VCIP 2010 Program Schedule
11-Jul
|
Time |
11-Jul |
||
|
9:00~12:00 |
|||
|
12:00~14:00 |
Lunch |
||
|
14:00~17:00 |
|||
|
17:00~18:00 |
Break |
||
|
18:00~21:00 |
Reception |
||
12-Jul~14-Jul
|
Time |
12-Jul |
13-Jul |
14-Jul |
|
8:30~8:45 |
Welcome |
|
|
|
8:45~9:45 |
|||
|
9:45~10:00 |
Break |
Break |
Break |
|
10:00~12:00 |
|||
|
12:00~13:30 |
Lunch |
Lunch |
Lunch |
|
13:30~15:10 |
|||
|
15:10~15:30 |
Break |
Break |
Break |
|
15:30~16:50 |
Regular Poster Session-1 (15 papers) Demo
Session-1 |
||
|
16:50~17:00 |
Break |
Break |
Break |
|
17:00~18:00 |
Panel 1 |
Panel 2 |
|
|
18:00~21:00 |
|
Banquet |
|
Special Session-1:
PERCEPTION BASED VISUAL SIGNAL ANALYSIS AND REPRESENTATION
Chair
Weisi Lin, Nanyang
Technological University(Singapore)
King
Ngi Ngan, Chinese
University of Hong Kong(Hong Kong)
Zhenzhong Chen, Nanyang
Technological University(Singapore)
Limitation and
challenges of image quality measurement
F. Zhang, S. Li, L. Ma,
K.-N. Ngan, The Chinese
University of Hong Kong, (Hong Kong China)
Perceptual image quality
assessment: recent progress and trends
W. Lin, M. Narwaria, Nanyang Technological
Univ. (Singapore)
Multi-feature based
visual saliency detection in surveillance video
Y. Tong, University Jean
Monnet (France); H. Konik, Laboratoire
Hubert Curien (France); F. Cheikhb,
F.-F.-E. Gurayab, Gjovik
University College (Norway); A. Tremeau, University
Jean Monnet (France)
The analysis on the
perception shift of skin colors due to simultaneous color contrast
C.-H. Chou, Tatung Univ.
(Taiwan)
Linking distortion
perception and visual saliency in H.264/AVC coded video containing packet loss
U. Engelke,
Blekinge Institute of Technology (Sweden); R. Pepion, P.-L. Callet, University of Nantes (France); H.-J. Zepernick,
Blekinge Institute of Technology (Sweden)
SSIM based perceptual
distortion rate optimization coding
S. Wang, S. Ma, W. Gao, Peking Univ. (China)
Special Session-2:
INTERACTIVE MULTIMEDIA ANALYSIS
Chair
Tao Mei, Microsoft Research Asia(China)
Dacheng Tao, Nanyang
Technological University(Singapore)
Ling Shao, University. of Sheffield(UK)
Zengfu Wang, University of
Science and Technology of China(China)
MusicFlow: an interactive music composition
S.-Y. Ping Tan, Z. Hu,
A.-Y.-L. Koh, Felicia D,
S. Zhao, National University of Singapore (Singapore)
Semi-automatic photo
clustering with distance metric learning
D. Ji,
CAS (China); M. Wang, Microsoft Research Asia Beijing (China)
Relevance feedback-based
building recognition
J. Li, N. Allinson, University of Sheffield (United Kingdom)
Interactive important
social character identification from large photo collections
P. Wu, Hewlett-Packard
Labs (United States)
A new quality metric for
compressed images based on DDCT
W. Lu, Xidian Univ. (China); D. Tao, Nanyang
Technological Univ. (Singapore); J. Li, X. Gao, Xidian Univ. (China); X. Li, Xi'an Institute of Optics and
Precision Mechanics State Key Laboratory of Transient Optics and Photo (China)
Special Session-3: 3D
VIDEO CODING AND PROCESSING
Chair
Dong Tian, Thomson(USA)
Chang-Wen Chen, New York State University at Buffalo(USA)
3D video coding - an
overview of present and upcoming standards
P. Merkle,
K. Müller, T. Wiegand, Fraunhofer
HHI (Germany)
Overview of FTV
(free-viewpoint television)
M. Tanimoto,
Nagoya Univ. (Japan)
Joint trilateral
filtering for depth map compression
S. Liu, State Univ. of
New York at Buffalo (United States); P. Lai, D. Tian,
Technicolor Research & Innovation (United States); C.W. Chen, State Univ.
