Search For:

Displaying 1-40 out of 40 total
Kernel Autoassociator with Applications to Visual Classification
Found in: Pattern Recognition, International Conference on
By Haihong Zhang, Weimin Huang, Zhiyong Huang, Bailing Zhang
Issue Date:August 2004
pp. 443-446
Autoassociator is an important issue in concept learning, and the learned concept of a particular class can be used to distinguish the class from the others. For nonlinear autoassociation, this paper presents a new model referred to as kernel autoassociato...
 
Kernel-Based Method for Tracking Objects with Rotation and Translation
Found in: Pattern Recognition, International Conference on
By Haihong Zhang, Zhiyong Huang, Weimin Huang, Liyuan Li
Issue Date:August 2004
pp. 728-731
This paper addresses the issue of tracking translation and rotation simultaneously. Starting with a kernel-based spatial-spectral model for object representation, we define an l₂-norm similarity measure between the target object and the observation, and de...
 
A 2D-3D Hybrid Approach to Video Stabilization
Found in: Computer-Aided Design and Computer Graphics, International Conference on
By Zhiyong Huang,Fazhi He,Xiantao Cai,Yuan Chen,Xiao Chen
Issue Date:September 2011
pp. 146-150
In this paper, we introduce a novel 2D-3D hybrid video stabilization method which combines virtues of 2D and 3D video stabilization methods in one routine. It attempts to achieve high-quality camera motions and to retain full frame coherence in each frame,...
 
Tennis Space: An Interactive and Immersive Environment for Tennis Simulation
Found in: Image and Graphics, International Conference on
By Shuhong Xu, Peng Song, Ching Ling Chin, Gim Guan Chua, Zhiyong Huang, Susanto Rahardja
Issue Date:September 2009
pp. 652-657
This paper reports the design and implementation of an interactive and immersive environment (IIE) for tennis simulation. The presented design layout, named Tennis Space, provides the necessary immersive experience without overly restricting the player. To...
 
An multiuser Undo/Redo method for replicated collaborative modeling systems
Found in: International Conference on Computer Supported Cooperative Work in Design
By Yuan Cheng, Fazhi He, Shuxu Jing, Zhiyong Huang
Issue Date:April 2009
pp. 185-190
Undo/Redo can help rolling the whole system back to some previous state. However, many group Undo/Redo researches are based on co-edit system of text object. This paper firstly addresses the Undo/Redo in 3D collaborative solid modeling system. After analys...
 
A maximum margin discriminative learning algorithm for temporal signals
Found in: Pattern Recognition, International Conference on
By Wenjie Xu, Jiankang Wu, Zhiyong Huang
Issue Date:August 2006
pp. 460-463
We propose a new maximum margin discriminative learning algorithm here for classification of temporal signals. It is superior to conventional HMM in the sense that it does not need prior knowledge of the data distribution. It learns the classifier by using...
 
Skyline Queries Against Mobile Lightweight Devices in MANETs
Found in: Data Engineering, International Conference on
By Zhiyong Huang, Christian S. Jensen, Hua Lu, Beng Chin Ooi
Issue Date:April 2006
pp. 66
Skyline queries are well suited when retrieving data according to multiple criteria. While most previous work has assumed a centralized setting this paper considers skyline querying in a mobile and distributed setting, where each mobile device is capable o...
 
Feature Combination and Relevance Feedback for 3D Model Retrieval
Found in: Multi-Media Modeling Conference, International
By Indriyati Atmosukarto, Wee Kheng Leow, Zhiyong Huang
Issue Date:January 2005
pp. 334-339
Retrieval of 3D models have attracted much research interest, and many types of shape features have been proposed. In this paper, we describe a novel approach of combining the feature types for 3D model retrieval and relevance feedback processing.Our appro...
 
The Hierarchical Degree-of-Visibility Tree
Found in: IEEE Transactions on Knowledge and Data Engineering
By Lidan Shou, Zhiyong Huang, Kian-Lee Tan
Issue Date:November 2004
pp. 1357-1369
In this paper, we present a novel structure called the Hierarchical Degree-of-Visibility Tree (HDoV-tree) for visibility query processing in visualization systems. The HDoV-tree builds on and extends the R-tree such that 1) the search space is pruned based...
 
Code Checking and Visualization of an Architecture Design
Found in: Visualization Conference, IEEE
By Rong Xu, Wawan Solihin, Zhiyong Huang
Issue Date:October 2004
pp. 10p
No summary available.
   
