Chen Change Loy B.Eng. Ph.D. MIEEE

Chen Change Loy

Post-doctoral Researcher

Vision Semantics Limited
Queen Mary Uni. of London
Mile End Rd., London E1 4NS

ccloy at visionsemantics com
ccloy at eecs qmul ac uk

I am a post-doctoral researcher with Vision Semantics Limited at Queen Mary University of London. I am currently working on the GETAWAY EU FP7 project. Previously I worked on the SAMURAI EU FP7 project with Prof. Shaogang Gong and Dr. Tao Xiang.

I received my PhD in Computer Science in December 2010 from the Queen Mary University of London. My PhD thesis is titled 'Activity Understanding and Unusual Event Detection in Surveillance Videos'.

My research interests include computer vision and machine learning, particularly in video analysis, active learning, random forest, non-parametric Bayesian models, and probabilistic graphical models.

Full publication list

Google scholar profile

Recent Publication

Stream-based Joint Exploration-Exploitation Active Learning, CVPR 2012, Oral presentation
Learning from streams of evolving and unbounded data is an important problem, for example in visual surveillance or internet scale data. For such large and evolving real- world data, exhaustive supervision is impractical, particularly so when the full space of classes is not known in advance therefore joint class discovery (exploration) and boundary learning (exploitation) becomes critical. Active learning has shown promise in jointly optimising exploration-exploitation with minimal human supervision. However, existing active learning methods either rely on heuristic multi-criteria weighting or are limited to batch processing. In this paper, we present a new unified framework for joint exploration-exploitation active learning in streams without any heuristic weighting. Extensive evaluation on classification of various image and surveillance video datasets demonstrates the superiority of our framework over existing methods.
PDF
Incremental Activity Modelling in Multiple Disjoint Cameras, TPAMI 2012
Activity modelling and unusual event detection in a network of cameras is challenging particularly when the camera views are not overlapped. We show that it is possible to detect unusual events in multiple disjoint cameras as context-incoherent patterns, through incremental learning of time delayed dependencies between distributed local activities observed within and across camera views. Specifically, we model multi-camera activities using a Time Delayed Probabilistic Graphical Model (TD-PGM) with different nodes representing activities in different decomposed regions from different views and the directed links between nodes encoding their time delayed dependencies. To deal with visual context changes, we formulate an incremental learning method for modelling time delayed dependencies that change over time. We validate the effectiveness of the proposed approach using a synthetic dataset and videos captured from a camera network installed at a busy underground station.
DOI PDF
Salient Motion Detection in Crowded Scenes, ISCCSP 2012
To reduce cognitive overload in CCTV monitoring, it is critical to have an automated way to focus the attention of operators on interesting events taking place in crowded public scenes. Motion saliency detection is pre-attentive stage in crowded scene analysis. We present a global motion saliency detection method based on spectral analysis, which aims to discover and localise interesting regions, of which the flows are salient in relation to the dominant crowd flows. The method is fast and does not rely on prior knowledge specific to a scene and any training videos. We demonstrate its potential on public scene videos, with applications in salient action detection, counter flow detection, and unstable crowd flow detection.
PDF

About Me

Education

  1. Ph.D. Computer Science, Queen Mary University of London, 2010
    Thesis: Activity Understanding and Unusual Event Detection in Surveillance Videos
    Advisors: Dr. Tao Xiang and Prof. Shaogang Gong
    Examiners: Prof. Tim Ellis and Dr. Gabriel Brostow
  2. B.Eng. Electronic Engineering (1st class honours), University of Science Malaysia, 2005
    Thesis: A Pressure-based Typing Biometrics System for User Authentication
    Advisor: Prof. Chee Peng Lim

Professional Experience

  1. Vision Semantics Limited, United Kingdom
    Postdoctoral Researcher, Jan 2012-Present
    Projects: GETAWAY
  2. Queen Mary University of London, United Kingdom
    Postdoctoral Researcher, Dec 2010-Dec 2011
    Projects: SAMURAI
  3. MIMOS Berhad, Malaysia
    Researcher, Jul 2007-Aug 2007
    Associate Researcher, May 2005-Jul 2007
    Research Assistant, Mar 2004-May 2004

