Welcome to Bin Zhao's Homepage

Basic Info

I am currently a Project Scientist in Prof. Eric Xing's group.

I received my Ph.D. degree in Machine Learning from Machine Learning Department, Carnegie Mellon Univ. in September 2014, under the supervision of Prof. Eric Xing. 

Before that, I received my B.Eng. degree from the Department of Automation, Tsinghua Univ. in 2006, and my M.Eng. degree from the Department of Automation, Tsinghua Univ. in 2009, under the supervision of Prof. Changshui Zhang.

My address:

8116 GHC, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA

My Email address: firstnamelastname@andrew.cmu.edu

 

Education

  • 2009-2014:     Carnegie Mellon University. Ph.D. in Machine Learning. September, 2014.
  • 2006-2009:     Tsinghua University. Master of Engineering in Automation. July, 2009 
  • 2002-2006:     Tsinghua University. Bachelor of Engineering in Automation. July 2006.                   

Research Interests

I’m broadly interested in areas where machine learning could help, especially computer vision and data mining. My research work is centered around designing, building and testing machine learning techniques for automatically exploring, understanding and compressing real world visual and textual data.

In the past few years, I have been working on ultra-large scale image classification, dynamic event detection and summarization of video streams, sparse coding, topic models, image segmentation, structured large margin method, semi-supervised learning, active learning, maximum margin clustering, and kernel learning.

Publications

2014

  1. Bin Zhao, Eric Xing. Quasi Real-Time Summarization for Consumer Videos. Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA, June 2014.
  2. Bin Zhao, Eric Xing. Hierarchical Feature Hashing for Fast Dimensionality Reduction. Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA, June 2014.

2013

  1. Bin Zhao, Eric Xing. Sparse Output Coding for Large-Scale Visual Recognition. Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR 2013), Portland, OR, USA, June 2013.
  2. Bin Zhao, Eric Xing. Structured Sparse Output Coding for Scalable Multi-Class ClassificationThe NIPS Workshop on Multi-Class and Multi-Label Learning with Millions of Categories (eXtreme Classification 2013), Lake Tahoe, NV, USA, December 2013.

2011

  1. Bin Zhao, Li Fei-Fei, Eric Xing. Large-Scale Category Structure Aware Image Categorization. Proceedings of the 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), Sierra Nevada, Spain, December 2011.
  2. Bin Zhao, Li Fei-Fei, Eric Xing. Online Detection of Unusual Events in Videos via Dynamic Sparse Coding. Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs, CO, USA, June 2011. [video]
  3. Bin Zhao, Xiaoxin Yin, Eric Xing. Max Margin Learning on Domain-Independent Web Information Extraction. Proceedings of the 20th ACM Conference on Information and Knowledge Management (CIKM 2011), Glaskow, UK, October 2011.
  4. Fei WangBin Zhao, Changshui Zhang. Unsupervised Large Margin Discriminative ProjectionIEEE Transactions on Neural Networks (TNN). 2011.

2010

  1. Bin Zhao, Li Fei-Fei, Eric Xing. Image Segmentation with Topic Random Fields. Proceedings of the 11th European Conference on Computer Vision (ECCV 2010).
  2. Fei Wang, Bin Zhao, Changshui Zhang. Linear Time Maximum Margin Clustering. IEEE Transactions on Neural Networks (TNN). vol. 21, no.2. 319-332. 2010.

2009

  1. Bin Zhao, James Kwok, Changshui Zhang. Maximum Margin Clustering with Multivariate Loss Function. Proceedings of the 9th IEEE International Conference on Data Mining (ICDM 09), Maimi, FL, USA, 2009.
    Acceptance rate: 70/786 = 8.91%
  2. Bin Zhao, Changshui Zhang. Compressed Spectral Clustering. ICDM workshop on Large-scale Data Mining: Theory and Applications (LDMTA 09), Miami, FL, USA, 2009.
  3. Bin Zhao, James Kwok, Fei Wang, Changshui Zhang. Unsupervised maximum margin feature selection with manifold regularization. The International Conference on Computer Vision and Pattern Recognition (CVPR 09), Miami, FL, USA, June 2009. [pdf]Acceptance rate: 383/1464 = 26.16%
  4. Bin Zhao, James Kwok, Changshui Zhang. Multiple Kernel Clustering. The 9th SIAM International Conference on Data Mining (SDM 09). Sparks, Nevada. April 2009. [pdf]
  5. Bin Zhao, Fei Wang, Changshui Zhang. Block Quantized Support Vector Ordinal Regression. IEEE Transactions on Neural Networks (TNN). vol.20, no.5. 882-890. 2009.

2008

  1. Bin Zhao, Fei Wang, Changshui Zhang. Maximum Margin Embedding. Proceedings of the 8th IEEE International Conference on Data Mining (ICDM 08), Pisa, Italy. 2008. [pdf]
    Acceptance rate: 144/724 = 19.89%
  2. Bin Zhao, Fei Wang, Changshui Zhang. CutS3VM: A Fast Semi-Supervised SVM Algorithm. The 14th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 08). Las Vegas, Nevada. 2008. pp. 830-838. [pdf]
    Acceptance rate: 50/500 = 10%
  3. Bin Zhao, Fei Wang, Changshui Zhang. Efficient Multiclass Maximum Margin Clustering. The 25th International Conference on Machine Learning (ICML 08). Helsinki, Finland. 2008. pp. 1248-1255. [pdf]
    Acceptance rate: 155/583 = 26.59%
  4. Bin Zhao, Fei Wang, Changshui Zhang. Efficient Maximum Margin Clustering Via Cutting Plane Algorithm. The 8th SIAM International Conference on Data Mining (SDM 08). Hyatt Regency Hotel, Atlanta, Georgia. 2008. pp. 751-762. (ORAL) [pdf][slides]
    Acceptance rate: 40/282 = 14.18%
  5. Bin Zhao, Fei Wang, Changshui Zhang, Yangqiu Song. Active Model Selection for Graph Based Semi-Supervised Learning. The 33rd International Conference on Acoustics, Speech, and Signal Processing (ICASSP 08), Las Vegas, Nevada. 2008. pp. 1881-1884.(ORAL) [pdf]

2007

  1. Bin Zhao, Fei Wang, Changshui Zhang. Smoothness Maximization via Gradient Descents. The 32nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP 07), Honolulu, Hawaii, 2007. pp. II-609-II-612. [pdf][poster]

Teaching

Machine Learning (CMU 10-701), TA for Prof. Eric Xing, Fall 2011
Machine Learning with Large Datasets (CMU 10-605), TA for Prof. William Cohen, Spring 2013

Code

We provide the Matlab code for Cutting Plane Maximum Margin Clustering (CPMMC).

Services

Program Committee of ICML 2014, ICML 2015. Reviewer for ICCV 2013, ECCV 2014, CVPR 2015. Reviewer for IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Parallel and Distributed Systems (TPDS), Pattern Recognition (PR), Data Mining and Knowledge Discovery (DMKD).

References

Available upon request.