Search For:

Displaying 1-42 out of 42 total
A Concatenational Graph Evolution Aging Model
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jinli Suo, Xilin Chen, Shiguang Shan, Wen Gao, Qionghai Dai
Issue Date:November 2012
pp. 2083-2096
Modeling the long-term face aging process is of great importance for face recognition and animation, but there is a lack of sufficient long-term face aging sequences for model learning. To address this problem, we propose a CONcatenational GRaph Evolution ...
 
Covariance discriminative learning: A natural and efficient approach to image set classification
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Ruiping Wang, Huimin Guo,L. S. Davis, Qionghai Dai
Issue Date:June 2012
pp. 2496-2503
We propose a novel discriminative learning approach to image set classification by modeling the image set with its natural second-order statistic, i.e. covariance matrix. Since nonsingular covariance matrices, a.k.a. symmetric positive definite (SPD) matri...
 
A data-driven approach for facial expression synthesis in video
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Kai Li, Feng Xu, Jue Wang, Qionghai Dai, Yebin Liu
Issue Date:June 2012
pp. 57-64
This paper presents a method to synthesize a realistic facial animation of a target person, driven by a facial performance video of another person. Different from traditional facial animation approaches, our system takes advantage of an existing facial per...
 
Content Adaptive Subsampling for Stereo Interleaving Video Coding
Found in: Data Compression Conference
By Yongbing Zhang,Xiangyang Ji,Haoqian Wang,Lei Zhang,Qionghai Dai
Issue Date:April 2012
pp. 179-188
Stereo interleaving video coding receives considerable attention due to its desirable property of being compatible with 2D video coding standards. The errors caused by sub sampling (causing distortion between subsamplinginterpolated image and the original ...
 
Packet Video Error Concealment Based on Compressed Sensing and Regularized Least Squares
Found in: Data Compression Conference
By Fu Changjun,Ji Xiangyang,Yongbing Zhang,Qionghai Dai
Issue Date:April 2012
pp. 394
Error concealment (EC) is an important post processing technique to deal with the packet loss during the transmission of compressed video stream. This paper aims to address the problem of recovering the missing block in the decoded video stream from the pe...
 
Converting 2D Video to 3D: An Efficient Path to a 3D Experience
Found in: IEEE Multimedia
By Xun Cao,Alan C. Bovik,Yao Wang,Qionghai Dai
Issue Date:October 2011
pp. 12-17
Editor's NoteThe 3D experience is poised to be the future of entertainment. The path to that future, however, is bumpy. Despite widely available 3D display devices, a lack of 3D content impedes the 3D industry's rapid growth. Here the authors discuss some ...
 
High resolution multispectral video capture with a hybrid camera system
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xun Cao, Xin Tong, Qionghai Dai,S. Lin
Issue Date:June 2011
pp. 297-304
We present a new approach to capture video at high spatial and spectral resolutions using a hybrid camera system. Composed of an RGB video camera, a grayscale video camera and several optical elements, the hybrid camera system simultaneously records two vi...
 
Exploring aligned complementary image pair for blind motion deblurring
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wen Li, Jun Zhang, Qionghai Dai
Issue Date:June 2011
pp. 273-280
Camera shake during long exposure is ineluctable in light-limited situations, and results in a blurry observation. Recovering the blur kernel and the latent image from the blurred image is an inherently ill-posed problem. In this paper, we analyze the imag...
 
Dynamic Shape Capture via Periodical-Illumination Optical Flow Estimation and Multi-view Photometric Stereo
Found in: 3D Imaging, Modeling, Processing, Visualization and Transmission, International Conference on
By Ying Fu,Yebin Liu,Qionghai Dai
Issue Date:May 2011
pp. 17-24
Multi-view photometric stereo is well established for the shape recovery of static objects. However, it is difficult to align motion images under varying illumination so as to perform photometric stereo reconstruction for dynamic objects. To tackle this is...
 
A Prism-Mask System for Multispectral Video Acquisition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xun Cao,Hao Du,Xin Tong,Qionghai Dai,Stephen Lin
Issue Date:December 2011
pp. 2423-2435
This paper presents a prism-mask system for capturing multispectral videos. The system is composed of a triangular prism, a monochrome camera, and an occlusion mask. Incoming light beams from the scene are sampled by the occlusion mask, dispersed into thei...
 
Compressed Multi-view Imaging with Joint Reconstruction
Found in: Data Compression Conference
By Changjun Fu, Xiangyang Ji, Qionghai Dai
Issue Date:March 2011
pp. 448
The newly emerging sampling methodology of compressed sensing opens a door to obtain compressed data directly. How to efficiently reconstruct the original from the compressed data becomes a new challenge problem. Many reconstruction works have been propose...
 
Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination
Found in: IEEE Transactions on Visualization and Computer Graphics
By Chenglei Wu, Yebin Liu, Qionghai Dai, Bennett Wilburn
Issue Date:August 2011
pp. 1082-1095
We propose a method to obtain a complete and accurate 3D model from multiview images captured under a variety of unknown illuminations. Based on recent results showing that for Lambertian objects, general illumination can be approximated well using low-ord...
 
Region Based Rate-Distortion Analysis for 3D Video Coding
Found in: Data Compression Conference
By Qifei Wang, Xiangyang Ji, Qionghai Dai, Naiyao Zhang
Issue Date:March 2010
pp. 555
In 3D video coding, to provide the high-quality interactive viewpoint video to audience, it is necessary to jointly optimize coding efficiency of color and depth images at a given bit-rates. In this paper, a region based distortion model is proposed to pre...
 
A Point-Cloud-Based Multiview Stereo Algorithm for Free-Viewpoint Video
Found in: IEEE Transactions on Visualization and Computer Graphics
By Yebin Liu, Qionghai Dai, Wenli Xu
Issue Date:May 2010
pp. 407-418
This paper presents a robust multiview stereo (MVS) algorithm for free-viewpoint video. Our MVS scheme is totally point-cloud-based and consists of three stages: point cloud extraction, merging, and meshing. To guarantee reconstruction accuracy, point clou...
 
Continuous depth estimation for multi-view stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yebin Liu, Xun Cao, Qionghai Dai, Wenli Xu
Issue Date:June 2009
pp. 2121-2128
Depth-map merging approaches have become more and more popular in multi-view stereo (MVS) because of their flexibility and superior performance. The quality of depth map used for merging is vital for accurate 3D reconstruction. While traditional depth map ...
 
An Improved MAD Prediction Method for H.264 Rate Control
Found in: Computer Science and Information Engineering, World Congress on
By Xiaodong Liu, Qionghai Dai, Chonggang Fu
Issue Date:April 2009
pp. 316-319
H.264 is becoming the worldwide digital video standard for consumer electronics and personal computers. In particular, H.264 has already been selected as a key compression codec for the next generation of optical disc formats, HD-DVD and Blue-ray disc. Rat...
 
An Improved Side Information Refinement Method in Distributed Video Coding
Found in: Computer Science and Information Engineering, World Congress on
By Xiaodong Liu, Qionghai Dai, Rui Wang
Issue Date:April 2009
pp. 312-315
Distributed video coding (DVC) is a new kind of video codec scheme that exploits the statistical characteristics of source at the decoder part. The estimated side information is modeled with the original Wyner-Ziv frame and an additive noise. Side informat...
 
Improved Methods for Initializing R-Q Model Parameters and Quantization Parameter in H.264 Rate Control
Found in: Computer Science and Information Engineering, World Congress on
By Xiaodong Liu, Qionghai Dai, Chonggang Fu
Issue Date:April 2009
pp. 320-323
Rate control plays an important role in video coding and transmission. Current initialization of Quantization Parameter (QP) in H.264 rate control takes the same value for images with different complexity as long as the bit number per pixel is the same whi...
 
Slepian-Wolf Coding of Binary Finite Memory Source Using Burrows-Wheeler Transform
Found in: Data Compression Conference
By Chao Chen, Xiangyang Ji, Qionghai Dai, Xiaodong Liu
Issue Date:March 2009
pp. 440
In this paper, an asymmetric Slepian-Wolf coding(SWC) scheme for binary finite memory source (FMS) is proposed. The a priori information about the source is extracted from the side information at the decoder by Burrows-Wheeler Transform (BWT). Such informa...
 
A Decentralized Key Management Scheme in Overlay Multicast Network
Found in: Multimedia and Expo, IEEE International Conference on
By Xingfeng Guo, Xiaodong Liu, Qionghai Dai
Issue Date:July 2006
pp. 1201-1204
The recent growth of the World Wide Web has sparked new research into using the Internet for novel types of group communication, like multiparty videoconferencing and real-time streaming. Multicast has the potential to be very useful, but it suffers from m...
 
Improved Similarity-Based Online Feature Selection in Region-Based Image Retrieval
Found in: Multimedia and Expo, IEEE International Conference on
By Fei Li, Qionghai Dai, Wenli Xu
Issue Date:July 2006
pp. 349-352
To bridge the gap between high level semantic concepts and low level visual features in content-based image retrieval (CBIR), online feature selection is really required. An effective similarity-based online feature selection algorithm in region-based imag...
 