Services and Activities

Conference Reviewer

  • ICCV, BMVC, AVSS, ICPR

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Journal of Machine Learning Research
  • IEEE Transactions on Image Processing
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Pattern Recognition
  • Image and Vision Computing
  • Information Fusion Journal
  • Signal Processing
  • The Computer Journal
  • International Journal of Computational Intelligence Studies
  • Journal of Intelligent and Fuzzy Systems

Honours and Awards

  • Full Ph.D. research studentship award by Queen Mary University of London, 2007-2010
  • International conference travel bursary (awarded by IEEE PAMI), 2009
  • International conference travel bursary (awarded by BMVA), 2009
  • Gold medal award, The 34th International Exhibition of Inventions, New Techniques and Products of Geneva, 2006
  • Gold medal award, Malaysia Public Institutions of Higher Learning R&D Expo, 2005
  • Special award for ICT cluster, Malaysia Public Institutions of Higher Learning R&D Expo, 2005
  • Honorary mention, National Instruments ASEAN Virtual Instrumentation Applications Contest, 2005 PDF
  • Hall of fame award, product research category, University of Science Malaysia, 2005-2006
  • Gold medal award, the best final year student in the field of Electronic Engineering, University of Science Malaysia (awarded by Intel), 2005
  • Dean's list for academic excellence, University of Science Malaysia, 2001-2005
  • Undergraduate scholarship by National Higher Education Fund Corporation, 2001-2005

Publication

Active Learning

  1. Stream-based Joint Exploration-Exploitation Active Learning
    C. C. Loy, T. M. Hospedales, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
    * Oral presentation
     PDF
  2. Stream-based Active Unusual Event Detection
    C. C. Loy, T. Xiang, and S. Gong
    Asian Conference on Computer Vision, Queenstown, New Zealand, 2010 (ACCV 2010)
    * Oral presentation
    PDF

Video Analysis

  1. Incremental Activity Modelling in Multiple Disjoint Cameras
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2012)
     DOI PDF
  2. Salient Motion Detection in Crowded Scenes
    C. C. Loy, T. Xiang, and S. Gong
    International Symposium on Communications, Control and Signal Processing (ISCCSP 2012)
     PDF
  3. Security and Surveillance
    S. Gong, C. C. Loy, and T. Xiang
    In T. Moeslund, A. Hilton, V. Krueger, L. Sigal (Eds.),
    Visual Analysis of Humans: Looking at People, Springer, 2011
    DOI PDF
  4. Activity Understanding and Unusual Event Detection in Surveillance Videos
    C. C. Loy
    PhD Thesis, Queen Mary University of London, 2010
     PDF
  5. Detecting and Discriminating Behavioural Anomalies
    C. C. Loy, T. Xiang, and S. Gong
    Pattern Recognition 2011(PR 2011)
    DOI PDF
  6. Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding
    C. C. Loy, T. Xiang, and S. Gong
    International Journal of Computer Vision, 2010 (IJCV 2010)
     DOI PDF
  7. Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
    C. C. Loy, T. Xiang, and S. Gong
    International Conference on Computer Vision, Kyoto, Japan, 2009 (ICCV 2009)
    * Oral presentation
    PDF
  8. Modelling Multi-object Activity by Gaussian Processes
    C. C. Loy, T. Xiang, and S. Gong
    British Machine Vision Conference, London, United Kingdom, 2009 (BMVC 2009)
    PDF Extended Abstract Poster
  9. Surveillance Video Behaviour Profiling and Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    Society of Photo-Optical Instrumentation Engineers Conference Series, 2009
  10. Multi-Camera Activity Correlation Analysis
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009 (CVPR 2009)
    * Oral presentation
    PDF
  11. From Local Temporal Correlation to Global Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    International Workshop on Machine Learning for Vision-based Motion Analysis, Marseille, France, 2008

Typing Biometrics / Keystroke Dynamics

  1. Authenticating the Identity of Computer Users with Typing Biometrics and the Fuzzy Min-Max Neural Network
    A. Quteishat, C. P. Lim, C. C. Loy, and W. K. Lai
    Special Issue on Biometrics and Its Applications, International Journal of Biomedical Soft Computing and Human Sciences, 2008
    PDF
  2. Keystroke Patterns Classification using the ARTMAP-FD Neural Network
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Taiwan, 2007 (IIHMSP 2007)
    PDF
  3. Pressure-based Typing Biometrics User Authentication Using The Fuzzy ARTMAP Neural Network
    C. C. Loy, C. P. Lim, and W. K. Lai
    International Conference on Neural Information Processing, Taiwan, 2005 (ICONIP 2005)
    PDF
  4. Classification of Computer System Users through Keystroke Dynamics
    C. C. Loy, I. Hanum, C. P. Lim, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, 2005

