Zhu Xiaobin, PhD, associate professor. In July 2013, he graduated from the State Key Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, with a doctorate degree. From 2013 to 2018, worked in the Computer Department of Beijing Technology and Business University. Joined the School of Computer and Communication Engineering, University of Science and Technology Beijing in 2019. He has long been engaged in the research of multimedia data mining and image and video intelligent analysis. In recent years, he has published 1 academic monograph in Intellectual Property Publishing House, and published in Pattern Recognition, TIFS, Neurocomputing, Information Science, AAAI, Computer Graphics Forum and other international and domestic journals and conferences He has published more than 30 related papers (including more than 16 first and corresponding authors in the past 5 years). In the research direction, long-term in-depth research has been conducted on the core issues of smart media applications, image super-resolution, fast hash retrieval, and image and video semantic analysis. In recent years, he has presided over 1 National Natural Science Foundation of China, 2 national key research and development sub-projects, participated in 1 National Natural Science Foundation of China general project as a backbone, participated in 1 Beijing Science and Technology Support Plan, and hosted more than 10 horizontal projects.

1 Xiaobin Zhu, Jing Liu, Jinqiao Wang, etc., "Sparse representation for robust abnormality detection in crowded scenes", Pattern Recognition, 47(5), pp. 1791–1799, 2014. (SCI: IF 3.962, JCR 2 )

2 Xiaobin Zhu, Zhuangzi Li, etc., “Residual Invertible Spatio-Temporal Network For Video Super-Resolution”, AAAI2019. (CCF-A Conference)

3 Yaqi Liu, Xiaobin Zhu(#同一作), Xianfeng Zhao*, Yun Cao, “Adversarial Learning for Constrained Image Splicing Detection and Localization based on Atrous Convolution”, IEEE Transactions on Information Forensics & Security, 2019. (Online, IF 5.824 , JCR Zone 1)

4 Xiaobin Zhu, Xin Jin, etc., “Context-aware local abnormality detection in crowded scene”, SCIENCE CHINA Information Sciences, 58(5), pp. 1-11, 2015. (SCI: IF 2.188, JCR 4 area)

5 Chunjie Zhang, Zhe Xue, Xiaobin Zhu*, etc., “Boosted random contextual semantic space based representation for visual recognition”, Information Sciences, Vol.369, pp. 160–170, 2016. (Corresponding author) (SCI: IF 4.305, JCR Zone 1)

6 Xiaobin Zhu, Qian Wang, etc., “Learning Region-wise Deep Feature Representation for Image Analysis”, Journal of Ambient Intelligence and Humanized Computing, 2018. (SCI: IF 1.423, JCR District 4) (Online)

7 Xiaobin Zhu, Zhuangzi Li, etc., "Generative Adversarial Image Super-Resolution Through Deep Dense Skip Connections", Computer Graphics Forum, 37(7), pp.289-300, 2018. (SCI:IF 2.046, JCR Zone 3 )

8 Xiaobin Zhu, Xinming Zhang, etc., “A Novel Framework for Semantic Segmentation with Generative Adversarial Network”, Journal of Visual Communication and Image Representation, Vol. 58, pp. 532-543. (SCI:IF 1.836, JCR 3 )

9 Xiaobin Zhu, Zhuangzi Li, etc., "Deep convolutional representations and kernel extreme learning machines for image classification", Multimedia Tools and Applications, 2018.

10 Peng Li, Xiaobin Zhu*, etc., "Hash Code Reconstruction for Fast Similarity Search", IEEE Signal Processing Letters, (Communication) (SCI: IF 2.813, JCR 3)

11 Xiaobin Zhu, Jing Liu, etc., “Key observation selection-based effective video synopsis for camera network”, Machine Vision and Applications, 25(1), pp. 145-157, 2014. (SCI: IF 1.306, JCR 4 Area)

12 Xiaoyu Zhang, Shupeng Wang, Xiaobin Zhu*, etc., “Update vs. upgrade: Modeling with indeterminate multi-class active learning”, Neurocomputing, Vol.162, pp. 163-170, 2015. (Corresponding author) (SCI :IF 3.241, JCR Zone 3)

