Picture of Xiaoyang Wang

Xiaoyang Wang

Murray Hill, NJ, USA
Video Analysis and Coding Researcher

Education

Rensselaer Polytechnic Institute, USA
Received Ph.D. Degree in Electrical Engineering (Dept. URL)
Received M.S. Degree in Applied Mathematics (Dept. URL)

Tsinghua University, China
Received M.S. and Bachelor's Degrees from Dept. of Electronic Engineering (Dept. URL)

Biography

Xiaoyang Wang received the Bachelor and M.S. degrees both from Tsinghua University, Beijing, China, in 2007 and 2010 respectively. He received his Ph.D. degree from Rensselaer Polytechnic Institute, Troy, NY in May 2015. Since June 2015, he has been working in Nokia Bell Labs, Murray Hill, NJ as a Video Analysis and Coding Researcher. His research interests include video analytics and understanding, object recognition, context modeling, probabilistic graphical models, machine learning, and deep learning. He won the ICPR Piero Zamperoni Best Student Paper Award in 2012. He is a member of the IEEE.

Research Interests

  • Artificial Intelligence
  • Deep Learning
  • IoT/M2M
  • Machine Learning

Honors and Awards

Finalist Best Intel Track 2 Scienti c Paper Award, 2016 International Conference on Pattern Recognition (URL)
Piero Zamperoni Best Student Paper Award, 2012 International Conference on Pattern Recognition (URL)

Professional Activities

Reviewer of the IEEE Transactions on Pattern Analysis and Machine Intelligence.
Reviewer of the IEEE Transactions on Multimedia.
Reviewer of the Pattern Recognition Letters.
Reviewer of the Image and Vision Computing.
Reviewer of the IET Computer Vision.
Reviewer of the IET Image Processing.
Reviewer of the AAAI Conference on Artificial Intelligence.

Selected Articles and Publications

  • Xiaoyang Wang, Qiang Ji, "Hierarchical Context Modeling for Video Event Recognition", in the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2016.
  • Xiaoyang Wang, Yue Zhao, Qiang Ji, "Taxonomy Augmented Object Recognition", in the International Conference on Pattern Recognition, pp. 1370-1375, 2016. (Oral, Finalist Best Intel Track 2 Scientific Paper Award)
  • Yue Zhao, Rui Zhao, Xiaoyang Wang, Qiang Ji, "Multilingual Articulatory Features Augmentation Learning", in the International Conference on Pattern Recognition, pp. 2895-2899, 2016.
  • Xiaoyang Wang, Qiang Ji, "Object Recognition with Hidden Attributes", in the International Joint Conference on Artificial Intelligence, pp. 3498-3504, 2016. (Oral)
  • Xiaoyang Wang, Qiang Ji, “Video Event Recognition with Deep Hierarchical Context Model”, in the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4418-4427, 2015.
  • A. Hoogs et al., “An End-to-End System for Content-Based Video Retrieval using Behavior, Actions, and Appearance with Interactive Query Refinement”, in the IEEE International Conference on Advanced Video and Signal-Based Surveillance, pp. 1-6, 2015.
  • Yue Zhao, Nan Zhou, Libing Zhang, Licheng Wu, Rui Zheng, Xiaoyang Wang, Qiang Ji, “Shared speech attribute augmentation for English-Tibetan cross-language phone recognition”, in the IEEE International Symposium on Signal Processing and Information Technology, pp. 539-543, 2015.
  • Xiaoyang Wang, Qiang Ji, “A Hierarchical Context Model for Event Recognition in Surveillance Video”, in the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2561-2568, 2014.
  • Xiaoyang Wang, Qiang Ji, “Context Augmented Dynamic Bayesian Networks for Event Recognition”, in Pattern Recognition Letters, vol. 43, pp. 62-70, 2014.
  • Xiaoyang Wang, Qiang Ji, “Attribute Augmentation with Sparse Coding”, in Proceedings of the 22nd International Conference on Pattern Recognition, pp. 4352-4357, 2014.
  • Ziheng Wang, Xiaoyang Wang, Qiang Ji, “Learning with Hidden Information”, in the International Conference on Pattern Recognition, pp. 238-243, 2014. (Oral)
  • Xiaoyang Wang, Qiang Ji, “A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects”, in the IEEE International Conference on Computer Vision, pp. 2120-2127, 2013.
  • Xiaoyang Wang, Qiang Ji, “Incorporating Contextual Knowledge to Dynamic Bayesian Networks for Event Recognition”, in the International Conference on Pattern Recognition, pp. 3378-3381, 2012. (Oral, Piero Zamperoni Best Student Paper Award)
  • Xiaoyang Wang, Qiang Ji, “A Novel Probabilistic Approach Utilizing Clip Attributes as Hidden Knowledge for Event Recognition”, in the International Conference on Pattern Recognition, pp. 3382-3385, 2012. (Oral)
  • Xiaoyang Wang, Qiang Ji, “Learning Dynamic Bayesian Network Discriminatively for Human Activity Recognition”, in the International Conference on Pattern Recognition, pp. 3553-3556, 2012.
  • Sangmin Oh, et al., “A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video”, in the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3153-3160, 2011.
  • Sangmin Oh, et al., “AVSS 2011 demo session: A large-scale benchmark dataset for event recognition in surveillance video”, in the IEEE International Conference on Advanced Video and Signal-Based Surveillance, PP. 527-528, 2011.
  • Xiaoyang Wang, Youbin Chen, “A Novel Seal Imprint Verification Method Based on Analysis of Difference Images and Symbolic Representation”, in the 4th International Workshop on Computational Forensics, pp. 56-67, 2010. (Oral)
  • Xiaoyang Wang, Youbin Chen, “Seal Image Registration Based on Shape and Layout Characteristics”, in the 2nd International Congress on Image and Signal Processing, vol. 7, pp. 3440-3444, 2009.

Books and Chapters

  • Xiaoyang Wang, Zhi Zeng, Qiang Ji, “Activity Modeling and Recognition using Probabilistic Graphical Models”, in Emerging Topics in Computer Vision and its Applications Series in Computer Vision, vol. 1, pp. 71-92, 2011.

Patents

  • Roger Levy, Larry O'Gorman, Xiaoyang Wang, “Method For Accelerated Usage of A Learning-Based Video Surveillance System”, filed the U.S. patent with Nokia in 2017.
  • Roger Levy, Larry O'Gorman, Xiaoyang Wang, “Method For Recovering Network Connection In Application Framework That Hides Sockets”, filed the U.S. patent with Nokia in 2017.