刘渭滨
博士、教授、博士生导师
博士、教授、博士生导师
办公电话: | 电子邮件: wbliu@bjtu.edu.cn |
通讯地址:北京交通大学信息科学研究所9教北304A | 邮编:100044 |
·1998.4~2001.10,北京交通大学信息科学研究所,博士研究生
·1995.9~1998.3,湖南大学电气与信息工程学院与中国科学院电工所联合培养,硕士研究生
·1991.9~1995.7,湖南大学电气与信息工程学院,本科生(免试保送硕士研究生)
·2011.12~至今, 北京交通大学信息科学研究所,教授、博导
·2006.6~2011.11,北京交通大学信息科学研究所,副教授
·2005.6~2006.5,北京交通大学信息科学研究所,讲师
·2001.11~2005.5,富士通研究开发中心信息技术研究部,研究员
海外工作经历
·2009.8~2010.8,美国宾夕法尼亚大学计算机与信息科学系(CIS),Visiting Researcher
·2002.10~2002.12,日本富士通研究所IT Media Lab,Researcher
欢迎对相关研究领域感兴趣的同学们联系我,加入我们团队。下方是招生专业目录信息。
主要研究方向:视频图像处理与模式识别、深度学习与人工智能、虚拟现实与人机交互、计算机视觉与感知理解、软件工程技术等。
作为项目负责人,主持多项国家自然科学基金、北京市自然科学基金、教育部博士点基金、高等学校基本科研业务费等多项国家级和省部级科研项目。作为主要研究人员,参加国家重点研发计划、国家973课题、国家自然科学基金等多项科研课题。同时,紧密结合行业与企业需求,承担过多个重要应用科研项目,具有长期的软件和应用系统项目组织、设计和开发经验。主要应用科研项目方向:图像视频智能分析处理、视频监控与行为分析、智能算法与应用系统、计算机图形图像处理、三维可视化与仿真系统等。
已在国际国内学术期刊与会议发表学术论文110余篇,其中,SCI检索期刊论文60余篇,EI检索期刊论文60余篇。
近期部分主要论文列表:
[1] Zhiyuan Zou, Weibin Liu*, et al. Minimum volume simplex-based scene representation and attribute recognition with feature fusion. Applied Intelligence, 2023, 53(8):8959-8977.
[2] Zhiyuan Zou, Weibin Liu*, et al. NMEAS: Neuro-MaxEnt architecture search, International Journal of Machine Learning and Cybernetics, 14(9):2963-2977.
[3] Jia Xu, Weibin Liu*, et al. MSPENet: Multi-scale adaptive fusion and position enhancement network for human pose estimation[J]. The Visual Computer, 2023, 39(5):2005-2019.
[4] Dandan Cao, Weibin Liu*, et al. Human pose estimation based on feature enhancement and multi-scale feature fusion[J]. Signal, Image and Video Processing, 2023, 17(3):643-650.
[5] Xiukun Zhang, Weibin Liu*, et al. GCAENet: global-class context with advanced edge network for single human parsing. The Visual Computer, 2023. doi: 10.1007/s00371-022-02735-4.
[6] Huaqing Hao, Weibin Liu*, et al. Multilabel Learning based Adaptive Graph Convolutional Network for Human Parsing[J]. Pattern Recognition, July 2022, 127:108593.
[7] Zhiyuan Zou, Weibin Liu*, et al. AdaNFF: A new method for adaptive nonnegative multi-feature fusion to scene classification[J]. Pattern Recognition, March 2022, 123: 108402.
[8] Hui Wang, Weibin Liu*, et al. Video segmentation via target objectness constraint and multi-head soft aggregation. Neurocomputing, 2022, 510:24-36.
[9] Haitao Xu, Weibin Liu*, et al. Motion-aware future frame prediction for video anomaly detection based on saliency perception[J]. Signal, Image and Video Processing, 2022, 16(8):2121-2129.
[10] Huaqing Hao, Weibin Liu*, et al. Context prior based semantic-spatial graph network for human parsing[J]. Neurocomputing, 2021, 457:13-25
[11] Hui Wang, Weibin Liu*, et al. A temporal attention based appearance model for video object segmentation[J]. Applied Intelligence, 2021, 52(2):2290-2300.
[12] Hui Wang, Weibin Liu*, et al. Video object segmentation via random walks on two-frame graphs comprising superpixels[J]. Journal of Visual Communication and Image Representation, 2021, 80:103293.
[13] Yuxing Wang, Weibin Liu*, et al. Balanced-RetinaNet: solving the imbalanced problems in object detection[J]. Journal of Electronic Imaging, 2021, 30(3):1-14.
[14] Yanhao Cheng, Weibin Liu*, et al. Weighted feature fusion and attention mechanism for object detection[J]. Journal of Electronic Imaging, 2021, 30(2):1-12.