A Real Time Interactive Dynamic Light Field Transmission System
Found in: Multimedia and Expo, IEEE International Conference on
By Yebin Liu, Qionghai Dai, Wenli Xu
Issue Date:July 2006
pp. 2173-2176
The ability to interactively and seamlessly roam in the scenario while watching a video through IP network is an exciting visual experience. In this work, we implemented a 3D TV system with real-time data acquisition, compression, internet transmission, li...
 
Channel-adaptive hybrid ARQ/FEC for robust video transmission over 3G
Found in: Multimedia and Expo, IEEE International Conference on
By Jianwei Wen, Qionghai Dai, Yihui Jin
Issue Date:July 2005
pp. 4 pp.
This paper addresses the important issues of error control for video transmission over 3G. Based on the time-varying wireless channel conditions and the essential defects of the traditional hybrid ARQ for real-time service, the architecture of the channel-...
 
A Line-Diamond Parallel Search Algorithm for Block Motion Estimation
Found in: Image and Graphics, International Conference on
By Guiguang Ding, Qionghai Dai
Issue Date:December 2004
pp. 320-323
The widespread use of block matching motion estimation (BMME) in video coding is due to its effectiveness and simplicity of implementation. This paper presents a novel fast BMME algorithm called the Line-Diamond Parallel Search (LDPS). The algorithm is bas...
 
Research on Dynamic Feedback and Elastic Scheduling Model and Algorithm for Flexible Workload
Found in: Computer Networks and Mobile Computing, International Conference on
By Yu Chen, Qionghai Dai
Issue Date:October 2003
pp. 283
Soft real-time applications, such as multimedia systems, are becoming increasingly unpredictable due to the variable of the tasks? attributes. Under this circumstance, the scheduling algorithms depending on the tasks? static attributes can?t provide useful...
 
Research on Model and Scheduling Algorithm for Double-Mode VoD Servers
Found in: Computer Networks and Mobile Computing, International Conference on
By Yu Chen, Qionghai Dai
Issue Date:October 2003
pp. 297
In this paper, we design Double-Mode VoD Server (DM-VS). DM-VS provides online on-Demand service and offline on-Demand service. For offline on-Demand service, DM-VS merges several requests accessing the same video clip into a batching multicast that will i...
 
A novel VLSI architecture for multidimensional discrete wavelet transform
Found in: Multimedia and Expo, IEEE International Conference on
By Xinjian Chen, Qionghai Dai
Issue Date:July 2003
pp. 697-700
In this short paper we propose a novel VLSI architecture for multidimensional discrete wavelet transform (m-D DWT) based on systolic array and non-separable approach. The proposed architecture performs a decomposition of an N/sub 1/ /spl times/ N/sub 2/ /s...
 
An improved RM algorithm for preventing streaming media tasks from starvation
Found in: Multimedia and Expo, IEEE International Conference on
By Shuhua Peng, Xiaodong Liu, Qionghai Dai, Yu Cheng
Issue Date:July 2003
pp. 589-592
A streaming media system is a soft real-time system according to streaming media service features. Some soft real-time tasks and best-effort tasks will be starved when using traditional RM algorithm to schedule streaming media services. Aiming at this prob...
 
Structuring Lecture Videos by Automatic Projection Screen Localization and Analysis
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kai Li,Jue Wang,Haoqian Wang,Qionghai Dai
Issue Date:February 2015
pp. 1
We present a fully automatic system for extracting the semantic structure of a typical academic presentation video, which captures the whole presentation stage with abundant camera motions such as panning, tilting, and zooming. Our system automatically det...
 
View-Based 3D Object Retrieval: Challenges and Approaches
Found in: IEEE MultiMedia
By Yue Gao,Qionghai Dai
Issue Date:July 2014
pp. 52-57
View-based 3D object retrieval is an emerging research topic that has numerous geographic-related applications in many fields, such as computer-aided design (CAD) and virtual city navigation. This article briefly introduces the recent research progress in ...
 
Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yebin Liu,J. Gall,C. Stoll, Qionghai Dai,Hans-Peter Seidel,C. Theobalt
Issue Date:November 2013
pp. 2720-2735
Capturing the skeleton motion and detailed time-varying surface geometry of multiple, closely interacting peoples is a very challenging task, even in a multicamera setup, due to frequent occlusions and ambiguities in feature-to-person assignments. To addre...
 
Coded focal stack photography
Found in: 2013 IEEE International Conference on Computational Photography (ICCP)
By Xing Lin,Jinli Suo,Gordon Wetzstein,Qionghai Dai,Ramesh Raskar
Issue Date:April 2013
pp. 1-9
We present coded focal stack photography as a computational photography paradigm that combines a focal sweep and a coded sensor readout with novel computational algorithms. We demonstrate various applications of coded focal stacks, including photography wi...
   
