Search For:

Displaying 1-50 out of 68 total
Viewport: A Distributed, Immersive Teleconferencing System with Infrared Dot Pattern
Found in: IEEE MultiMedia
By Cha Zhang,Qin Cai,Philip A. Chou,Zhengyou Zhang,Ricardo Martin-Brualla
Issue Date:January 2013
pp. 17-27
The Viewport immersive teleconferencing system reconstructs sparse 3D representations for each user and applies virtual seating to maintain the same seating geometry as face-to-face meetings.
 
Virtual View Reconstruction Using Temporal Information
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Shujie Liu,Philip A. Chou,Cha Zhang,Zhengyou Zhang,Chang Wen Chen
Issue Date:July 2012
pp. 115-120
The most significant problem in generating virtual views from a limited number of video camera views is handling areas that have become dis-occluded by shifting the virtual view away from the camera view. We propose using temporal information to address th...
 
Calibration between depth and color sensors for commodity depth cameras
Found in: Multimedia and Expo, IEEE International Conference on
By Cha Zhang, Zhengyou Zhang
Issue Date:July 2011
pp. 1-6
Commodity depth cameras have created many interesting new applications in the research community recently. These applications often require the calibration information between the color and the depth cameras. Traditional checkerboard based calibration sche...
 
A novel see-through screen based on weave fabrics
Found in: Multimedia and Expo, IEEE International Conference on
By Cha Zhang, Ruigang Yang,Tim Large, Zhengyou Zhang
Issue Date:July 2011
pp. 1-6
See-through screens (STS) have found important applications in remote collaboration systems to enhance non-verbal communication and gaze awareness. Existing STS designs often sacrifice the display quality significantly, rendering low-contrast images that d...
 
Boosted multi-task learning for face verification with applications to web image and video search
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiaogang Wang, Cha Zhang, Zhengyou Zhang
Issue Date:June 2009
pp. 142-149
Face verification has many potential applications including filtering and ranking image/video search results on celebrities. Since these images/videos are taken under uncontrolled environments, the problem is very challenging due to dramatic lighting and p...
 
Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yang Wang, Lei Zhang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengyou Zhang, Dimitris Samaras
Issue Date:November 2009
pp. 1968-1984
In this paper, we present a new method to modify the appearance of a face image by manipulating the illumination condition, when the face geometry and albedo information is unknown. This problem is particularly difficult when there is only a single image o...
 
Taylor expansion based classifier adaptation: Application to person detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Cha Zhang, Raffay Hamid, Zhengyou Zhang
Issue Date:June 2008
pp. 1-8
Because of the large variation across different environments, a generic classifier trained on extensive data-sets may perform sub-optimally in a particular test environment. In this paper, we present a general framework for classifier adaptation, which imp...
 
Microsoft Kinect Sensor and Its Effect
Found in: IEEE Multimedia
By Zhengyou Zhang
Issue Date:April 2012
pp. 4-10
Recent advances in 3D depth cameras such as Microsoft Kinect sensors (www.xbox.com/en-US/kinect) have created many opportunities for multimedia computing. The Kinect sensor lets the computer directly sense the third dimension (depth) of the players and the...
 
Realistic audio in immersive video conferencing
Found in: Multimedia and Expo, IEEE International Conference on
By Sanjeev Mehrotra, Wei-ge Chen, Zhengyou Zhang,Philip A. Chou
Issue Date:July 2011
pp. 1-4
With increasing computation power, network bandwidth, and improvements in display and capture technologies, fully immersive conferencing and tele-immersion is becoming ever closer to reality. Outside of video, one of the key components needed is high quali...
 
Action detection using multiple spatial-temporal interest point features
Found in: Multimedia and Expo, IEEE International Conference on
By Liangliang Cao, YingLi Tian, Zicheng Liu, Benjamin Yao, Zhengyou Zhang, Thomas S. Huang
Issue Date:July 2010
pp. 340-345
This paper considers the problem of detecting actions from cluttered videos. Compared with the classical action recognition problem, this paper aims to estimate not only the scene category of a given video sequence, but also the spatial-temporal locations ...
 
Meta-tag propagation by co-training an ensemble classifier for improving image search relevance
Found in: Computer Vision and Pattern Recognition Workshop
By Aayush Sharma, Gang Hua, Zicheng Liu, Zhengyou Zhang
Issue Date:June 2008
pp. 1-6
The ever-increasing gigantic amount of images over the web necessitates automatic schemes for meta-tagging content descriptions such as object categories. These meta-tags are essential to text-based image search engines to improve their search relevance. T...
 