[15] Yanhao Cheng, Weibin Liu*, et al. Complementary Feature Pyramid Network for Human Pose Estimation[C]. 2021 International Joint Conference on Neural Networks (IJCNN 2021), 2021.
[16] Jun Wang, Weibin Liu*, et al. Attention shake Siamese network with auxiliary relocation branch for visual object tracking[J]. Neurocomputing, 2020, 400:53-72.
[17] Bin Wang, Weibin Liu*, et al. Motion capture data segmentation using Riemannian manifold learning[J]. Computer Animation and Virtual Worlds, 2020, 31:e1885. https://doi.org/10.1002/cav.1885
[18] Xingjie Wang, Weibin Liu*, et al. Discriminative context-aware correlation filter network for visual tracking[C]. Intelligent Systems and Applications (IntelliSys 2020), Sept 2020.
[19] Jun Wang, Weibin Liu*, et al. A framework of tracking by multi-trackers with multi-features in a hybrid cascade way [J]. Signal Processing: Image Communication, 2019, 78:306-321.
[20] Cheng Liu, Weibin Liu*, et al. A weighted edge-based level set based on multi-local statistical information for noisy image segmentation. Journal of Visual Communication and Image Representation, 2019, 59: 89-107.
[21] Menglei Jin, Weibin Liu*, et al. A robust visual tracker based on DCF algorithm[J]. International Journal of Software Engineering and Knowledge Engineering, 2019, 29: 1819-1834.
[22] Xing Liu, Weibin Liu*, et al. Image Caption Generation with Local Semantic Information and Global Information[C]. The 16th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2019), 2019.
[23] Menglei Jin, Weibin Liu*, Weiwei Xing. A Robust Visual Tracker Based on DCF Algorithm[C]. The 2019 International Conference on Software Engineering and Knowledge Engineering, 2019.
[24] Yaru Cheng, Weibin Liu*, et al. A Novel Algorithm for Exemplar-based Image Inpainting[C]. The 2019 International Conference on Software Engineering and Knowledge Engineering, 2019.
[25] Jun Wang, Weibin Liu*, et al. Visual object tracking with multi-scale superpixels and color-feature guided kernelized correlation filters[J]. Signal Processing: Image Communication, 2018, 63:44-62
[26] Chuanmin Zhang, Weibin Liu*, et al. Color image enhancement based on local spatial homomorphic filtering and gradient domain variance guided image filtering[J]. Journal of Electronic Imaging, 2018, 27(6):063026.
[27] Cheng Liu, Weibin Liu*, et al. An improved edge-based level set method combining local regional fitting information for noisy image segmentation[J]. Signal Processing, 2017, 130:12-21.
[28] Jun Wang, Weibin Liu*, et al. Two-level superpixel and feedback based visual object tracking[J]. Neurocomputing, 2017, 267:581-596.
[29] Xiaomin Yu, Weibin Liu*, et al. Behavioral segmentation for human motion capture data based on graph cut method[J]. Journal of Visual Languages & Computing, 2017, 43:50-59.
[30] 刘渭滨, 邹智元*, 等. 模式分类中的特征融合方法综述. 北京邮电大学学报, 2017, 4: 1-7.
已获国家发明专利授权18项:
基于授权信息的数媒文件实时加解密方法与系统,ZL2019100821059
基于最小单纯形融合特征学习的场景图像属性识别方法,ZL2018101055762
基于非负特征融合的场景图像分类方法,ZL2018100346008
一种列车无线车次号校核信息数据分析系统及方法,ZL2017109399966
一种GSM-R网络在线实时测试系统及方法,ZL2017109785453
一种机车CIR设备GIS数据库无线升级系统和方法 ZL2017109399364
一种无线列调网络测试日志数据回放与分析方法 ZL2017100388171
一种光照不均图像的增强方法及系统,ZL2016110483695
图像径向畸变的自动矫正方法及系统,ZL2016106942369
改进的基于边缘水平集的含噪图像分割方法与系统,ZL2015108373175
一种铁路GPRS网络关键网元设备主动监测系统和方法 ZL2015100803851
一种用于复杂结构化场景的人群运动轨迹异常检测方法,ZL2015101419356
基于畸变直线结构检测的图像径向畸变矫正的方法及系统,ZL2015104302240
基于人体运动捕捉数据字符串表示的行为分割方法,ZL2015104061085
一种用于复杂场景的层次式人群仿真方法及系统,ZL2015100886093
动态时变环境下寻求全局时间最优路径的方法及系统,ZL201410222902X
针对摄像机抖动下运动目标检测的电子稳像方法及系统,ZL2010105915117
动态背景下的运动目标检测方法及系统,ZL201010582856.6