Research

Gary's research interests include:
  • Digital Geometry Processing
  • Data Analysis and Visualization
  • Information Retrieval and Indexing
  • Pattern Recognition
He has broad interests in developing and applying graphics, visualization, vision and optimization techniques to multi-dimensional data analysis. This data includes, but not limited to, collection of 2D images, 3D face image sequences, 3D motion capture data, 3D models with rigid / non-rigid deformation, and 4D geometry sequences.



 Current Interests and Highlights

 Gary K.L. Tam, Vivek Kothari and M. Chen, "An Analysis of Machine- and Human-Analytics in Classification", IEEE Transactions on Visualization and Computer Graphics, 23(1):71-80, 2017.
[Accepted to VIS 2016, Best paper award in VAST section]
[IEEE Computing Now: Snapshot of Current Trends in Visualization (Honourably mentioned in Feb 2017 issue)]
[PDF(PostPrint) / URL / DOI] [Fast Forward Video (Music and Voice Over)]

In this work, we present a study that traces the technical and cognitive processes in two visual analytics applications to a common theoretic model of soft knowledge that may be added into a visual analytics process for constructing a decision-tree model. Both case studies involved the development of classification models based on the “bag of features” approach...



David Pickup et al., "Shape Retrieval of Non-rigid 3D Human Models" International Journal of Computer Vision, 120(2):169–193, 2016. [URL / DOI]

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks...


 
Robert Palmer, Xianghua Xie and Gary K.L. Tam, "Automatic Aortic Root Segmentation with Shape Constraints and Mesh Regularisation", Proc. British Machine Vision Conference (BMVC), September 2015. [URL / DOI]

Fully automated 3D segmentation is not only challenging due to, for instance, ambiguities in appearance, but it is also computationally demanding. We present a fully automatic, learning-based deformable modelling method for segmenting the aortic root in CT images using a two-stage mesh deformation...




Gary K.L. Tam, Ralph MartinP.L. Rosin and Yu-Kun Lai, "An Efficient Approach to Correspondences between Multiple Non-Rigid Parts",  Computer Graphics Forum, 33(5):137-146, 2014.
 [PDF(PostPrint)/DOI]

Identifying multiple deformable parts on meshes and establishing dense correspondences between them are tasks of fundamental importance to computer graphics, with applications to e.g. geometric edit propagation and texture transfer. Much research has considered establishing correspondences between non-rigid surfaces, but little work can both identify similar multiple deformable parts and handle partial shape correspondences. This paper addresses two related problems, treating them as a whole ...
 


Gary K.L. Tam, Ralph MartinP.L. Rosin and Yu-Kun Lai, "Diffusion Pruning for Rapidly and Robustly Selecting Global Correspondences using Local Isometry",  ACM Transactions on Graphics, 33(1):4, 2014.  [PDF(PostPrint)/Cover/DOI]

Finding correspondences between two surfaces is a fundamental operation in various applications in computer graphics and related fields. Candidate correspondences can be found by matching local signatures, but as they only consider local geometry, many are globally inconsistent. We provide a novel algorithm to prune a set of candidate correspondences to those most likely to be globally consistent. Our approach can handle ...





H. Fang, N.M. ParthaláinA.J AubreyGary KL TamR. BorgoP.L. RosinP.W. GrantD. MarshallM. Chen, "Facial expression recognition in dynamic sequences: An integrated approach", Pattern Recognition, 47(3):1271–1281, 2014. [PDF(PostPrint)/DOI]

Automatic facial expression analysis aims to analyse human facial expressions and classify them into discrete categories. Methods based on existing work are reliant on extracting information from video sequences and employ either some form of subjective thresholding of dynamic information or attempt to identify the particular individual frames in which the expected behaviour occurs...


