Welcome!

About me

I have beeing working as a research assistant at Intelligent System Lab with Professor Qiang Ji since 2017, and have been a scholar in RPI-IBM AIRC program since 2019. My research focus is mainly on probabilistic graphical models and its applications in knowledge-augmented deep learning.

My experience

Aug. 2017- present: Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute

Jan. 2020 - Aug. 2020: Externship at IBM Thomas J.Watson Research Center

Aug. 2015- May. 2017: School of Engineering, Brown University

Sep. 2011- May. 2015: Department of Modern Physics, University of Science and Technology of China

Publications

Zijun Cui, Tian Gao, Kartik Talamadupula and Qiang Ji.

Knowledge-augmented Deep Learning and Its Applications: A Survey

IEEE Transactions on Neural Networks and Learning Systems (under review)

Zijun Cui, Tian Gao, Kartik Talamadupula and Qiang Ji..

Biomechanics-guided Facial Action Unit Detection through Force Modeling

IEEE Conference on Computer Vision and Pattern Recognitoon (CVPR), 2023

Zijun Cui, Hanjing Wang, Tian Gao, Kartik Talamadupula and Qiang Ji.

Variational Message Passing Neural Network for Maximum-A-Posteriori Inference

38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022

Zijun Cui, Naiyu Yin, Yuru Wang and Qiang Ji.

Empirical Bayesian Approaches for Robust Constraint-based Causal Discovery under Insufficient Data

31st International Joint Conference on Artificial Intelligence (IJCAI), 2022

PDF arXiv Slides

Zijun Cui, Pavan Kapanipathi, Kartik Talamadupula, Tian Gao and Qiang Ji.

Type-augmented Relation Prediction in Knowledge Graphs

35th AAAI Conference on Artificial Intelligence (AAAI), 2021.

PDF Appendix Poster

Zijun Cui, Tengfei Song, Yuru Wang and Qiang Ji.

Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition

34th Conference on Neural Information Processing Systems (NeurIPS), 2020.

PDF Appendix Poster

Zijun Cui, Yong Zhang and Qiang Ji.

Label Error Correction and Generation Through Label Relationships

34th AAAI Conference on Artificial Intelligence (AAAI), 2020.

Zijun Cui and Qiang Ji.

Blendshape-augmented Facial Action Units Detection

Workshop on Differentiable Vision, Graphics, and Physics in Machine Learning at NeurIPS, 2020.

Chenyi Kuang, Zijun Cui, Jeffrey Kephart, and Qiang Ji.

AU-aware 3D Face Reconstruction through Personalized AU-specific Blendshape Learning

European Conference on Computer Vision (ECCV), 2022.

Tengfei Song, Zijun Cui, Yuru Wang, Wenming Zheng, and Qiang Ji.

Dynamic Probabilistic Graph Convolution for Facial Action Unit Intensity Estimation

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Tengfei Song, Zijun Cui, Wenming Zheng, and Qiang Ji.

Hybrid Message Passing with Performance-Driven Structures for Factial Action Unit Detection

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Projects

Artificial Intelligence Research Collaboration

Since 2019, I have been a scholar in Artificial Intelligence Research Collaboration (AIRC) program. My work is mainly focused on knowledge-augmented deep learning.

Data-Driven Discovery of Models

From 2017 to 2019, I was working on the Data-Driven Discovery of Models (D3M) Project. My work was mainly focused on local markov blanket discovery and its applications to structured feature selection.

Services

Guest reviewer, IEEE Transactions on Affective Computing

Reviewer, CVPR 2022

Reviewer, UAI 2022

Reviewer, ECCV 2022

Contact Me

cuiz3@rpi.edu