Others - Data Mining, Pattern Recognition

  1. Robust Modular ARTMAP for Multi-Class Shape Recognition
    C. P. Tan, C. C. Loy, W. K. Lai, and C. P. Lim
    IEEE International Joint Conference on Neural Networks, Hong Kong, 2008 (IJCNN 2008)
  2. Modular ARTMAP for Multi-Class Pattern Recognition
    C. C. Loy, C. P. Tan, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, 2007
  3. Use of Circle-Segments as a Data Visualization Technique for Feature Selection in Pattern Classification
    S. L. Wang, C. C. Loy, C. P. Lim, W. K. Lai, and K. S. Tan
    International Conference on Neural Information Processing, Japan, 2007 (ICONIP 2007)
    PDF
  4. Needle in a Data Haystack: Finding Similarities in High-Dimensional Data
    W. K. Lai, A. Z. Fatimah, and C. C. Loy
    MIMOS Symposium on ICT & Microelectronics, 2006
  5. Investigation into the Use of N-grams for Ovarian Cancer Identification
    Z. Z. Sharifah, C. C. Loy, S. Y. Tai, and W. K. Lai
    International Conference of Artificial Intelligence in Engineering and Technology, 2006
  6. Dimensionality Reduction of Protein Mass Spectrometry Data Using Random Projection
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Neural Information Processing, Hong Kong, 2006 (ICONIP 2006)
    PDF

Thesis

  1. Activity Understanding and Unusual Event Detection in Surveillance Videos
    C. C. Loy
    PhD Thesis, Queen Mary University of London, 2010
    PDF

Book Chapter

  1. Security and Surveillance
    S. Gong, C. C. Loy, and T. Xiang
    In T. Moeslund, A. Hilton, V. Krueger, L. Sigal (Eds.),
    Visual Analysis of Humans: Looking at People, Springer, 2011
    DOI PDF

Journal

  1. Incremental Activity Modelling in Multiple Disjoint Cameras
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2012)
     DOI PDF
  2. Detecting and Discriminating Behavioural Anomalies
    C. C. Loy, T. Xiang, and S. Gong
    Pattern Recognition 2011(PR 2011)
    DOI PDF
  3. Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding
    C. C. Loy, T. Xiang, and S. Gong
    International Journal of Computer Vision, 2010 (IJCV 2010)
     DOI PDF
  4. Authenticating the Identity of Computer Users with Typing Biometrics and the Fuzzy Min-Max Neural Network
    A. Quteishat, C. P. Lim, C. C. Loy, and W. K. Lai
    Special Issue on Biometrics and Its Applications, International Journal of Biomedical Soft Computing and Human Sciences, 2008
    PDF

Conference

  1. Stream-based Joint Exploration-Exploitation Active Learning
    C. C. Loy, T. M. Hospedales, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
    * Oral presentation
    PDF
  2. Stream-based Active Unusual Event Detection
    C. C. Loy, T. Xiang, and S. Gong
    Asian Conference on Computer Vision, Queenstown, New Zealand, 2010 (ACCV 2010)
    * Oral presentation
     PDF
  3. Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
    C. C. Loy, T. Xiang, and S. Gong
    International Conference on Computer Vision, Kyoto, Japan, 2009 (ICCV 2009)
    * Oral presentation
     PDF
  4. Modelling Multi-object Activity by Gaussian Processes
    C. C. Loy, T. Xiang, and S. Gong
    British Machine Vision Conference, London, United Kingdom, 2009 (BMVC 2009)
    PDF Extended Abstract Poster
  5. Multi-Camera Activity Correlation Analysis
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009 (CVPR 2009)
    * Oral presentation
     PDF
  6. Robust Modular ARTMAP for Multi-Class Shape Recognition
    C. P. Tan, C. C. Loy, W. K. Lai, and C. P. Lim
    IEEE International Joint Conference on Neural Networks, Hong Kong, 2008 (IJCNN 2008)
  7. Keystroke Patterns Classification using the ARTMAP-FD Neural Network
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Taiwan, 2007 (IIHMSP 2007)
    PDF
  8. Use of Circle-Segments as a Data Visualization Technique for Feature Selection in Pattern Classification
    S. L. Wang, C. C. Loy, C. P. Lim, W. K. Lai, and K. S. Tan
    International Conference on Neural Information Processing, Japan, 2007 (ICONIP 2007)
    PDF
  9. Investigation into the Use of N-grams for Ovarian Cancer Identification
    Z. Z. Sharifah, C. C. Loy, S. Y. Tai, and W. K. Lai
    International Conference of Artificial Intelligence in Engineering and Technology, 2006
  10. Dimensionality Reduction of Protein Mass Spectrometry Data Using Random Projection
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Neural Information Processing, Hong Kong, 2006 (ICONIP 2006)
    PDF
  11. Pressure-based Typing Biometrics User Authentication Using The Fuzzy ARTMAP Neural Network
    C. C. Loy, C. P. Lim, and W. K. Lai
    International Conference on Neural Information Processing, Taiwan, 2005 (ICONIP 2005)
    PDF

