2014 December - Lamma Island

About

Welcome to the Video, Image, and Sound Analysis Lab (VISAL) at the City University of Hong Kong! The lab is directed by Dr. Antoni Chan in the Department of Computer Science.

Our main research activities include:

  • Computer Vision, Surveillance
  • Machine Learning, Pattern Recognition
  • Computer Audition, Music Information Retrieval
  • Eye Gaze Analysis

For more information about our current research, please visit the projects and publication pages.

Opportunities for graduate students and research assistants - if you are interested in joining the lab, please check this information.

New! A postdoc position is available with my collaborator at HKU — the project is about using machine learning to analyze eye gaze.

Latest News [more]

  • [Jun 28, 2016]

    Congratulations to Sijin for defending his thesis!

  • [Jun 25, 2016]

    Congratulations to Adeel for winning a “Best Research Paper Award 2013/14″ from the Higher Education Commission (HEC) of Pakistan for his TPAMI 2013 paper!

  • [Apr 26, 2016]

    Congratulations to Huy for defending his Thesis!

  • [Mar 18, 2016]

    Congratulations to Zheng for defending his thesis!

Recent Publications [more]

  • Counting People Crossing a Line using Integer Programming and Local Features.
    Zheng Ma and Antoni B. Chan,
    IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), to appear, 2016.
  • Information Distribution within Music Sequences.
    Antoni B. Chan and Janet H. Hsiao,
    Music Perception, to appear, 2016.
  • Mind reading: Discovering individual preferences from eye movements using switching hidden Markov models.
    Tim Chuk, Antoni B. Chan, Shinsuke (Shin) Shimojo, and Janet H. Hsiao,
    In: The Annual Meeting of the Cognitive Science Society (CogSci), Philadelphia, Aug 2016.
  • Analytic Eye Movement Patterns in Face Recognition are Associated with Better Performance and more Top-down Control of Visual Attention: an fMRI Study.
    Cynthia Y.H. Chan, J.J. Wong, Antoni B. Chan, Tatia M.C. Lee, and Janet H. Hsiao,
    In: The Annual Meeting of the Cognitive Science Society (CogSci), Philadelphia, Aug 2016.
  • Hidden Markov Modeling of eye movements with image information lead to better discovery of regions of interest.
    Stephan Brueggemann, Antoni B. Chan, and Janet H. Hsiao,
    In: The Annual Meeting of the Cognitive Science Society (CogSci), Philadelphia, Aug 2016.
  • Patternista: Learning Element Style Compatibility and Spatial Composition for Ring-based Layout Decoration.
    Quoc Huy Phan, Paul Asente, Jingwan Lu, Antoni B. Chan, and Hongbo Fu,
    In: Non-Photorealistic Animation and Rendering (Expressive) 2016, Lisbon, May 2016.
  • Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation.
    Sijin Li, Weichen Zhang, and Antoni B. Chan,
    In: Intl. Conf. on Computer Vision (ICCV):2848-2856, Santiago, Dec 2015. [spotlight video]
  • FlexyFont: Learning Transferring Rules for Flexible Typeface Synthesis.
    Quoc Huy Phan, Hongbo Fu, and Antoni B. Chan,
    Computer Graphics Forum (Proc. Pacific Graphics 2015), 34(7), Oct 2015. [video]
  • Hidden Markov model analysis reveals better eye movement strategies in face recognition.
    Tim Chuk, Antoni B. Chan, and Janet H. Hsiao,
    In: The Annual Meeting of the Cognitive Science Society (CogSci):393-398, Pasadena, Jul 2015.
  • Eye Movement Pattern in Face Recognition is Associated with Cognitive Decline in the Elderly.
    Cynthia Y.H. Chan, Antoni B. Chan, Tatia M.C. Lee, and Janet H. Hsiao,
    In: The Annual Meeting of the Cognitive Science Society (CogSci):321-326, Pasadena, Jul 2015.

Recent Project Pages [more]

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

We propose a maximum-margin structured learning framework with deep neural network that learns the image-pose score function for human pose estimation.

imgposeembed5
Small Instance Detection using Object Density Maps

We propose a novel object detection framework using object density maps for partially-occluded small instances, such as pedestrians in low resolution surveillance video.

videoImg_0045
Pose Estimation with Deep Convolutional Neural Network

We propose a heterogeneous multi-task learning framework for 2D human pose estimation from monocular images using a deep convolutional neural network that combines pose regression and part detection. We also extend the model to 3D human pose estimation.

deep-pose-conv-r1-for-demo