of New York at Buffalo (United States)
Time-variable camera
separation for compression of stereoscopic video
M. Ji,
Univ. of Sci. and Tech. of China (China); M. Hannuksela,
M. Gabbouj, Nokia Research Center (Finland); H. Li,
Univ. of Sci. and Tech. of China (China)
Special Session-4:
SPARSE REPRESENTATION AND COMPRESSED SENSING
Chair
Xin Li, West Virginia University(USA)
Lei Zhang, Hong Kong Polytechnic University(Hong Kong)
Super-resolution with
nonlocal regularized sparse representation
W. Dong, G. Shi, Xidian Univ Key Lab of Intell Perception & Image Understanding (China); L.
Zhang, The Hong Kong Polytechnic Univ. (HongKong,China);
X. Wu, McMaster Univ. (Canada)
Dynamic measurement rate
allocation for distributed compressive video sensing
H.-W. Chen, L.-W. Kang, C.-S. Lu, Academia Sinica
Institute of Information Science(Taiwan)
Collective sensing: a
fixed-point approach in the metric space
X. Li, West Virginia
Univ. (United States)
Practical compressive
sensing with toeplitz and circulant
matrices
W. Yin, Rice Univ.
(United States); S. Morgan, New Mexico Consortium (United States); J Yang,
Nanjing Univ. (China); Y.Zhang, Rice Univ. (United
States);
EdgeCS: edge guided compressive sensing reconstruction
W. Guo,
Case Western Reserve Univ. (United States);W.T. Yin, Rice Univ. (United States)
Special Session-5:
IMMERSIVE INTERACTION FOR NETWORKED MULTIVIEW VIDEO SYSTEMS
Chair
Gene Cheung, National Institute of Informatics(Japan)
Antonio Ortega, University of Southern California(USA)
Immersive haptic interaction
with media
N. Dindar,
A.-M. Tekalp, C. Basdogan, Koc Univ. (Turkey)
Approaches to 3-D video
compression
S.-R. Han, T. Yamasaki,
K. Aizawa, The Univ. of
Tokyo (Japan)
On media data structures
for interactive streaming in immersive applications
G. Cheung, National
Institute of Informatics (Japan); A. Ortega, Univ. of Southern California
(United States); N.-M. Cheung, B. Girod, Stanford
Univ. (United States)
Joint tracking and multiview video compression
C. Zhang, D. Florencio,
Microsoft Corp. (United States)
Popularity-aware rate
allocation in multi-view video
A. Fiandrotti,
Politecnico di Torino (Italy); J. Chakareski,
P. Frossard, Ecole Polytechnique Fédérale de
Lausanne (Switzerland)
Special Session-6:
INTERNET VIDEO CONTENT DISTRIBUTION
Chair
Yonggang Wen, Cisco Systems(USA)
Xiaoqing Zhu, Cisco Systems(USA)
Optimization on rate
allocation and distortion control for scalable video coding multicast networks
L. Jiang, J. Zou, Shanghai Univ. (China); H. Xiong, Shanghai Jiao Tong
Univ. (China)
Improving P2P
live-content delivery using SVC
T. Schierl,
Fraunhofer HHI (Germany); Y. S. Fuente,
C. Hellge, T. Wiegand, Technische Universität Berlin
(Germany)
