育工作经历
1999.9—2003.6，重庆大学数理学院(现为数学与统计学院)，获理学学士学位，
2003.9—2006.6，重庆大学数理学院(现为数学与统计学院)，获理学硕士学位，
2007.9—2011.6，重庆大学计算机学院，获工学博士学位，
2008.9—2009.9，加拿大阿尔伯塔大学(University of Alberta)联合培养，
2011.8-2014.8，重庆大学软件学院(现为大数据与软件学院)，讲师
2014.9 至今，重庆大学大数据与软件学院，副教授
主要科研项目
[1] 国家自然科学基金面上项目：复杂场景下视频行为特征学习方法研究（**） 负责人 2022.1-2025.12
[2] 中央高校基金自科专项“前沿科学与颠覆性卡脖子技术研究子项”：时空协同的非对齐视频行为识别方法研究（2021CDJQY-018） 负责人 2021.1-2022.12
[3] 重庆市自然科学基金（基础研究与前沿探索项目）：面向视频行为识别的多模态深度度量学习研究（cstc2018jcyjAX0410）负责人 2018.7—2021.6
[4] 国家自然科学基金青年基金：无控制条件下上下文感知和遮挡鲁棒的人脸对齐研究 （**） 负责人 2015.1-2017.12
[5] 重庆市前沿与应用基础（一般）：无控制条件下利用上下文关系的人脸对齐研究 (cstc2015jcyjA40037) 负责人 2015.7-2018.6
[6] 博士点新教师基金：基于多特征和多标记流形学习的人体年龄估计方法研究（20**3）负责人 2014.1-2016.12
[7] 中央高校基金：视频监控系统中基于人体特征的年龄估计方法研究(CDJZR12 09 00 02) 负责人
学术兼职
[1]Area Chair, IEEE International Conference on Multimedia and Expo (ICME), 2020
[2]Session Co-Chair at the 1st International Workshop on Human Identification in Multimedia, in conjunction with IEEE International Conference on Multimedia and Expo (ICME), 2014
[3]Co-organizer, Special Session on “Video Analysis and Understanding”, SPIE International Conference on Visual Communication and Image Processing (VCIP), 2015. (Co-organized with Associate Prof. Xin Feng)
[4]Co-organizer, Workshop on “Large-Scale Soft Biometircs”, IEEE Winter Conference on Applications of Computer Vision (WACV), 2017. (Co-organized with Associate Prof. Xin Feng, Associate Prof.Xiuzhuang Zhou,and Assistant Prof. Li Geng)
[5] 中国生物特征识别大会程序委员会委员（2016-）


