427 Richards Hall
Department of Electrical and Computer Engineering
Northeastern University
Boston, MA, USA

Yu Kong (孔屿) [Google Scholar]

Short Bio

My name is Yu Kong. I am a Postdoc in Prof. Yun (Raymond) Fu's Synergetic Media Learning (SMILE) lab, in the department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA. I received my PhD degree in Beijing Institute of Technology, supervised by Prof. Yunde Jia. During Dec 2007 to July 2009, I was a visiting student at National Laboratory of Pattern Recognition (NLPR), Chinese Academy of Science, supervised by Prof. Weiming Hu and Prof. Hanzi Wang.


Research Interests
  • Computer Vision: Video Understanding, Action Recognition, Object Recognition, Object Detection, Image Geolocation.
  • Machine Learning: Graphical model, deep learning, max-margin training, hashing methods, boosting, random forests, metric learning. 

Wordle word cloud generated from the titles of my papers.

  • Yu Kong and Yun Fu. Bilinear Heterogeneous Information Machine for RGB-D Action Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [PDF] NEW

  • Yu Kong, Behnam Sattar, and Yun Fu. Hierarchical 3D Kernel Descriptors for Action Recognition Using Depth Sequences. IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2015. NEW

  • Yu Kong and Yun Fu. Modeling Supporting Regions for Close Human Interaction Recognition. European Conference on Computer Vision workshop, 2014.

  • Chengcheng Jia, Yu Kong, Zhenming Ding, and Yun Fu. Latent Tensor Transfer Learning for RGB-D Action Recognition. ACM Multimedia 2014 (long paper). [PDF]

  • Yu Kong, Dmitry Kit, and Yun Fu. A Discriminative Model with Multiple Temporal Scales for Action Prediction. 
    European Conference on Computer Vision (ECCV), 2014. [PDF]

  • Dmitry Kit, Yu Kong, and Yun Fu. LASOM: Location Aware Self-Organizing Map for Discovering Similar and Unique Visual Features of Geographical Locations.
    International Joint Conference on Neural Network (IJCNN), 2014. (Oral)

  • Yu Kong, Yunde Jia and Yun Fu. Interactive Phrases: Semantic Descriptions for Human Interaction Recognition. 
    IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2014

  • Yu Kong, Wei Liang, and Yunde Jia. Recognizing Human Interaction from Videos by a Discriminative Model. IET Computer Vision. Accepted. 

  • Cuiwei Liu, Mingtao Pei, Xinxiao Wu, Yu Kong, and Yunde Jia. Learning a discriminative mid-level feature for action recognition. Science China Information Sciences, 2013 

  • Jie Hu, Yu Kong, and Yun Fu. Activity Recognition by Learning Structural and Pairwise Mid-level Features Using Random Forest. Automatic Face and Gesture Recognition (FG), 2013. [PDF]

          [PDF], [Poster], [PPT]
  • Yu Kong and Yunde Jia. A Hierarchical Model for Human Interaction Recognition. IEEE International Conference on Multimedia and Expo (ICME), 2012, oral [PDF] [PPT]

  • Zhi Yang, Yu Kong, and Yun Fu. Decomposed Contour Prior for Shape Recognition. International Conference on Pattern Recognition (ICPR), 2012. [PDF]

  • Zhi Yang, Yu Kong, and Yun Fu. Contour-HOG: A Stub Feature based Level Set Method for Learning Object Contour. British Conference on Computer Vision (BMVC), 2012. [PDF]

  • Cuiwei Liu, Yu Kong, Xinxiao Wu, and Yunde Jia. Action Recognition with Discriminative Middle Level Features. International Conference on Pattern Recognition (ICPR), 2012, oral

Prior to 2012
  • Yu Kong, Xiaoqin Zhang, Weiming Hu, Yunde Jia. Adaptive Learning Codebook for Action Recognition. Pattern Recognition Letters. 32 (2011) pp. 1178- 1186. 

  • Zhen Dong, Yu Kong, Cuiwei Liu, Yunde Jia. Recognizing Human Interaction by Multiple Features. Asian Conference on Pattern Recognition (ACPR), 2011. [PDF]

  • Yu Kong, Xiaoqin Zhang, Weiming Hu, Yunde Jia. Learning Human Action with an Adaptive Codebook. International Conference on Virtual Systems and Multimedia (VSMM), 2010.6. invited paper [PDF]

  • Qingdi Wei, Xiaoqin Zhang, Yu Kong, Weiming Hu, and Haibin Ling. Compact Visual Codebook for Action Recognition. International Conference on Image Processing (ICIP), 2010. [PDF]

  • Xiaoqin Zhang, Weiming Hu, Xiangyang Wang, Yu Kong, Nianhua Xie, Hanzi Wang. A Swarm Intelligence Based Searching Strategy for Articulated 3D Human Body Tracking. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR), 2010. 

  • Yu Kong, Weiming Hu, Xiaoqin Zhang, Hanzi Wang, Yunde Jia. Learning Group Activity in Soccer Videos from Local Motion. Asian Conference on Computer Vision (ACCV), 2009.9, oral, 36 out of 670. [PDF]

  • Qingdi Wei, Xiaoqin Zhang, Yu Kong, Weiming Hu, and Haibin Ling. Group Action Recognition Using Space-Time Interest Points. International Symposium on Visual Computing (ISVC), 2009. 

  • Yu Kong, Xiaoqin Zhang, Qingdi Wei, Weiming Hu, Yunde Jia. Group Action Recognition in Soccer Videos. International Conference on Pattern Recognition (ICPR), 2008.12 [PDF]

Professional Services


  • IEEE Transaction on Multimedia
  • Neurocomputing
  • IEEE Transaction on Cybernetics
  • IEEE Transaction on Circuits and Systems for Video Technology
  • IEEE Transactions on Systems, Man, and Cybernetics 
  • Pattern Recognition Letters 
  • Journal of Visual Communication and Image Representation 
  • Journal of Software (in Chinese) 

External Reviewer

  • CVPR 2013, 2014
  • ECCV 2014
  • Multimedia 2012, 2014
  • BMVC 2012, 2014

        BIT-Interaction Dataset [NEW]

Last updated:April 8th, 2015