Robust and Accurate Visual Echo Cancelation in a Full-duplex Projector-Camera System
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Miao Liao, Ruigang Yang, Zhengyou Zhang
Issue Date:October 2008
pp. 1831-1840
In this paper we study the problem of
 
Face Re-Lighting from a Single Image under Harsh Lighting Conditions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yang Wang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengyou Zhang, Dimitris Samaras
Issue Date:June 2007
pp. 1-8
In this paper, we present a new method to change the illumination condition of a face image, with unknown face geometry and albedo information. This problem is particularly difficult when there is only one single image of the subject available and it was t...
 
Robust Local Scoring Function for Text-Independent Speaker Verification
Found in: Pattern Recognition, International Conference on
By Ming Liu, Thomas S. Huang, Zhengyou Zhang
Issue Date:August 2006
pp. 1146-1149
Traditionally, the Universal Background Model (UBM) is viewed as the background model of the entire acoustic feature space. We propose a novel interpretation of the UBM model, and consider it as a mapping function that transforms the variable length observ...
 
Speech Modelingwith Magnitude-Normalized Complex Spectra and Its Application to Multisensory Speech Enhancement
Found in: Multimedia and Expo, IEEE International Conference on
By Amarnag Subramanya, Zhengyou Zhang, Zicheng Liu, Alex Acero
Issue Date:July 2006
pp. 1157-1160
A good speech model is essential for speech enhancement, but it is very difficult to build because of huge intra-and extra-speaker variation. We present a new speech model for speech enhancement, which is based on statistical models of magnitude-normalized...
 
Robust and Accurate Visual Echo Cancelation in a Full-Duplex Projector-Camera System
Found in: Computer Vision and Pattern Recognition Workshop
By Miao Liao, Mingxuan Sun, Ruigang Yang, Zhengyou Zhang
Issue Date:June 2006
pp. 10
We developed a comprehensive set of techniques to address the ?visual echo? problem in a full-duplex projectorcamera system. A calibration procedure records the geometric and photometric transfer between the projector and camera in a look-up table. With th...
 
Computer Vision Technologies for Remote Collaboration Using Physical Whiteboards, Projectors and Cameras
Found in: Computer Vision for Interactive and Intelligent Environment
By Zhengyou Zhang
Issue Date:November 2005
pp. 109-122
A whiteboard provides a large shared space for the participants to focus their attention and express their ideas, and is therefore a great collaboration tool for information workers. However, it has several limitations; notably, the contents on the whitebo...
 
Automatic Head-size Equalization in Panorama Images for Video Conferencing
Found in: Multimedia and Expo, IEEE International Conference on
By Ya Chang, R. Cutler, Zicheng Liu, Zhengyou Zhang, A. Acero, M. Turk
Issue Date:July 2005
pp. 506-509
In panorama images captured by omni-directional cameras during video conferencing, the image sizes of the people around the conference table are not uniform due to the varying distances to the camera. Spatially varying-uniform (SVU) scaling functions have ...
 
Linear Combination Representation for Outlier Detection in Motion Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Guodong Guo, Charles R. Dyer, Zhengyou Zhang
Issue Date:June 2005
pp. 274-281
In this paper we show that Ullman and Basri?s linear combination (LC) representation, which was originally proposed for alignment-based object recognition, can be used for outlier detection in motion tracking with an affine camera. For this task LC can be ...
 
Eye Gaze Correction with Stereovision for Video-Teleconferencing
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ruigang Yang, Zhengyou Zhang
Issue Date:July 2004
pp. 956-960
<p><b>Abstract</b>—The lack of eye contact in desktop video teleconferencing substantially reduces the effectiveness of video contents. While expensive and bulky hardware is available on the market to correct eye gaze, researchers have be...
 
Camera Calibration with One-Dimensional Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhengyou Zhang
Issue Date:July 2004
pp. 892-899
<p><b>Abstract</b>—Camera calibration has been studied extensively in computer vision and photogrammetry and the proposed techniques in the literature include those using 3D apparatus (two or three planes orthogonal to each other or a pla...
 
Image-Based Surface Detail Transfer
Found in: IEEE Computer Graphics and Applications
By Zicheng Liu, Zhengyou Zhang, Ying Shan
Issue Date:May 2004
pp. 30-35
This article presents a novel technique, called image-based surface detail transfer, that transfers geometric details from one surface to another with simple 2D image operations. The authors? basic finding is that, without knowing its 3D geometry, geometri...
 
Automatic Eyeglasses Removal from Face Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chenyu Wu, Ce Liu, Heung-Yueng Shum, Ying-Qing Xu, Zhengyou Zhang
Issue Date:March 2004
pp. 322-336
<p><b>Abstract</b>—In this paper, we present an intelligent image editing and face synthesis system that automatically removes eyeglasses from an input frontal face image. Although conventional image editing tools can be used to remove ey...
 
Model-Based Head Pose Tracking With Stereovision
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Ruigang Yang, Zhengyou Zhang
Issue Date:May 2002
pp. 0255
We present a robust model-based stereo head tracking algorithm that operates in real time on a commodity PC. The use of an individualized three-dimensional head model, coupled with the epipolar constraint from the stereo image pair, greatly improves the ro...
 