Fast Rendering of Foveated Volume in the Wavelet Domain
Found in: Visualization Conference, IEEE
By Hang Yu, Ee-Chien Chang, Zhiyong Huang, Zhijian Zheng
Issue Date:October 2004
pp. 26p
No summary available.
   
An Adaptive Sampling Method for Layered Depth Image
Found in: Computer Graphics International Conference
By Ravinder Namboori, Hung Chuan Teh, Zhiyong Huang
Issue Date:June 2004
pp. 206-213
Sampling issue is an important problem in image based rendering. In this paper, we propose an adaptive sampling method to improve the Layered Depth Image framework. Different from the existing methods of interpolating or splatting neighboring pixels, our m...
 
An Implementation of a Game Engine for Air Combat Simulation
Found in: Multi-Media Modeling Conference, International
By Jiong Gao, Zhiyong Huang
Issue Date:January 2004
pp. 365
No summary available.
   
Applying Speech Interface to Mahjong Game
Found in: Multi-Media Modeling Conference, International
By Jie Zhang, Ji Zhao, Shuanhu Bai, Zhiyong Huang
Issue Date:January 2004
pp. 86
Computer game development has raised many challenges to the computer science. Among of them, human computer interaction and networking are two fundamental aspects. We propose a multi-player game framework with a speech interface based on existing speech sy...
 
Decomposing Polygon Meshes by Means of Critical Points
Found in: Multi-Media Modeling Conference, International
By Yinan Zhou, Zhiyong Huang
Issue Date:January 2004
pp. 187
Polygon mesh is among the most common data structures used for representing objects in computer graphics. Unfortunately, a polygon mesh does not capture high-level structures, unlike a hierarchical model. In general, high-level abstractions are useful for ...
 
An Enhanced Framework for Real-Time Hair Animation
Found in: Computer Graphics and Applications, Pacific Conference on
By Wenqi Liang, Zhiyong Huang
Issue Date:October 2003
pp. 467
Maximizing visual effect is a major problem in real-time animation. A real-time hair animation framework was proposed in [9, 10] based on 2D representation and texture mapping. One problem is that it lacks of the volumetric effect due to its 2D nature. Thi...
 
Non-Photorealistic Rendering and Content-Based Image Retrieval
Found in: Computer Graphics and Applications, Pacific Conference on
By Xiaowen Ji, Zoltan Kato, Zhiyong Huang
Issue Date:October 2003
pp. 153
In this paper, we will show how non-photorealistic rendering (NPR) can take a new role in content-based image retrieval (CBIR). The proposed CBIR method applies a novel image similarity measure: Unlike traditional features like color, texture, or shape, ou...
 
A Framework to Customize a Face Model for Reusing Animation
Found in: Computer Graphics International Conference
By Kaicheng Zhang, Zhiyong Huang, Tat-Seng Chua
Issue Date:July 2003
pp. 258
In this paper, we propose a framework to customize a face model for reusing animation. In this framework, two orthogonal photos of a human face are used as input. Based on them, a set of feature points is manually selected. Then, the existing face model wi...
 
3D Model Retrieval With Morphing-Based Geometric and Topological Feature Maps
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Meng Yu, Indriyati Atmosukarto, Wee Kheng Leow, Zhiyong Huang, Rong Xu
Issue Date:June 2003
pp. 656
Recent advancement in 3D digitization techniques have prompted to the need for 3D object retrieval. Our method of comparing 3D objects for retrieval is based on 3D morphing. It computes, for each 3D object, two spatial feature maps that describe the geomet...
 
HDoV-tree: The Structure, The Storage, The Speed
Found in: Data Engineering, International Conference on
By Lidan Shou, Zhiyong Huang, Kian-Lee Tan
Issue Date:March 2003
pp. 557
In a visualization system, one of the key issues is to optimize performance and visual fidelity. This is especially critical for large virtual environments where the models do not fit into the memory. In this paper, we present a novel structure called HDoV...
 
Augmenting SSEs with Structural Properties for Rapid Protein Structure Comparison
Found in: Bioinformatic and Bioengineering, IEEE International Symposium on
By Chern-Hooi Chionh, Zhiyong Huang, Kian-Lee Tan, Zhen Yao
Issue Date:March 2003
pp. 341
Comparing protein structures in three dimensions is a computationally expensive process that makes a full scan of a protein against a library of known protein structures impractical. To reduce the cost, we can use an approximation of the three dimensional ...
 