13 Yaqi Liu, Xiaoyu Zhang, Xiaobin Zhu*, etc., “ListNet-based object proposals ranking”, Neurocomputing, Vol.267, pp. 182-194, 2017. (Corresponding author) (SCI:IF 3.241, JCR 3 area )

14 Peng Li, Peng Ren, Xiaoyu Zhang, Qian Wang, Xiaobin Zhu*, "Region-Wise Deep Feature Representation for Remote Sensing Images", Remote Sensing, 2018. (Corresponding author) (SCI: IF 3.406, JCR 3)

15 Xiao-Yu Zhang, Haichao Shi, Xiaobin Zhu*, Peng Li, “Active semi-supervised learning based on self-expressive correlation with generative adversarial networks”, Neurocomputing, 2019. (Corresponding author) (SCI:IF 3.241, JCR 3 Area)

16 Zhuangzi Li, Xiaobin Zhu*, Lei Wang, Peiyu Guo2, "Image Classification using Convolutional Neural Networks and Kernel Extreme Learning Machines ", ICIP, 2018. (Corresponding Author) (CCF-C Conference)

17 Xinming Zhang, Xiaobin Zhu*, etc., "SegGAN: Semantic Segmentation with Generative Adversarial Network", BigMM2018.

18 Changsheng Li, Fan Wei, Weishan Dong, Xiangfeng Wang, Junchi Yan, Xiaobin Zhu, Qingshan Liu, Xin Zhang, "Spatially Regularized Streaming Sensor Selection", AAAI 2016, pp.3871-3879. (CCF-A conference)

19 Monograph: Research on Anomaly Detection and Abstract Technology for Intelligent Video Surveillance Intellectual Property Press 2015.

20 Changsheng Li, Qingshan Liu, Weishan Dong, Xiaobin Zhu, Jing Liu, Hanqing Lu, "Human Age Estimation Based on Locality and Ordinal Information", IEEE Transaction on Cybernetics 45(11), pp.2522-2534, 2015. (SCI : IF 8.803, JCR Zone 1)

Vertical project:

1. Research on abnormal event detection technology for crowded monitoring scenarios (youth) National Natural Science Foundation of China 2015/01-2017/12

2. Sub-topic of the National Key R&D Program: Research on Third Party Film and Television Assets Convergence and Trusted Transaction Technology (No. 2017YFB1401000) 2017/12-2020/11, Ministry of Science and Technology

3. Sub-topic of the National Key R&D Program: Deep Learning-based Copyright Tracking and Real-time Copyright Monitoring Technology (No. 2018YFB0803700) Hosted by the Ministry of Science and Technology 2018/1-2020/12

Horizontal items:

1. Horizontal-video search fast algorithm research and implementation, 2015, Sohu Video

2. Horizontal-Research and realization of video content classification and identification, 2016, Sohu Video

3. Horizontal-Research and implementation of content-based video sorting algorithm, Sohu Video, 2017

1. The second prize of 2017 Radio, Film and Television Technology Innovation Award (provincial and ministerial level) ranked second

Project Title: Research on the Application of Deep Learning Technology in Media Convergence

2. The third prize of the 2017 China Film and Television Technology Society Film and Television Science and Technology Excellent Paper Award (provincial and ministerial level) ranked second

Paper Title: Research on Media Fusion Technology Based on Massive Heterogeneous Data Association and Mining

3. The third prize of the 2017 China Film and Television Technology Society Film and Television Science and Technology Excellent Paper Award (provincial and ministerial level) ranked second

Paper Title: Research on Converged Media Intelligence Engine Based on Deep Learning

4. Instructor of CCCV2017 Best Paper (China Computer Vision Conference)

Paper Title: Qiang Cai, Ziyu Xue, Xiaoyu Zhang, Xiaobin Zhu, "A Novel Framework for Image Description Generation".