Multibody Grouping via Orthogonal Subspace Decomposition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ying Wu, Zhengyou Zhang, Thomas S. Huang, John Y. Lin
Issue Date:December 2001
pp. 252
Multibody structure from motion could be solved by the factorization approach. However, the noise measurements would make the segmentation difficult when anaylyzing the shape interaction martix. This paper presents an orthogonal subspace decomposition and ...
 
Image-Based Surface Detail Transfer
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ying Shan, Zicheng Liu, Zhengyou Zhang
Issue Date:December 2001
pp. 794
We present a novel technique, called Image-Based Surface Detail Transfer, to transfer geometric details from one sur-face to another with simple 2D image operations. The basic observation is that, without knowing its 3D geometry, geo-metric details (local ...
 
Determining Reflectance Parameters and Illumination Distribution from a Sparse Set of Images for View-dependent Image Synthesis
Found in: Computer Vision, IEEE International Conference on
By Ko Nishino, Zhengyou Zhang, Katsushi Ikeuchi
Issue Date:July 2001
pp. 599
A framework for photo-realistic view-dependent image synthesis of a shiny object from a sparse set of images and a geometric model is proposed. Each image is aligned with the 3D model and decomposed into two images with regards to the reflectance component...
 
Cloning Your Own Face With A Desktop Camera
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang, Zicheng Liu, Denis Adler, Michael Cohen, Erik Hanson, Ying Shan
Issue Date:July 2001
pp. 745
No summary available.
   
Robust head motion computation by taking advantage of physical properties
Found in: Human Motion, Workshop on
By Zicheng Liu, Zhengyou Zhang
Issue Date:December 2000
pp. 73
Head motion determination is an important problem for many applications including face modeling and tracking. We present a new algorithm to compute the head motion between two views from the correspondences of five feature points (eye corners, mouth corner...
 
A Flexible New Technique for Camera Calibration
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhengyou Zhang
Issue Date:November 2000
pp. 1330-1334
<p><b>Abstract</b>—We propose a flexible new technique to easily calibrate a camera. It only requires the camera to observe a planar pattern shown at a few (at least two) different orientations. Either the camera or the planar pattern can...
 
Corner Guided Curve Matching and its Application to Scene Reconstruction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ying Shan, Zhengyou Zhang
Issue Date:June 2000
pp. 1796
Corners and curves are important image features in many vision-based applications. Corners are usually more stable and easier to match than curves, while curves contain richer information of scene structure. In previous work, corners are often used to reco...
 
What Can Be Determined from a Full and a Weak Perspective Image?
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang, P. Anandan, Heung-Yeung Shum
Issue Date:September 1999
pp. 680
This paper presents a first investigation on the structure from motion problem from the combination of full and weak perspective images. This problem arises in multiresolution object modeling, where multiple zoomed-in or closeup views are combined with wid...
 
Flexible Camera Calibration by Viewing a Plane from Unknown Orientations
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang
Issue Date:September 1999
pp. 666
We propose a flexible new technique to easily calibrate a camera. It only requires the camera to observe a planar pattern shown at a few (at least two) different orientations. Either the camera or the planar pattern can be freely moved. The motion need not...
 
Efficient Bundle Adjustment with Virtual Key Frames: A Hierarchical Approach to Multi-Frame Structure from Motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Heung-Yeung Shum, Zhengyou Zhang, Qifa Ke
Issue Date:June 1999
pp. 2538
In this paper we present an efficient hierarchical approach to structure from motion for long image sequences. There are two key elements to our approach: accurate 3D reconstruction for each segment and efficient bundle adjustment for the whole sequence. T...
 
Computing Rectifying Homographies for Stereo Vision
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Charles Loop, Zhengyou Zhang
Issue Date:June 1999
pp. 1125
Image rectification is the process of applying a pair of 2 dimensional projective transforms, or homographies, to a pair of images whose epipolar geometry is known so that epipolar lines in the original images map to horizontally aligned lines in the trans...
 
On the Optimization Criteria Used in Two-View Motion Analysis
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhengyou Zhang
Issue Date:July 1998
pp. 717-729
<p><b>Abstract</b>—The three best-known criteria in two-view motion analysis are based, respectively, on the distances between points and their corresponding epipolar lines, on the gradient-weighted epipolar errors, and on the distances b...
 
Euclidean Structure from Uncalibrated Images Using Fuzzy Domain Knowledge: Application to Facial Images Synthesis
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang, Katsunori Isono, Shigeru Akamatsu
Issue Date:January 1998
pp. 784
Use of uncalibrated images has found many applications such as image synthesis. However, it is not easy to specify the desired position of the new image in projective or af.ne space. This paper proposes to recover Euclidean structure from uncalibrated imag...
 