IPTV multicast with
peer-assisted lossy error control
Z. Li, Stanford Univ.
(United States); X. Zhu, A. Begen, Cisco Systems
(United States); B. Girod, Stanford Univ. (United
States)
Designing QoE experiments to evaluate peer-to-peer streaming
applications
T. Z. J. Fu, D. M. Chiu,
The Chinese Univ. of Hong Kong (Hong Kong, China); Z. Lei, Applied Science and
Technology Research Institute (Hong Kong, China)
Special Session-7:
VISUAL QUALITY ASSESSMENT
Chair
Xinbo
Gao,Xidian
University(China)
Dacheng Tao, Nanyang
Technological University(Singapore)
Xuelong Li, Univ. of London(UK)
Video quality metric for
temporal fluctuation measurement
J. X. Yang, H. R. Wu,
RMIT Univ. (Australia)
Frame-loss adaptive
temporal pooling for video quality assessment
S. Wan, Northwestern Polytechnical University (China); F. Yang, X. Zhang, C. J, Xidian University (China)
A perceptual metric for
evaluating quality of synthesized sequences in 3DV system
Y. Zhao, L. Yu, Zhejiang
University (China)
Color image quality
assessment with biologically inspired feature and machine learning
C. Deng, Xidian University (China); D. Tao, Nanyang
Technological University (Singapore)
Image quality assessment
and human visual system
X. Gao, W. Lu, Xidian University (China); D. Tao, Nanyang
Technological University (Singapore); X. Li, Xi'an Institute of Optics and
Precision Mechanics (China)
An image quality
assessment metric with no reference using hidden markov
tree model
F. Gao, X. Gao, W. Lu, Xidian University (China); D. Tao, Nanyang
Technological University (Singapore); X. Li, Xi'an Institute of Optics and
Precision Mechanics (China)
Special Session-8:
STANDARD DEBUNKED: VIDEO CODING AND TRANSMISSION TECHOLOGIES REVISITED
Chair
Chia-Wen Lin, National Tsing Hua University(Taiwan)
Chia-Hung Yeh, National
Sun Yat-Sen University(Taiwan)
Multi-Order-Residual (MOR)
video coding: framework, analysis and performance
Q. Zhang, S.-H. Kim, Y. Dai, C.-C. J. Kuo, Univ.
of Southern California (USA)
Predictive patch
matching for inter frame coding
T. Chen, Xidian University (China); X. Sun, F. Wu, Microsoft Research
Asia (China)
A game-theoretical
pricing mechanism for multiuser rate allocation for video over WiMAX
C.-A. Chen,
C.-W. Lo, C.-W. Lin, Y.-C. Chen, National Tsing Hua University (Taiwan)
New intra prediction
with finite state machine for H.264/AVC
C.-H. Yeh, S.-J. F. Jiang, C.-S. Wu,
National Sun Yat-Sen Univ
(Taiwan)
Introducing differential
motion estimation into hybrid video coders
M. Cagnazzo,
B. Pesqeut-Popescu, Telecom ParisTech
(France)
Regular Lecture
Session-1: VIDEO CODING
Addressing the
uncertainty in critical rate estimation for pixel-domain Wyner-Ziv
video coding
A. Rehman,
Univ of Waterloo (Canada); H. Chen, E.Steinbach, Technische Univ München (Germany)
Reconstruction for
distributed video coding: a markov random field
approach with context-adaptive smoothness prior
Y. Zhang, H. Xiong,
Shanghai Jiao Tong Univ. (China); Z. He, Univ. of Missouri (United States); S.Yu, Shanghai Jiao Tong Univ. (China)
Transform domain Wyner-Ziv video coding with refinement of noise residue and
side information
X. Huang, S. Forchhammer, Technical Univ of
Denmark (Denmark)