Workshop

  1. Salient Motion Detection in Crowded Scenes
    C. C. Loy, T. Xiang, and S. Gong
    International Symposium on Communications, Control and Signal Processing (ISCCSP 2012)
     PDF
  2. Surveillance Video Behaviour Profiling and Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    Society of Photo-Optical Instrumentation Engineers Conference Series, 2009
  3. From Local Temporal Correlation to Global Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    International Workshop on Machine Learning for Vision-based Motion Analysis, Marseille, France, 2008
  4. Modular ARTMAP for Multi-Class Pattern Recognition
    C. C. Loy, C. P. Tan, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, December 2007
  5. Needle in a Data Haystack: Finding Similarities in High-Dimensional Data
    W. K. Lai, A. Z. Fatimah, and C. C. Loy
    MIMOS Symposium on ICT & Microelectronics, 2006
  6. Classification of Computer System Users through Keystroke Dynamics
    C. C. Loy, I. Hanum, C. P. Lim, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, 2005

2012

  1. Stream-based Joint Exploration-Exploitation Active Learning
    C. C. Loy, T. M. Hospedales, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
    * Oral presentation
     PDF
  2. Incremental Activity Modelling in Multiple Disjoint Cameras
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2012)
     DOI PDF
  3. Salient Motion Detection in Crowded Scenes
    C. C. Loy, T. Xiang, and S. Gong
    International Symposium on Communications, Control and Signal Processing (ISCCSP 2012)
     PDF

2011

  1. Security and Surveillance
    S. Gong, C. C. Loy, and T. Xiang
    In T. Moeslund, A. Hilton, V. Krueger, L. Sigal (Eds.),
    Visual Analysis of Humans: Looking at People, Springer, 2011
    DOI PDF
  2. Detecting and Discriminating Behavioural Anomalies
    C. C. Loy, T. Xiang, and S. Gong
    Pattern Recognition 2011(PR 2011)
    DOI PDF

2010

  1. Activity Understanding and Unusual Event Detection in Surveillance Videos
    C. C. Loy
    PhD Thesis, Queen Mary University of London, 2010
     PDF
  2. Stream-based Active Unusual Event Detection
    C. C. Loy, T. Xiang, and S. Gong
    Asian Conference on Computer Vision, Queenstown, New Zealand, 2010 (ACCV 2010)
    * Oral presentation
     PDF
  3. Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding
    C. C. Loy, T. Xiang, and S. Gong
    International Journal of Computer Vision, 2010 (IJCV 2010)
     DOI PDF

2009

  1. Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
    C. C. Loy, T. Xiang, and S. Gong
    International Conference on Computer Vision, Kyoto, Japan, 2009 (ICCV 2009)
    * Oral presentation
     PDF
  2. Modelling Multi-object Activity by Gaussian Processes
    C. C. Loy, T. Xiang, and S. Gong
    British Machine Vision Conference, London, United Kingdom, 2009 (BMVC 2009)
    PDF Extended Abstract Poster
  3. Surveillance Video Behaviour Profiling and Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    Society of Photo-Optical Instrumentation Engineers Conference Series, 2009
  4. Multi-Camera Activity Correlation Analysis
    C. C. Loy, T. Xiang, and S. Gong
    IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009 (CVPR 2009)
    * Oral presentation
     PDF

