About me

I was a PhD student at Department of Electrical, Computer, and System Engineering, Rensselaer Polytechnic Institute. My advisor is Professor Qiang Ji. I successfully defended my dissertation on Nov. 4, 2016. I will be joining Facebook as a research scientist.

I received my Bachelor's Degree in Aug. 2011 from Department of Electronic Engineering, Tsinghua University, China.

My research interests are machine learning and its applications in computer vision, specifically:

  • Probabilistic graphical models, and their applications in deep learning
  • Structure learning in Bayesian network
  • Human action recognition
  • Facial expression recognition
  • Other interesting topics

    • Publications

    Articles in journals

    Siqi Nie, Cassio P. de Campos, and Qiang Ji, "Efficient Learning of Bayesian Networks with Bounded Tree-width," International Journal of Approximate Reasoning (IJAR), 2016. [link]

    Siqi Nie, Ziheng Wang, and Qiang Ji, "A Generative Restricted Boltzmann Machine based Method for High-Dimensional Motion Data Modeling," Computer Vision and Image Understanding (CVIU), Vol. 136, pp. 14-22, 2015. [link]

    Jixu Chen, Siqi Nie, and Qiang Ji, "Data-free Prior Model for Upper Body Pose Estimation and Tracking," IEEE Transactions on Image Processing (TIP), Vol. 22, Issue 12, pp. 4627-4639, 2013.

    Articles in conference proceedings

    Quan Gan, Siqi Nie, Shangfei Wang, and Qiang Ji, "Differentiating between Posed and Spontaneous Expressions with Latent Regression Bayesian Network," in AAAI Conference on Artificial Intelligence (AAAI), 2017. To appear.

    Siqi Nie and Qiang Ji, "Latent Regression Bayesian Network for Data Representation," in Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), 2016.

    Siqi Nie, Tian Gao, and Qiang Ji, "An Information Theoretic Feature Selection Framework Based on Integer Programming," in Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), 2016.

    Siqi Nie, Cassio P. de Campos, and Qiang Ji, "Learning Bayesian Networks with Bounded Tree-width via Guided Search," in AAAI Conference on Artificial Intelligence (AAAI), 2016. Oral Presentation. [PDF] [supp]

    Siqi Nie, Cassio P. de Campos, and Qiang Ji, "Learning Bounded Tree-width Bayesian Networks via Sampling," in Proceedings of the 13th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU), 2015. [PDF]

    Siqi Nie, Denis D. Mauá, Cassio P. de Campos, and Qiang Ji, "Advances in Learning Bayesian Networks of Bounded Treewidth," in Advances in Neural Information Processing Systems (NIPS), 2014. Spotlight Presentation. [PDF] [supp] [arXiv]

    Siqi Nie and Qiang Ji, "Capturing Global and Local Dynamics for Human Action Recognition," in Proceedings of the 22nd International Conference on Pattern Recognition (ICPR), 2014. Oral Presentation. [PDF]

    Siqi Nie and Qiang Ji, "Feature Learning using Bayesian Linear Regression Model," in Proceedings of the 22nd International Conference on Pattern Recognition (ICPR), 2014. [PDF]

    He Wen, Wang Ye, Siqi Nie, Xiaoping Zheng, and Hanyi Zhang, "Asynchronous linear optical sampling for monitoring impairments in multilevel signal modulation format generation," Asia Communications and Photonics Conference and Exhibition, 2011.

    Demos

  • Real-time facial expression recognition. [YouTube]

    • Services

  • Guest reviewer, International Journal of Approximate Reasoning
  • Guest reviewer, IEEE Transactions on Image Processing
  • Guest reviewer, Neurocomputing
  • Subreviewer, AAAI Conference on Artificial Intelligence
  • Guest reviewer, IEEE International Conference on Systems, Man, and Cybernetics
  • Guest reviewer, EURASIP Journal of Image and Video Processing
  • Guest reviewer, MultiMedia Tools and Applications

    • Contact me

    Email: nies AT rpi DOT edu