Modeling Geometric Structure and Illumination Variation of a Scene from Real Images
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang
Issue Date:January 1998
pp. 1041
We present in this paper a system which automatically builds, from real images, a scene model containing both 3D geometric information of the scene structure and its photometric information under various illumination conditions. The geometric structure is ...
 
Understanding the Relationship Between the Optimization Criteria in Two-View Motion Analysis
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang
Issue Date:January 1998
pp. 772
The three best known criteria in two-view motion analysis are based, respectively, on the distances between points and their corresponding epipolar lines, on the gradient-weighted epipolar errors, and on the distances between points and the reprojections o...
 
Estimating Motion and Structure from Correspondences of Line Segments between Two Perspective Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhengyou Zhang
Issue Date:December 1995
pp. 1129-1139
<p><it>Abstract</it>—We present in this paper an algorithm for determining 3D motion and structure from correspondences of <it>line segments</it> between two perspective images. To our knowledge, this paper is the first invest...
 
Motion and Structure of Four Points from One Motion of a Stereo Rig with Unknown Extrinsic Parameters
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhengyou Zhang
Issue Date:December 1995
pp. 1222-1227
<p><it>Abstract</it>—We describe an analytical method for recovering 3D motion and structure of four or more points from one motion of a stereo rig. The extrinsic parameters are unknown. The motion of the stereo rig is also unknown. Becau...
 
Estimating motion and structure from correspondences of line segments between two perspective images
Found in: Computer Vision, IEEE International Conference on
By Zhengyou Zhang
Issue Date:June 1995
pp. 257
Presents an algorithm for determining 3D motion and structure from correspondences of line segments between two perspective images. To our knowledge, the paper is the first investigation of use of line segments in motion and structure from motion. Classica...
 
Improving multiview face detection with multi-task deep convolutional neural networks
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Cha Zhang,Zhengyou Zhang
Issue Date:March 2014
pp. 1036-1041
Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specific...
   
Wide-Baseline Hair Capture Using Strand-Based Refinement
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Linjie Luo,Cha Zhang,Zhengyou Zhang,Szymon Rusinkiewicz
Issue Date:June 2013
pp. 265-272
We propose a novel algorithm to reconstruct the 3D geometry of human hairs in wide-baseline setups using strand-based refinement. The hair strands are first extracted in each 2D view, and projected onto the 3D visual hull for initialization. The 3D positio...
 
Robust part-based face matching with multiple templates
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Kye-Hyeon Kim, Cha Zhang, Zhengyou Zhang, Seungjin Choi
Issue Date:April 2013
pp. 1-7
Part-based matching can handle significant variations in facial expression and partial occlusion. However, under large pose variations, it is sometimes difficult to find corresponding local parts in a pair of images. In this paper, we propose a novel part-...
   
Tensor-Based Human Body Modeling
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yinpeng Chen,Zicheng Liu,Zhengyou Zhang
Issue Date:June 2013
pp. 105-112
In this paper, we present a novel approach to model 3D human body with variations on both human shape and pose, by exploring a tensor decomposition technique. 3D human body modeling is important for 3D reconstruction and animation of realistic human body, ...
 
Measuring the engagement level of TV viewers
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Javier Hernandez, Zicheng Liu,Geoff Hulten,Dave DeBarr,Kyle Krum,Zhengyou Zhang
Issue Date:April 2013
pp. 1-7
This work studies the feasibility of using visual information to automatically measure the engagement level of TV viewers. Previous studies usually utilize expensive and invasive devices (e.g., eye trackers or physiological sensors) in controlled settings....
   
Iterative Local-Global Energy Minimization for Automatic Extraction of Objects of Interest
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gang Hua, Zicheng Liu, Zhengyou Zhang, Ying Wu
Issue Date:October 2006
pp. 1701-1706
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels during iteration. We introduce...
 
Model-Based Bundle Adjustment with Application to Face Modeling
Found in: Computer Vision, IEEE International Conference on
By Ying Shan, Zicheng Liu, Zhengyou Zhang
Issue Date:July 2001
pp. 644
We present a new model-based bundle adjustment algorithm to recover the 3D model of a scene/object from a sequence of images with unknown motions. Instead of representing scene/object by a collection of isolated 3D features (usually points), our algorithm ...
 
Mining noisy tagging from multi-label space
Found in: Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM '12)
By Ming Yang, Zhengyou Zhang, Zhongang Qi, Zhongfei (Mark) Zhang
Issue Date:October 2012
pp. 1925-1929
In this paper we study the problem of mining noisy tagging. Most of the existing discriminative classification methods to this problem only consider one tag at a time as the classification target, and completely ignore the rest of the given tags at the sam...
     
 1  2 Next >>