H. Fang, Gary KL Tam, R. BorgoA.J Aubrey  P.W. Grant  P.L. Rosin  C. Wallraven, D. CunninghamD. Marshall and M. Chen, "Visualizing Natural Image Statistics", IEEE Transactions on Visualization and Computer Graphics, 19(7):1228-1241, 2013. [PDF(PostPrint)/DOI]

Natural image statistics is an important area of research in cognitive sciences and computer vision. Visualization of statistical results can help identify clusters and anomalies as well as analyze deviation, distribution and correlation. Furthermore, they can provide visual abstractions and symbolism for categorized data. In this...




Gary K.L. Tam, Zhi-Quan Cheng, Yu-Kun Lai, Frank Langbein, Yonghuai LiuD. Marshall, Ralph Martin, Xianfang SunP.L. Rosin, "Registration of 3D Point Clouds and Meshes: A Survey From Rigid to Non-Rigid", IEEE Transactions on Visualization and Computer Graphics, 19(7):1199-1217, 2013. [PDF(PostPrint)/DOI]

3D surface registration transforms multiple 3D datasets into the same coordinate system so as to align overlapping components of these sets. Recent surveys have covered different aspects of either rigid or non-rigid registration, but seldom discuss them as a whole. Our study serves two purposes:...



Gary K.L. Tam and Rynson Lau, "Embedding Retrieval of Articulated Geometry Models," IEEE Trans. on Pattern Analysis and Machine Intelligence, 34(11):2134-46, 2012. [PDF(PostPrint)/DOI] [Models Sequence] [Codes]

Due to the popularity of computer games and animation, research on 3D articulated geometry model retrieval is attracting a lot of attention in recent years. However, most existing works extract high dimensional features to represent models and suffer from practical limitations...










Gary K.L.  Tam, H. Fang, A.J Aubrey, P.W. Grant, P.L. Rosin, D. Marshall, M. Chen, "Visualization of Time‐Series Data in Parameter Space for Understanding Facial Dynamics," Computer Graphics Forum 30(3):901-910, 2011. [PDF(PostPrint)/DOI]

Over the past decade, computer scientists and psychologists have made great efforts to collect and analyze facial dynamics data that exhibit different expressions and emotions. Such data is commonly captured as videos and are transformed into feature-based time-series prior to any analysis...  




Gary K.L. Tam, Q. Zheng, M. Corbyn, Rynson Lau, "Motion Retrieval Based on Energy Morphing," IEEE International Symposium on Multimedia (ISM), pp.210-220, 2007. [PDF(PostPrint)/DOI]

Matching and retrieval of motion sequences has become an important research area in recent years, due to the increasing availability and popularity of motion capture data. The main challenge in matching two motion sequences is the diversity of the captured motions, ...



Gary K.L. Tam and Rynson Lau, "Deformable Model Retrieval Based on Topological and Geometric Signatures," IEEE Trans. on Visualization and Computer Graphics (TVCG), 13(3):470-482, May 2007. [PDF(PostPrint)/DOI]

With the increasing popularity of 3D applications such as computer games, a lot of 3D geometry models are being created. To encourage sharing and reuse, techniques that support matching and retrieval of these models are emerging. However, only a few of them can handle deformable models...






 

Gary K.L. Tam, Rynson Lau, and C.W. Ngo, "Deformable Geometry Model Matching by Topological and Geometric Signatures," Proc. International Conference on Pattern Recognition (ICPR), pp. 910-913, Aug. 2004. [PDF(PostPrint)/DOI]

In this paper, we present a novel method for efficient 3D model comparison. The method matches highly deformed models by comparing topological and geometric features. First, we propose 「Bi-directional LSD analysis」 to locate reliable topological points and rings...


 
Gary K.L. Tam, Rynson Lau, and C.W. Ngo, "Deformable Geometry Model Matching Using Bipartite Graph," Proc. Computer Graphics International (CGI), pp. 335-342, June 2004.  [PDF(PostPrint)/DOI]

In this paper, we present a novel method for efficient 3D model comparison. The method is designed to match highly deformed models through capturing two types of information. First, we propose a feature point extraction algorithm, which is based on 「Level Set Diagram」, ...