主要从事“基于人工智能的视频大数据分析”的研究。主持/参与了国家重大研发、国家自然基金、深圳市科创委重点专项、新加坡智慧城市建设(POLCAM 2.0)等多个项目(其中POLCAM 2.0被新加坡《海峡时报》作为重大科技成果予以报道)。近年来，围绕图像去噪&复原、运动估计、目标分割、视频大数据人体行为分析&事件检测，发表学术论文近50篇，其中30余篇发表在图像处理和人工智能领域的国际顶级会议(如CVPR2021, ECCV2020, ICCV2019, CVPR2018)和国际权威SCI期刊(如IEEE Transactions-IP、Pattern Recognition、IEEE Transactions-CSVT)上。第一作者/通信作者论文20多篇，其中CCF A类会议&中科院1区SCI论文13篇。指导研究生荣获中国人工智能学会主办的ACAIT2020大会“最佳学生论文奖”，获ICCV2021‒MMVRAC挑战赛2个赛道亚军。

先后担任SCI期刊The Visual Computer (IF=2.601, JCR 2区)编委， JVCIR (IF=2.678) 特刊“Multi-Modality Human Activity Understanding”首席客座编委，CC&HTS (IF=1.339) 执行客座编委，亚洲人工智能技术大会ACAIT2021 Publication Chair & ACAIT2020程序委员会委员，2020年亚洲计算机视觉大会(ACCV) Workshop MMHAU第一组织者，2020年第91期CCF走进高校-武汉大学专场执行主席，2019年亚洲模式识别大会(ACPR) Workshop MAGR第一组织者，国际知名遥感大会ISPRS IWIDF2017区域主席。中文核心期刊《计算机工程》青年编委。

工程技术开发成果被BBC、Dutch TV、新加坡《海峡时报》等国际主流媒体广泛报道。参与完成的“第七届世界军人运动会测绘地理信息综合保障服务及关键技术”荣获2020年中国测绘学会测绘科技“一等奖”（省部级）。主持开发的基于视频大数据的异常事件检测子系统被世界500强企业埃森哲(Accenture)商业推广，已有近20万个该智能探头安装于新加坡大街小巷。

教育经历

2016年12月1日 – 2018年7月31日:

• 研究员, School of Electrical & Electronic Engineering

• 南洋理工大学,  新加坡

• 合作导师: Prof. Junsong Yuan

• 大学排名 (2020): 11th (QS); 43th (USNews); 48th (Times)

2015年12月1日 – 2016年11月31日:

• 博士后, School of Computing, Informatics, Decision System Engineering

• 亚利桑那州立大学,  美国

• 合作导师: Full Prof. & School Chair Baoxin Li

• 大学排名 (2020): 43th (USNews  美国计算机科学); 11th (USNews  美国摄影与遥感)

2011 年 9 月 1 日 – 2015 年 10 月 31 日:

• 博士, Department of Information and Computing Sciences

• 乌特勒支大学 (Utrecht University),  荷兰

• 导师: Full Prof. Remco Veltkamp

• 大学排名 (2020): 55th (USNews); 75th (Times)

2008 年 9 月 1 日 – 2011 年 8 月 31 日:

• 硕博连读,  武汉大学测绘遥感信息工程国家重点实验室

• 武汉大学,  中国

• 导师: 王高峰，秦前清

1. Yujin Chen^#, Zhigang Tu^#, Di Kang, Ruizhi Chen, Linchao Bao, Zhengyou Zhang, and Junsong Yuan. Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion. IEEE Transactions on Image Processing (T-IP), vol.30, pp.4008-4021, 2021. (共同第一作者, IF=10.856，CCF A类期刊/中科院1区)

2. Yunpeng Chang, Zhigang Tu*, Bin Luo, and Junsong Yuan. Video Anomaly Detection with Spatio-Temporal Dissociation. Pattern Recognition, vol., pp., 2021. (通信作者，IF=7.74，中科院1区)