近年来部分科研论文 （“*”为通讯作者）
期刊论文
[1] Jiahong Xie, Yongxin Ge*, Junyin Zhang, Sheng Huang, Feiyu Chen, and Hongxin Wang. Low-resolution Assisted Three-stream Network for Person Re-identification. The Visual Computer, 2021. DOI：10.1007/s00371-021-02127-0
[2] Jiaruo Yu, Yongxin Ge*, Xiaolei Qin, Ziqiang Li, Sheng Huang, and Feiyu Chen. Deep Feature Enhancing and Selecting Network for Weakly Supervised Temporal Action Localization. Journal of Visual Communication and Image Representation, 2021, 80(10): 103276.
[3]Yongxin Ge*, Junyin Zhang, Xinyu Ren, Chenqiu Zhao, Juan Yang, and Anup Basu. Deep Variation Transformation Network for Foreground Detection. IEEE Transactions on Circuits and Systems for Video Technology (CSVT), 2021, 31(9): 3544-3558.
[4] Yongxin Ge*, Xiaolei Qin, Dan Yang, Martin Jagersand. Deep Snippet Selective Network for Weakly Supervised Temporal Action Localization. Pattern Recognition. 2021, 110(2): 107686.
[5] Xiaolei Qin, Yongxin Ge*, Hui Yu, Feiyu Chen, Dan Yang. Spatial Enhancement and Temporal Constraint for Weakly Supervised Action Localization. IEEE Signal Processing Letters, 2020, 27:1520-1524.
[6] Yongxin Ge*, Junyin Zhang, Chen Peng, Min Chen, Jiahong Xie, and Dan Yang. Deep Shape Constrained Network for Robust Face Alignment. Pattern Recognition Letters, 2020, 138:587-593.
[7] Xiaolei Qin, Yongxin Ge*, Jinyuan Feng, Dan Yang, Feiyu Chen, Sheng Huang, and Ling Xu. DTMMN: Deep Transfer Multi-Metric Network for RGB-D Action Recognition. Neurocomputing, 2020, 406:127-134.
[8] Chenqiu Zhao, Aneeshan Sain, Ying Qu, Yongxin Ge*, Haibo Hu*. Background Subtraction based on Integration of Alternative Cues in Freely Moving Camera. IEEE Transactions on Circuits and Systems for Video Technology (CSVT), 2019, 29(7): 1933-1945.
[9] Yongxin Ge*, Cheng Peng, Mingjian Hong, Sheng Huang, and Dan Yang. Joint local regressors learning for face alignment. Neurocomputing, 2016, 208:262-268.
[10] Venice Erin Liong, Jiwen Lu, and Yongxin Ge*. Regularized Local Metric Learning for Person Re-Identification. Pattern Recognition Letters, 2015, 68: 288-296.
[11] Yongxin Ge*, Dan Yang, Jiwen Lu, Bo Li and Xiaohong Zhang. Active Appearance Models Using Statistical Characteristics of Gabor Based Texture Representation. Journal of Visual Communication and Image Representation, 2013, 24(5): 627-634.
会议论文
[12]Junyin Zhang, Yongxin Ge*, Xinqian Gu, Boyu Hua, and Tao Xiang.Self-Supervised Pre-training on the Target Domain for Cross-Domain Person Re-identification. ACM Multimedia (MM), 2021.
[13] Jiaruo Yu, Yongxin Ge*, Ziqiang Li, Zhongming Chen, and Xiaolei Qin. Context Driven Network with Bayes for Weakly Supervised Temporal Action Localization. IEEE International Conference on Multimedia and Expo (ICME), 2021.
[14]Ziqiang Li, Yongxin Ge*, Jinyuan Feng, Xiaolei Qin, Jiaruo Yu, Hui Yu. Deep Selective Feature Learning for Action Recognition, IEEE International Conference on Multimedia and Expo (ICME), 2020. (Oral)
[15] Xiaolei Qin, Yongxin Ge, Liuwei Zhan, Guangrui Li, Sheng Huang, Hongxing Wang and Feiyu Chen. Joint Deep Learning for RGB-D Action Recognition. VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing, Taichung, Taiwan, July 2, 2018. (Oral)
[16]Yongxin Ge*, Xinqian Gu, Min Chen, Hongxin Wang, and Dan Yang. Deep multi-metric learning for person re-identification. IEEE International Conference on Multimedia and Expo (ICME), 2018. (Oral)
[17] Cheng Peng, Yongxin Ge*, Mingjian Hong, Sheng Huang, and Dan Yang. Robust face alignment with cascaded coarse-to-fine auto-encoder. IEEE International Conference on Image Processing (ICIP), Beijing, China, Sep. 18-20, 2017. (Oral)
[18] Yongxin Ge*, Min Chen, Martin Jagersand and Dan Yang. Active appearance model search using partial least squares regression. The IEEE International Conference on Visual Communications and Image Processing (VCIP), 13 - 16 December 2015, Singapore. (Oral)
[19] Venice Erin Liong, Yongxin Ge*, and Jiwen Lu. Discriminative Regularized Metric Learning for Person Re-Identification. The 8^th IAPR International Conference on Biometrics (ICB), May 19-22, 2015 Phuket, Thailand, 52-57.
[20] Venice Erin Liong, Jiwen Lu, and Yongxin Ge*. Regularized Bayesian metric learning for person re-identification. ECCV 2014 Workshops, September 6 - 12, 2014, Zurich, Switzerland, 209-224.
[21] Yongxin Ge*, Jiwen Lu, Xin Feng and Dan Yang. Body-Based Human Age Estimation at a Distance. IEEE International Conference on Multimedia and Expo (ICME), San Jose, California, USA, July 15-19, 2013, 1-4. (short paper)
[22] Yongxin Ge*, Jiwen Lu, Fan Wu and Dan Yang. Age Estimation from Human Body Images. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Vancouver, Canada, May 26 - 31, 2013, 2337-2341.
授权发明专利
[1] 葛永新,陈乐扬,杨丹,张小洪,徐玲,杨梦宁,洪明坚,王洪星,黄晟,陈飞宇，基于整合深度典型时间规整及相关修正的行为识别方法，ZL6.1，2020，中国。
[2] 葛永新,潘志辉, 徐玲, 洪明坚,杨梦宁,张小洪,杨丹，王洪星，黄晟，基于阈值操作的代价敏感神经网络的警告分类方法，ZL2.3，2019，中国。
[3] 葛永新,杨梦宁,马鹏,张小洪,洪明坚,徐玲,胡海波，一种人脸识别方法，ZL4.5，2016，中国。
[4] 葛永新,杨丹,杨梦宁,张小洪,洪明坚,徐玲,胡海波，基于角点对CS距离匹配的图像配准方法，ZL3.0，2014，中国。




Last Update: 09-23-2021, Copyright 2011~2021, Yongxin Ge All Rights Reserved




上一条： 付春雷
下一条：周魏