葛永新, 教授/博导
重庆市学术技术带头人
大数据智能研究所,副所长
主要研究方向为计算机视觉、机器学习、大数据智能等
Email: yongxinge@cqu.edu.cn
葛永新是重庆大学大数据与软件学院教授、博士生导师,重庆市学术技术带头人,大数据智能研究所副所长,中国仿真学会视觉与计算专委会副秘书长,CCF高级会员。主要研究方向为计算机视觉、机器学习、大数据智能等,主持国家自然科学基金2项,重庆市技术创新与应用发展专项重点项目课题1项,教育部博士点新教师基金1 项,重庆市自然科学基金2 项,中央高校基金自科专项和医工融合重点项目各1项,以第一或通讯作者在IEEE TIP、IEEE TCSVT、IEEE TITS、ACM MM、计算机学报等高水平期刊和会议上发表论文30余篇,授权发明专利10余项,获重庆市科技进步一等奖(2021),汽车工程学会科技进步二等奖(2023)和中国兵器装备集团科技进步一等奖(2023),多次担任国际会议IJCAI和ICME的领域主席(Area Chair).
教育工作经历
1999.9—2003.6,重庆大学数学与统计学院,获理学学士学位,
2003.9—2006.6,重庆大学数学与统计学院,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
2014.9-2022.8,重庆大学大数据与软件学院,副教授
2022.9 至今,重庆大学大数据与软件学院,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(62176031), 负责人 ,2022.1-2025.12
[2] 重庆市技术创新与应用发展专项重点项目:道路路面病害智能识别技术研究与应用(CSTB2022TIAD-KPX0100),课题负责人,2022.12-2025.12
[3] 中央高校基金医工融合重点项目:面向脑灌注异常分析的脑血管影像亚结构评估方法研究(2023CDJYGRH-ZD05),联合负责人,2023.10-2026.9
[4] 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
[5] 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
[6] 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 (61402062),负责人, 2015.1-2017.12
[7] 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
学术兼职
1. 中国仿真学会视觉计算与仿真专委会副秘书长
2. CCF 高级会员
3. Area Chair/ Session Chair: IJCAI, ICME
4. 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)
5. 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)
6. 中国生物特征识别大会程序委员会成员(2016-)
近年来代表性科研论文(“*”为通讯作者)
[1] Senlong Huang, Yongxin Ge*, Dongfang Liu, Mingjian Hong, Junhan Zhao, and Alexander C. Loui. Rethinking Copy-Paste for Consistency Learning in Medical Image Segmentation. IEEE Transactions on Image Processing (TIP), 2025,34:1060-1074.
[2] Zheyi Ji, Yongxin Ge*, Chijioke Chukwudi, et al.. Counterfactual Bidirectional Co-Attention Transformer for Integrative Histology-Genomic Cancer Risk. IEEE Journal of Biomedical and Health Informatics (JBHI), 2025. DOI: 10.1109/JBHI.2025.3548048
[3] Jiake Leng, Yiyan Zhang, Xiang Liu, Yiming Cui, Junhan Zhao*, and Yongxin Ge*. Error-Robust and Label-Efficient Deep Learning for Understanding Tumor Microenvironment from Spatial Transcriptomics. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024, 34(8):6785-6796.
[4] Yanwen Wu, Mingjian Hong, Ao Li, Sheng Huang, Huijun Liu, Yongxin Ge*. Self-Supervised Adversarial Learning for Domain Adaptation of Pavement Distress Classification. IEEE Transaction on Intelligent Transportation Systems (TITS), 2024, 25(2):1966-1977.
[5] Long Deng, Ao Li, Bingxin Zhou, and Yongxin Ge*. Two-Stream Temporal Feature Aggregation Based on Clustering for Few-Shot Action Recognition. IEEE Signal Processing Letters, 2024, 31:2435-2439.
[6] Boyu Hua, Junyin Zhang, Ziqiang Li, Yongxin Ge*. Cross-Modality Channel Mixup and Modality Decorrelation for RGB-Infrared Person Re-identification. IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 2023, 5(4):512-523.
[7] Huijun Liu, Chunhua Yang, Ao Li*, Sheng Huang, Xin Feng, Zhimin Ruan, and Yongxin Ge*. Deep Domain Adaptation for Pavement Crack Detection. IEEE Transaction on Intelligent Transportation Systems (TITS), 2022, 24(2):1669-1681
[8] 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.
[9] Yongxin Ge*, Xiaolei Qin, Dan Yang, Martin Jagersand. Deep Snippet Selective Network for Weakly Supervised Temporal Action Localization. Pattern Recognition. 2021, 110(2): 107686.
[10] 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.
[11] 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.
[12] Ao Li, Huijun Liu, Jinrong Sheng, Zhongming Chen, and Yongxin Ge*. Efficient Dual-Confounding Eliminating for Weakly-supervised Temporal Action Localization. ACM Multimedia (ACM MM), 2024: 8179 - 8188.
[13] Ziqiang Li, Yongxin Ge*, Jiaruo Yu, and Zhongming Chen. Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization. ACM Multimedia (ACM MM), 2022: 5371 - 5379.
[14] 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 (ACM MM), 2021: 4268 - 4276..
[15] 李傲,葛永新*,刘慧君,杨春华,周修庄. 内容感知的可解释性路面病害检测模型. 计算机研究与发展,2024,61(3):701-715.
[16] 蒲瞻星, 葛永新*. 基于多特征融合的小样本视频行为识别算法. 计算机学报, 2023,46(3):594-608.
Last Update: 04-12-2025, Copyright 2011~2023, Yongxin Ge All Rights Reserved