3. Yujin Chen, Zhigang Tu*, Di Kang, Linchao Bao, Ying Zhang, Xuefei Zhe, Ruizhi Chen, Junsong Yuan. Model-based 3D Hand Reconstruction via Self-Supervised Learning. CVPR, pp.10451-10460, 2021. (通信作者，CCF A类会议，CV&AI三大顶会之一)

4. Jiaxu Zhang, Gaoxiang Ye, Zhigang Tu*, Yongtao Qin, Qianqing Qin, Jinlu Zhang, and Jun Liu. A Spatial Attentive and Temporal Dilated (SATD) GCN for Skeleton-Based Action Recognition. CAAI Transactions on Intelligence Technology, Sep. 2021. (通信作者, ESCI, 中国人工智能学会主办的ACAIT2020大会“最佳学生论文奖”)

5. Long Tian, Zhigang Tu*, Dejun Zhang, Jun Liu, Baoxin Li, and Junsong Yuan. Unsupervised Learning of Optical Flow With CNN-based Non-Local Filtering. IEEE Transactions on Image Processing (T-IP), vol.29, pp.8429–8442, Aug., 2020. (通信作者, IF=10.856，CCF A类期刊/中科院1区)

6. Yunpeng Chang, Zhigang Tu*, Wei Xie, Junsong Yuan. Clustering-driven Deep Autoencoder for Video Anomaly Detection. European Conference on Computer Vision (ECCV), pp.329-345, 2020. (通信作者，计算机视觉&人工智能三大顶会之一)  

7. Dejun Zhang*, Linchao He, Zhigang Tu*, Shifu Zhang, Fei Han, and Boxiong Yang. Learning Motion Representation for Real-Time Spatio-Temporal Action Localization. Pattern Recognition, vol.103, pp.107312, July 2020. (通信作者，IF=7.74，中科院1区)

8. Yujing Chen, Zhigang Tu*, Liuhao Ge, Dejun Zhang, Ruizhi Chen, and Junsong Yuan. SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning. IEEE Int. Conference on Computer Vision (ICCV), pp.6961–6970, Nov. 2019. (通信作者，CCF A类，计算机视觉&人工智能三大顶会之一)

9. Zhigang Tu, Hongyan Li*, Dejun Zhang, Justin Dauwels, Baoxin Li, and Junsong Yuan. Action-Stage Emphasized Spatio-Temporal VLAD for Video Action Recognition. IEEE Transactions on Image Processing, 28(6):2799–2812, Jun. 2019. (IF=10.856，CCF A类期刊/中科院1区)

10. Zhigang Tu*, Wei Xie, Justin Dauwels, Baoxin Li, and Junsong Yuan. Semantic Cues Enhanced Multi-modality Multi-Stream CNN for Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 29(5): 1423–1437, May 2019. (IF=4.685，中科院2区)

11. Zhigang Tu*, Wei Xie*, Dejun Zhang, Ronald Poppe, Remco C. Veltkamp, Baoxin Li, and Junsong Yuan. A survey of variational and CNN-based optical flow techniques. Signal Processing: Image Communication, vol.72, pp.9–24, March 2019. (综述, 热点论文, IF=3.256，中科院2区)

12. Zhigang Tu, Wei Xie, Qianqing Qin*, Remco C. Veltkamp, Baoxin Li, and Junsong Yuan. Multi-Stream CNN: Learning Representations Based on Human-Related Regions for Action Recognition. Pattern Recognition, vol.79, pp.32–43, July 2018. (IF=7.74，中科院1区)

13. Zhigang Tu*, Zuwei Guo, Wei Xie, Mengjia Yan, Remco.  C.  Veltkamp, Baoxin Li, and  Junsong Yuan. Fusing disparate object signatures for salient object detection in video. Pattern Recognition, vol.72, pp.285–299, Dec. 2017. (IF=7.74，中科院1区)

14. ZhigangTu*, WeiXie, JunCao, Coertvan Gemeren, Ronald Poppe, and Remco C. Veltkamp. Variational Method for Joint Optical Flow Estimation and Edge-aware Image Restoration. Pattern Recognition, vol.65, pp.11–25, May 2017. (IF=7.74，中科院1区)