Design and Implementation of a WAP GIS Framework
Found in: Web Information Systems Engineering Workshops, International Conference on
By Yue Li, Zhong Xie, Zhiyong Huang
Issue Date:December 2002
pp. 81
WAP GIS is a mobile GIS service that gives us Geographic information, maps, and text at any time and anywhere when we need them. It broadens not only the WAP service contents but also the traditional GIS applications. This paper presents a design and imple...
 
Robust Invisible Watermarking of Volume Data Using the 3D DCT
Found in: Computer Graphics International Conference
By Yinghui Wu, Xin Guan, Mohan S. Kankanhalli, Zhiyong Huang
Issue Date:July 2001
pp. 0359
Abstract: In this paper, we propose a novel watermarking algorithm for 3D volume data based on the spread-spectrum communication technique which is invisible and robust.
 
Polygonizing Non-Uniformly Distributed 3D Points by Advancing Mesh Frontiers
Found in: Computer Graphics International Conference
By Indriyati Atmosukarto, Luping Zhou, Wee Kheng Leow, Zhiyong Huang
Issue Date:July 2001
pp. 0175
Abstract: 3D digitization devices produce very large sets of 3D points sampled from the surfaces of the objects being scanned. A mesh construction procedure needs to be applied to derive polygon mesh from the 3D point sets. As the 3D points derived from di...
 
Implementation of a Graphics Design Framework on the Web
Found in: Computer Graphics and Applications, Pacific Conference on
By Xiaoyan Xie, Hao Wang, Zhiyong Huang
Issue Date:October 2000
pp. 421
We propose a client-server graphics design framework and have implemented a room design system using CORBA. We have integrated technologies used in distributed computation (Java and CORBA) and computer graphics (VRML). To support multiuser collaborative de...
 
Mesh Construction from Non-Uniformly Distributed and Noisy 3D Points Recovered from Image Sequence
Found in: Computer Graphics and Applications, Pacific Conference on
By Indriyati Atmosukarto, Wee Kheng Leow, Zhiyong Huang, Yong Zhang, Kah Kay Sung
Issue Date:October 2000
pp. 423
This paper describes a novel method for constructing triangle meshes from noisy and non-uniformly distributed 3D points. It consists of two steps. (1) Noise point removal uses clustering algorithm and epipolar constraint method to identify and remove noise...
 
Rapid 3D Model Acquisition from Images of Small Objects
Found in: Geometric Modeling and Processing
By Wee Kheng Leow, Zhiyong Huang, Yong Zhang, Rudy Setiono
Issue Date:April 2000
pp. 33
This paper describes a system for rapid acquisition of 3D models of objects for use in applications such as CAD and VR. The system consists of an image capturing platform, which comprises a PC-controlled turntable and CCD camera, and associated computer vi...
 
An Animation Interface Designed for Motion Capture
Found in: Computer Animation
By Tom Molet, Zhiyong Huang, Ronan Boulic, Daniel Thalmann
Issue Date:June 1997
pp. 77
We present an animation interface designed to conveniently control the motion capture process. The transition of performer's hand gestures tracked by a dataglove is recognized for software remote control. An intuitive camera metaphor allows to specify the ...
 
Affine Object Tracking with Kernel-Based Spatial-Color Representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Haihong Zhang, Weimin Huang, Zhiyong Huang, Liyuan Li
Issue Date:June 2005
pp. 293-300
This paper presents a new visual tracking method that can achieve accurate estimation of affine transformation and precise spatial-color representation. The estimation of transformation provides more information than translation for better motion understan...
 
gHull: A GPU algorithm for 3D convex hull
Found in: ACM Transactions on Mathematical Software (TOMS)
By Ashwin Nanjappa, Mingcen Gao, Thanh-Tung Cao, Tiow-Seng Tan, Zhiyong Huang
Issue Date:September 2013
pp. 1-19
A novel algorithm is presented to compute the convex hull of a point set in ℝ3 using the graphics processing unit (GPU). By exploiting the relationship between the Voronoi diagram and the convex hull, the algorithm derives the approximation of the c...
     
A hybrid method for video stabilization and retargeting
Found in: Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service (ICIMCS '13)
By JingJing Zhang, QiuHong Zhang, ZhiYong Huang
Issue Date:August 2013
pp. 46-51
Both video stabilization and retargeting are important post processing techniques for film production. In many cases, we need to stabilize the shaky handhold video and adapt it to target displays with different resolutions and aspect ratios. Video stabiliz...
     