2008

  1. From Local Temporal Correlation to Global Anomaly Detection
    C. C. Loy, T. Xiang, and S. Gong
    International Workshop on Machine Learning for Vision-based Motion Analysis, Marseille, France, 2008
  2. Authenticating the Identity of Computer Users with Typing Biometrics and the Fuzzy Min-Max Neural Network
    A. Quteishat, C. P. Lim, C. C. Loy, and W. K. Lai
    Special Issue on Biometrics and Its Applications, International Journal of Biomedical Soft Computing and Human Sciences, 2008
    PDF
  3. Robust Modular ARTMAP for Multi-Class Shape Recognition
    C. P. Tan, C. C. Loy, W. K. Lai, and C. P. Lim
    IEEE International Joint Conference on Neural Networks, Hong Kong, 2008 (IJCNN 2008)

2007

  1. Modular ARTMAP for Multi-Class Pattern Recognition
    C. C. Loy, C. P. Tan, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, 2007
  2. Keystroke Patterns Classification using the ARTMAP-FD Neural Network
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Taiwan, 2007 (IIHMSP 2007)
    PDF
  3. Use of Circle-Segments as a Data Visualization Technique for Feature Selection in Pattern Classification
    S. L. Wang, C. C. Loy, C. P. Lim, W. K. Lai, and K. S. Tan
    International Conference on Neural Information Processing, Japan, 2007 (ICONIP 2007)
    PDF

2006

  1. Needle in a Data Haystack: Finding Similarities in High-Dimensional Data
    W. K. Lai, A. Z. Fatimah, and C. C. Loy
    MIMOS Symposium on ICT & Microelectronics, 2006
  2. Investigation into the Use of N-grams for Ovarian Cancer Identification
    Z. Z. Sharifah, C. C. Loy, S. Y. Tai, and W. K. Lai
    International Conference of Artificial Intelligence in Engineering and Technology, 2006
  3. Dimensionality Reduction of Protein Mass Spectrometry Data Using Random Projection
    C. C. Loy, W. K. Lai, and C. P. Lim
    International Conference on Neural Information Processing, Hong Kong, 2006 (ICONIP 2006)
    PDF

2005

  1. Pressure-based Typing Biometrics User Authentication Using The Fuzzy ARTMAP Neural Network
    C. C. Loy, C. P. Lim, and W. K. Lai
    International Conference on Neural Information Processing, Taiwan, 2005 (ICONIP 2005)
    PDF
  2. Classification of Computer System Users through Keystroke Dynamics
    C. C. Loy, I. Hanum, C. P. Lim, W. K. Lai
    MIMOS Symposium on ICT & Microelectronics, 2005

Download datasets, codes

Datasets

Name Description
QMUL Junction Dataset

A busy traffic dataset for research on activity analysis and behaviour understanding. Details ...

Download

Keystroke100 Dataset

A pressure-sensitive keystroke dynamics dataset for research on keystroke dynamics and typing biometrics. Details ...

Download

Codes

Name Description
Time Delayed Mutual Information

MATLAB code for computing time delayed mutual information (TDMI) between time series.

Time Delayed Mutual Information analysis is employed in our work for learning pairwise time delayed association between regional activity patterns in a multi-camera network.

Reference:
C. C. Loy, T. Xiang, and S. Gong, Incremental Activity Modelling in Multiple Disjoint Cameras, TPAMI 2012

Download Codes [16 KB]

Cross Canonical Correlation Analysis

MATLAB code for computing cross canonical correlation (xCCA) between time series.

Reference:
C. C. Loy, T. Xiang, and S. Gong, Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding, IJCV 2010

Download Codes [15 KB]

Scene Segmentation

MATLAB code for segmenting a scene into regions based on activity patterns. C++ codes for spectral clustering by L. Zelnik-Manor and P. Perona are included.

Reference:
C. C. Loy, T. Xiang, and S. Gong, Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding, IJCV 2010

Download Codes + Data [7.8 MB]

Background Subtraction

MATLAB and C++ codes for background modelling and subtraction.

A mean-shift based background subtraction for robust background subtraction in video with sudden global intensity change. A static background image is first generated based on minimum cut, the method then adapts the background image to the intensity level of current frame prior to actual background subtraction.

Reference:
C. C. Loy, T. Xiang, and S. Gong, Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding, IJCV 2010

Download Codes [50 KB] Download Testing Data [13 MB]