15. Zhigang Tu*, Ronald Poppe, and Remco C. Veltkamp. Weighted Local Intensity Fusion Method for Variational Optical Flow Estimation. Pattern Recognition, vol.50, pp.223–232, Feb. 2016. (IF=7.74，中科院1区)

16. Zhigang Tu, Nico. Aa, CoertVan Gemeren, and Remco C. Veltkamp*. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition, vol.47, no.5, pp.1926–1940, May 2014. (IF=7.74，中科院1区)

17. Zhigang Tu*, Ronald Poppe, and Remco C. Veltkamp. Adaptive Guided Image Filter for Warping in Variational Optical Flow. Signal Processing, vol.127, pp.253–265, Oct. 2016. (IF=4.662，中科院2区)

18. Zhigang Tu, Yikang Li, Jun Cao, and Baoxin Li.  MSR-CNN:  Applying Motion Salient Region Based Descriptors for Action Recognition. In Proc. International Conference on Pattern Recognition (ICPR), pp.3524–3529, Dec. 2016. (CCF C类会议)

19. Zhigang Tu, Coert Van Gemeren, and Remco C. Veltkamp. Improved color patch similarity measure based weighted median filter. In Proc. Asian Conference on Computer Vision (ACCV), vol.9007, pp.413–427, 2015. (CCF C类会议)

20. Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, and Junsong Yuan. Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display. In Proc. Comput. Vis. Pattern Recogn. (CVPR), pp.2031–2040, 2018. (CCF A类，计算机视觉&人工智能三大顶会之一)

21. Zhigang Tu, Wei Xie, Wolfgang Hurst, and Qianqing Qin. Weighted root mean square approach to select the optimal smoothness parameter of the variational optical flow algorithms. Optical Engineering, vol.51, no.3, 037202, 2012. (IF=1.084，中科院4区)

22. Zhigang Tu, Ronald Poppe, and Remco C. Veltkamp. Estimating Accurate Optical Flow in the Presence of Motion Blur. Journal of Electronic Imaging, vol.24, no.5, 053018, 2015. (IF: 0.945，中科院4区)

专利

1. 《一种区域视频人体动作行为实时识别方法》，专利号：201910513640.5，发文序号：2019102100381650

2. 《一种基于深度学习的非局部滤波器无监督光流估计算法》，专利号：202010328677.3，发文序号：2020042400068710

3. 《一种融合多源信息的高精度视频异常事件检测方法》，专利号：202010391419.X，发文序号：2020051101270520

4. 《一种基于半监督学习的深度图像手势估计方法》，专利号：202010503293.0，发文序号：2020071600873190

5. 《一种基于边界框关键点距离的目标检测方法》，专利号：2020111067602.0，发文序号：20210201011006.40

奖励

1. 2021国际计算机视觉大会(ICCV2021) MMVRAC挑战赛“骨架人体动作识别”、“鱼眼视频人体动作识别”两个赛道亚军；

2. 《第七届世界军人运动会测绘地理信息综合保障服务及关键技术》,中国测绘学会, 科技进步“一等奖”(省部级), 2020，排名7/15；

3. 第四届亚洲人工智能技术大会(ACAIT2020)“最佳学生论文奖”, 中国人工智能学会，通讯作者.

研究服务

1. 担任SCI期刊The Visual Computer (IF=2.601，CCF C类)编委.

2. 担任SCI期刊Journal of Visual Communication and Image Representation (IF=2.678)客座编委.

3. 担任中文核心期刊《计算机工程》青年编委.

4. 担任ACCV 2020, Workshop on Multi-visual-Modality Human Activity Understanding (MMHAU) 组织者(Organizer), Kyoto, Japan. http://tuzhigang.cn/ACCV_Workshop.html

5. 担任The 5th Asian Conference on Pattern Recognition (ACPR) 2019, Workshop on Multi-sensor for Action and Gesture Recognition组织者(Organizer), Auckland (奥克兰), New Zealand, 2019.

6. 担任The 5th Asian Conference on Artificial Intelligence Technology (ACAIT) 2021的Publication Chair; ACAIT 2020的程序委员会委员.