Towards more engaging telepresence by face tracking
Found in: Proceedings of the Workshop at SIGGRAPH Asia (WASA '12)
By Keng Peng Tee, Liyuan Li, Rui Yan, Yuanwei Chua, Zhiyong Huang
Issue Date:November 2012
pp. 137-141
Video conferencing is widely used with the growing popularity of Internet call systems such as FaceTime, Skype and broad band network. However, people still find it unnatural compared to face-to-face talk. One of the problems is that the display screen and...
     
Face replacement in video from a single image
Found in: SIGGRAPH Asia 2012 Posters (SA '12)
By Arthur Niswar, Ee Ping Ong, Zhiyong Huang
Issue Date:November 2012
pp. 1-1
We present a novel system to replace the face in a video with the face of a different person from a single image, where the face is not limited to be in a specific pose, e.g. exactly frontal. There are some systems to replace the face in a video with the f...
     
Fast and automatic 3D full head synthesis using iPhone
Found in: SIGGRAPH Asia 2011 Sketches (SA '11)
By Ee Ping Ong, Hong Thai Nguyen, Zhiyong Huang
Issue Date:December 2011
pp. 1-2
3D full head synthesis (3DFHS) is of interest in many applications, including gaming and social networks. One well known related work is [Blanz and Vetter 1999] but it is only restricted to the synthesis of the face area (and not the head area). FaceGen [F...
     
Pose-invariant 3D face reconstruction from a single image
Found in: ACM SIGGRAPH ASIA 2010 Sketches (SA '10)
By Arthur Niswar, Ee Ping Ong, Zhiyong Huang
Issue Date:December 2010
pp. 1-2
This technical sketch presents a novel method to reconstruct 3D face model from only a single image. Different from other methods, ours does not require the face in the image to be in a specific pose. This method deforms a generic 3D face model to fit the ...
     
HVS based histogram adjustment for tone mapping
Found in: ACM SIGGRAPH ASIA 2009 Sketches (SIGGRAPH ASIA '09)
By Corey Manders, Farzam Farbiz, Ishtiaq Rasool Khan, Susanto Rahardja, Zhiyong Huang
Issue Date:December 2009
pp. 1-1
Global tone mapping operators (TMOs) are better in preserving the naturalness and relative illumination of the HDR scene compared to the local TMOs. However, they cannot preserve the details like the local TMOs. We propose a human visual system (HVS) based...
     
A 3D shape matching framework
Found in: Proceedings of the 1st international conference on Computer graphics and interactive techniques in Austalasia and South East Asia (GRAPHITE '03)
By Ee Chien Chang, Mohan S. Kankanhalli, Rong Xu, Zhiyong Huang
Issue Date:February 2003
pp. 269-270
The research of 3D shape matching starts to get more attention recently. In this short paper, we present a 3D shape matching framework. First, we give a general definition of similarity value of two objects. Then, an algorithm is proposed consisting of Pri...
     
Performance guaranteed rendering using the HDoV tree
Found in: Proceedings of the 1st international conference on Computer graphics and interactive techniques in Austalasia and South East Asia (GRAPHITE '03)
By Kian Lee Tan, Lidan Shou, Zhiyong Huang
Issue Date:February 2003
pp. 253-254
We propose the Hierarchical Degree-of-Visibility (HDoV) tree for performance guaranteed rendering. Each tree node represents a spatial region in the scene, and contains a DoV value that reflects the degree of visibility of the object(s) in the region with ...
     
Decomposing polygon meshes for interactive applications
Found in: Proceedings of the 2001 symposium on Interactive 3D graphics (SI3D '01)
By Tong Wing Toon, Xuetao Li, Zhiyong Huang
Issue Date:March 2001
pp. 35-42
we present an exact and interactive collision detection system, I-COLLIDE, for large-scale environments. Such environments are characterized by the number of objects undergoing rigid motion and the complexity of the models. The algorithm does not assume th...
     
Interactive 3D modeling using only one image
Found in: Proceedings of the ACM symposium on Virtual reality software and technology (VRST '00)
By Sujin Liu, Zhiyong Huang
Issue Date:October 2000
pp. 49-54
For virtual reality systems, modeling of 3D objects and scenes is important and challenging. In this paper, we present an image-based interactive 3D modeling framework consisting of three major modules: photogrammetric modeling, human interaction, and text...
     
 1