Visual Information Processing and Learning
Visual Information Processing and Learning
Jiabei Zeng

Research area: Computer Vision, Affective Computing

Jiabei Zeng, Ph.D. 

I am an assistant professor at Institute of Computing Technology, Chinese Academy on Sciences. My research is on computer vision and affective computing, particularly understanding human's affect by developing some machine learning methods. Currently, I work closely with Professor Shiguang Shan and Professor Xilin Chen.

In the spring of 2017, I obtained my Ph.D. degree from Beihang University (aka Beijing University of Aeronautics and Astronautics) under the supervision of Professor Zhang Xiong. Before that, I received my B.S. degree from the same university in 2011. In the third and the fourth year of my doctoral program, I was a visiting scholar sponsored by China Scholarship Council at Robotics Institute in Carnegie Mellon University, under the supervision of Professor Fernando De la Torre. My doctoral thesis is Methods for Spontaneous Facial Action Unit Analysis.

Experience
Educational experience
  • 2013.9-2015.8 Robotics Institute, Carnegie Mellon University, visiting student.
  • 2011.9-2017.3 School of Computer Science and Engineering, Beihang University, Ph.D.
  • 2007.9-2011.7 School of Advanced Engineering, Beihang University, B.S.
Academic experience
  • 2017.3-present Institute of Computing Technology, Chinese Academy of Sciences, Assistant Professor
Research project

1.   Natural facial expression recognition based on large-scale data with hybrid labels

Project type: NSFC
Project time: 2018.01-2020.12
Project leader: Jiabei Zeng
Book or Paper

Papers

Journal paper:

[1]. Jiabei Zeng, Yang Liu, Biao Leng, Zhang Xiong, Yiu-ming Cheung. Dimensionality Reduction in Multiple Ordinal Regression. IEEE transactions on neural networks and learning systems, 2018, 29(9): 4088-4101.

[2]. Jiabei Zeng, Wen-Sheng Chu, Fernando De la Torre, Jeffrey F. Cohn, and Zhang Xiong. Confidence Preserving Machine for Facial Action Unit Detection. IEEE Transactions on Image Processing, 2016, 25(10): 4753-4767.

[3]. Jiabei Zeng, Biao Leng, and Zhang Xiong. 3-D Object Retrieval using Topic Model. Multimedia Tools and Applications, 2015, 75(18): 7859-7881.

[4]. Biao Leng, Jiabei Zeng, Min Yao, and Zhang Xiong. 3D Object Retrieval With Multi-topic Model Combining Relevance Feedback and LDA Model. IEEE Transactions on Image Processing, 2015, 24(1): 94-105.

[5]. Biao Leng, Jiabei Zeng, Zhang Xiong, Weifeng Lv, Yueliang Wan. Probability tree based passenger flow prediction and its application to the Beijing subway system. Frontiers of Computer Science, 2013, 7(2): 195-203.

[6]. Jia-Bei Zeng, Biao Leng, Zhang Xiong, Zheng Qin. Pedestrian dynamics in a two-dimensional complex scenario using a local view floor field model. International Journal of Modern Physics C, 2011.8.01, 22(8): 775-803.

Conference paper:

[1]. Jiabei Zeng, Shiguang Shan, Xilin Chen. Facial Expression Recognition with Inconsistently Annotated Datasets. European Conference on Computer Vision, 2018.

[2]. Yong Li, Jiabei Zeng, Shiguang Shan, Xilin ChenPatch-Gated CNN for Occlusion-aware Facial Expression Recognition. International Conference on Pattern Recognition2018. (Oral)

[3]. Yuanyuan Liu, Jiabei Zeng, Shiguang Shan, Zhuo Zheng. Multi-channel Pose-aware Convolution Neural Networks for Multi-view Facial Expression Recognition. IEEE International Conference on Automatic Face & Gesture Recognition, 2018. 

[4]. Yong Li, Jiabei Zeng, Jie Zhang, Anbo Dai, Meina Kan, Shiguang Shan, and Xilin Chen. KinNet: Fine-to-Coarse Deep Metric Learning for Kinship Verification. In Proceedings of the Workshop on Recognizing Families In the Wild, 2017.

[5]. Jiabei Zeng, Wen-Sheng Chu, Fernando De la Torre, Jeffrey F. Cohn and Zhang Xiong. Confidence Preserving Machine for Facial Action Unit Detection. IEEE International Conference on Computer Vision, 2015, 3622-3630.

[6]. Wen-Sheng Chu, Jiabei Zeng, Fernando De la Torre, Jeffrey F. Cohn, and Daniel S. Messinger. Unsupervised Synchrony Discovery in Human Interaction. IEEE International Conference on Computer Vision, 2015, 3146-3154.


Visual Information Processing and Learning
  • Address :No.6 Kexueyuan South Road
  • Zhongguancun,Haidian District
  • Beijing,China
  • Postcode :100190
  • Tel : (8610)62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • Big Lecture of DL

Copyright @ Visual Information Processing and Learning 京ICP备05002829号 京公网安备1101080060