Motion-compensated
filtering of reference picture for video coding
H. Tang, Zhejiang Univ.
(China)
Hybrid bit-stream
rewriting from scalable video coding to H.264/AVC
B. Li, Y. Guo, H. Li, C. W. Chen, Univ. of Sci. and Tech. of China
(China)
A perceptual-based
approach to bit allocation for H.264 encoder
T.-Sh. Ou, Y.-H. Huang, H. Chen,
National Taiwan Univ. (Taiwan)
Regular Lecture
Session-2: IMAGE CODING
Low bit-rate image
coding via interpolation oriented adaptive down-sampling
Y. Zhang, J. Zhang, Habin institue of technology
(China); R. Xiong, peking Univ. (China); D. Zhao, Habin institue of technology
(China); S. Ma, peking Univ. (China)
Improved line-based
image coding by exploiting long-distance correlations
X. Peng,
Univ.of Sci. and Tech. of China (China); J. Xu, F.
Wu, Microsoft Research Asia (China)
Pattern-based assembled
DCT scheme for image coding
Z. Chen, X. Xu,
Technicolor Corporate Research (China)
localized multiple adaptive interpolation filters with single-pass
encoding
X. Guo,
MediaTek Inc. (China)
A total variation based
approach for composing better pictures in multiple description coding
S. Zhu, B. Zeng, The Hong Kong University of
Science and Technology (China)
Regular Lecture
Session-3: IMAGE AND VIDEO TRANSMISSION
Compressed sensing based
video multicast
M. Schenkel,
C. Luo, P. Frossard, F. Wu,
Microsoft Research Asia (China)
Bandwidth auction for
SVC streaming in dynamic multi-overlay
Y. Xiong, J. Zou, Shanghai University (China), H. Xiong, Shanghai Jiao
Tong University (China)
A deadline-aware
transmission framework for H.264/AVC video over IEEE 802.11e EDCA wireless
networks
J. Du, Xidian University (China), C. W. Chen, State University of
New York at Buffalo (United States)
A packet-layer video
quality assessment model based on spatiotemporal complexity estimation
L. Ning,
Z. Chen, Technicolor Corporate Research Beijing (China)
Regular Lecture
Session-4: OBJECT SEGMENTATION AND TRACKING
A framework for
multi-object tracking over distributed wireless camera networks
V. Gau,
J.-N. Hwang, University of Washington (United States)
A refined particle
filter method for contour tracking
X. Sun, H. Yao, S. Zhang,
Harbin Institute of Technology (China)
Robust object tracking
based on sparse representation
S. Zhang, H. Yao, X. Sun, S. Liu, Harbin Institute of Technology
(China)
An adaptive approach to
human motion tracking from video
L. Wu, C. W. Chen, State
University of New York at Buffalo (United States)
Automatic segmentation
of breast tumor in ultrasound image with simplified PCNN and improved fuzzy
mutual information
J. Shi, Z. Xiao,
Shanghai University (China), S. Zhou, Fudan
University (China)
Unsupervised salient
object segmentation from color images
Z. Liu，L. Shen，L. Wang, Z. Zhang,
Shanghai Univ. (China)
Regular Lecture
Session-5: CONTENT ANAYLSIS
Ripplet-II transform for feature extraction
J. Xu, D. Wu, Univ. of
Florida (USA)
Subspace learning for silhouette
based human action recognition
L. Shao, The University of Sheffield (UK); R. Jin, Hangzhou. (China)
Scale and rotation
invariant Gabor texture descriptorfor texture
classification
Z. Li, G. Liu, Xi'an Jiaotong Univ. (China)
Scene categorization based
on heterogenous features
F. Lu, X. Yang, R.
Zhang, S. Yu, Shanghai Jiao Tong Univ. (China)
Subjective evaluation of
stereoscopic crosstalk perception
L. Xing, Q2S, NTNU
(Norway); T. Ebrahimi, EPFL. (Switzerland
); A. Perkis, Q2S, NTNU (Norway)
Regular Lecture
Session-6: MEDIA SYSTEMS
High throughput VLSI
architecture for multi-resolution integer motion estimation in high definition
AVS video encoder
H. Yin, China Jiliag Univ. (China); H. Qi, H. Xu, X. Xie,
W. Gao, