张顺利

基本信息

教育背景

2011-2016年，清华大学，博士

2008-2011年，山东大学，硕士

工作经历

2016年3月-至今：北京交通大学，软件学院

2018年10月-2019年10月：美国卡内基梅隆大学（CMU），计算机学院，访问学者

研究方向

▣人工智能

❶ 视频图像处理与分析/计算机视觉

  ● 图像增强复原

  ● 视觉目标跟踪、视频分割

  ● 目标检测与识别

  ● 行为动作识别

  ● 步态识别

❷ 智能认知决策

  ● 路径规划

  ● 资源分配

  ● 任务规划

  ● 智能推荐

❸ 机器学习与深度学习

Research Interests

▣ Artificial Intelligence

□ Multimedia: Image & Video Processing and Analysis / Computer Vision 

  ●Image Enhancement and Restoration

  ●Object Tracking and Video Segmentation

  ●Object Detection and Recognition

  ●Action Recognition

  ●Gait Recognition

□ Intellegent Cognition and Decision

  ●Path Planning

  ●Resource Allocation

  ●Mission Planning

  ●Intellegent Recommendation

□ Machine Learning and Deep Learning

招生专业

• 软件工程硕士
• 软件工程博士

科研项目

● 2023-2024，多模态视觉感知语义分割技术研究，自然科学基金横向项目，主持

● 2023-2024，智能任务分配规划技术研究，省部级企事业项目，主持

● 2020-2023, 复杂天气条件下的目标跟踪和步态识别研究, 国家自然科学基金面上项目，主持

● 2020-2022, 基于注意力机制的目标跟踪和步态识别研究，北京市自然科学基金面上项目，主持

● 2020-2021, 半监督学习目标跟踪研究，北京交通大学，主持

● 2019-2022, 基于深度学习的智能交通视频目标检测识别和跟踪方法, 国家自然科学基金面上项目，参与

● 2019-2020, 基于深度强化学习的路径规划与目标分配研究，北京交通大学，主持

● 2018-2019, 智能试纸识别算法研究，北京交通大学，主持

● 2018-2019, 基于深度强化学习的视觉目标跟踪和行为识别研究, 北京市自然科学基金-海淀原始创新联合项目, 主持

● 2017-2019, 基于时空结构约束与特征学习的目标跟踪研究, 国家自然科学基金青年项目, 主持

● 2016-2018, 基于分层鉴别式模型的目标跟踪研究, 北京交通大学人才基金, 主持

教学工作

● 本科生课程：移动应用开发技术/综合研究专题/机器学习

● 硕士生课程：机器学习/深度学习原理与应用

● 博士生课程：深度学习模型与算法/智能交通前沿专题

论文/期刊

· J. Chen, Q. Yang, S. Tian and S. Zhang, Adaptive Quantization with Mixed-Precision Based on Low-Cost Proxy, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 6720-6724

· Q. Yang, Y. Zhang, Z. Zhao, J. Zhang and S. Zhang, IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network, in IEEE Signal Processing Letters, vol. 31, pp. 1374-1378, 2024

· S. Qin, S. Zhang and Y. Zhang, "Using Mask-Based Enhancement and Feature Aggregation for Single Image Deraining," in IEEE Signal Processing Letters, vol. 30, pp. 828-832, 2023

· S. Qin, S. Zhang, Y. Zhang and H. Gao, "CAENet: Using Collaborative Attention Transformer and Add-Boost Strategy for Single Image Deraining," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5

· Senmao Tian, Ming Lu, Jiaming Liu, Yandong Guo, Yurong Chen, Shunli Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 1756-1765

· Ming Wang, Xianda Guo, Beibei Lin, Tian Yang, Zheng Zhu, Lincheng Li, Shunli Zhang, Xin Yu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 13424-13433

· F. Bao, Y. Cao, S. Zhang, B. Lin and S. Zhao, Using Segmentation With Multi-Scale Selective Kernel for Visual Object Tracking, in IEEE Signal Processing Letters, vol. 29, pp. 553-557, 2022

· Ming Wang, Beibei Lin, Xianda Guo, Lincheng Li, Zheng Zhu, Jiande Sun, Shunli Zhang, Yu Liu, Xin Yu; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 536-551

· Lin B, Zhang S*, Yu X. Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2021: 14648-14656.

· Tian S, Zhang S*, Lin B. Blind Image Deblurring Based on Dual Attention Network and 2D Blur Kernel Estimation. 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021: 1729-1733. 

· Lin B, Zhang S*, Liu Y, et al. Multi-Scale Temporal Information Extractor For Gait Recognition. 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021: 2998-3002.

· Beibei Lin, Shunli Zhang*, Feng Bao. Gait Recognition with Multiple-Temporal-Scale 3D Convolutional Neural Network. Proceedings of the 28th ACM International Conference on Multimedia (ACM MM). 2020.

· Shunli Zhang, Li Zhang, Alexander Hauptmann. Fuzzy Least Squares Support Vector Machine with Adaptive Membership for Object Tracking, IEEE Transactions on Multimedia, vol. 22, no. 8, pp. 1998-2011,  Aug. 2020. 

· Shunli Zhang, Wei Lu, Weiwei Xing, Li Zhang. Learning scale-adaptive tight correlation filter for object tracking, IEEE Transactions on Cybernetics, vol. 50, no. 1, pp. 270-283,  Jan. 2020.

· Yupei Zheng, Xin Yu, Miaomiao Liu, Shunli Zhang*. Residual Multiscale Based Single Image Deraining. BMVC, 147, 2019.

· Shunli Zhang, Wei Lu, Weiwei Xing, Li Zhang. Using fuzzy least squares support vector machine with metric learning for object tracking, Pattern Recognition, 2018, 84: 112-125.

· Shunli Zhang, Yao Sui, Sicong Zhao, Li Zhang. Graph Regularized Structured Support Vector Machine for Object Tracking. IEEE Transactions on Circuit and System for Video Technology, vol.27, no.6, pp.1249-1262, June 2017.

· Sicong Zhao, Shunli Zhang, and Li Zhang. Towards occlusion handling: object tracking with background estimation. IEEE Transactions on Cybernetics, 48.7 (2017): 2086-2100.

· Lincheng Li, Shunli Zhang, Xin Yu, Li Zhang. PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching. IEEE Transactions on Circuit and System for Video Technology.  28(3), 679-692, 2016.

· Jun Yang, Shunli Zhang, Li Zhang. Object tracking with hierarchical multiview learning. Journal of Electronic Imaging, vol. 25, no.5, pp. 053006-053006. September 2016.

· Juntao Sun, Shunli Zhang, and Li Zhang. Object tracking with spatial context model. IEEE signal processing letter. vol. 23, no. 5, May 2016.

· Shunli Zhang, Sicong Zhao, Yao Sui, Li Zhang. Single object tracking with fuzzy least squares support vector machine, IEEE Transactions on Image Processing, vol.24, no.12, pp.5723-5738, December 2015. 

· Shunli Zhang, Xin Yu, Yao Sui, Sicong Zhao, Li Zhang. Object tracking with multi-view support vector machines, IEEE Transactions on Multimedia, vol.17, no.3, pp.265-278, March 2015.

· Shunli Zhang, Yao Sui, Xin Yu, Sicong Zhao, Li Zhang. Hybrid support vector machines for robust object tracking, Pattern Recognition, vol.48, no.8, pp.2474-2488, August 2015.

· Shunli Zhang, Yao Sui, Sicong Zhao, Xin Yu, Li Zhang. Multi-local-task learning with global regularization for object tracking, Pattern Recognition, vol.48, no.12, pp.3881-3894, December 2015.

· Yao Sui, Shunli Zhang, Li Zhang. Robust visual tracking via sparsity-induced subspace learning, IEEE Transactions on Image Processing, vol.24, no.12, pp.4686-4700, December 2015.

· Xin Yu, Shunli Zhang, Xiaolin Zhao, Li Zhang. Removing blur kernel noise via a hybrid lp norm. Journal of Electronic Imaging. vol.24, no.1, 013011, January/February, 2015.

· Yao Sui, Xiaolin Zhao, Shunli Zhang, Xin Yu, Sicong Zhao, Li Zhang. Self-expressive tracking, Pattern Recognition, vol.48, no.9, pp.2872–2884, September 2015.

· Xin Yu, Feng Xu, Shunli Zhang, Li Zhang. Efficient patch-wise non-uniform deblurring for a single image, IEEE Transactions on Multimedia, vol.16, no.6, pp.1510-1524, October 2014.

· Li Zhang, Yubo Guo, Juntao Sun, Xin Yu, Shunli Zhang. Object tracking by feedback update scheme with sparsity constraint. Journal of Tsinghua University (Science and Technology), 11(005), 2013

· Shunli Zhang, Min Han, Weifeng Sun, Mingqiang Yang. Iris feature extraction and recognition based on Empirical mode decomposition. 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), vol.6, pp. 2633-2636. 

专著/译著

专利

软件著作权

获奖与荣誉

2021，第二届国际步态识别大赛（HID2021），第1名

2020，首届国际步态识别大赛（HID2020）， 第1名

社会兼职