High-rank coded aperture projection for extended depth of field
Found in: 2013 IEEE International Conference on Computational Photography (ICCP)
By Chenguang Ma,Jinli Suo,Qionghai Dai,Ramesh Raskar,Gordon Wetzstein
Issue Date:April 2013
pp. 1-9
Projectors require large apertures to maximize light throughput. Unfortunately, this leads to shallow depths of field (DOF), hence blurry images, when projecting on non-planar surfaces, such as cultural heritage sites, curved screens, or when sharing visua...
   
Video-based hand manipulation capture through composite motion control
Found in: ACM Transactions on Graphics (TOG)
By Feng Xu, Jianjie Zhang, Jianyuan Min, Jinxiang Chai, Qionghai Dai, Yangang Wang, Yebin Liu
Issue Date:July 2013
pp. 1-14
This paper describes a new method for acquiring physically realistic hand manipulation data from multiple video streams. The key idea of our approach is to introduce a composite motion control to simultaneously model hand articulation, object movement, and...
     
Cooperative cross-layer transmission for scalable video to resource-constrained receiver
Found in: Proceedings of the 10th International Conference on Mobile and Ubiquitous Multimedia (MUM '11)
By Hongjiang Xiao, Qiong Liu, Qionghai Dai
Issue Date:December 2011
pp. 152-155
For resource-constrained wireless scenarios, this paper proposes a cooperative cross-layer scheme to improve the performance of scalable video transmission. At the application layer, the extraction parameters of scalable video coding are first optimized to...
     
Video-based characters: creating new human performances from a multi-view video database
Found in: ACM SIGGRAPH 2011 papers (SIGGRAPH '11)
By Carsten Stoll, Christian Theobalt, Feng Xu, Gaurav Bharaj, Hans-Peter Seidel, James Tompkin, Jan Kautz, Qionghai Dai, Yebin Liu
Issue Date:August 2011
pp. 287-294
We present a method to synthesize plausible video sequences of humans according to user-defined body motions and viewpoints. We first capture a small database of multi-view video sequences of an actor performing various basic motions. This database needs t...
     
Video-based characters: creating new human performances from a multi-view video database
Found in: ACM Transactions on Graphics (TOG)
By Carsten Stoll, Christian Theobalt, Feng Xu, Gaurav Bharaj, Hans-Peter Seidel, James Tompkin, Jan Kautz, Qionghai Dai, Yebin Liu
Issue Date:July 2011
pp. 1-33
We present a method to synthesize plausible video sequences of humans according to user-defined body motions and viewpoints. We first capture a small database of multi-view video sequences of an actor performing various basic motions. This database needs t...
     
Intelligent query: open another door to 3d object retrieval
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Jialie Shen, Meng Wang, Naiyao Zhang, Qionghai Dai, Yue Gao
Issue Date:October 2010
pp. 1711-1714
The increasing number of available 3D objects makes their efficient retrieval technology highly desired. Extensive research has been dedicated to view-based 3D object retrieval because of its advantage of 2D views for 3D object content representation. In t...
     
3D object retrieval with bag-of-region-words
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Naiyao Zhang, Qionghai Dai, You Yang, Yue Gao
Issue Date:October 2010
pp. 955-958
View-based method becomes an essential approach to 3D object retrieval in recent years. In the view-based 3D object retrieval framework, each object is described by a set of views and representative features are extracted from these views to match the obje...
     
Representative views re-ranking for 3D model retrieval with multi-bipartite graph reinforcement model
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Naiyao Zhang, Qionghai Dai, You Yang, Yue Gao
Issue Date:October 2010
pp. 947-950
In this paper, we propose a multi-bipartite graph reinforcement model for representative views re-ranking in 3D model retrieval. Given the views of one query 3D model, all query views are grouped into clusters to generate representative views and correspon...
     
W2Go: a travel guidance system by automatic landmark ranking
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Jinhui Tang, Qionghai Dai, Ramesh Jain, Richang Hong, Tat-Seng Chua, Yue Gao
Issue Date:October 2010
pp. 123-132
In this paper, we present a travel guidance system W2Go (Where to Go), which can automatically recognize and rank the landmarks for travellers. In this system, a novel Automatic Landmark Ranking (ALR) method is proposed by utilizing the tag and geo-tag inf...
     
Sketch realizing: lifelike portrait synthesis from sketch
Found in: Computer Graphics International (CGI '09)
By Di Wu, Qionghai Dai
Issue Date:May 2009
pp. 13-20
People usually visualize their imaginations or memories through sketching. However, it might be difficult to record color and texture details powered by a large database of photographs gathered from the Web. This paper deals with the imagination visualizat...
     
 1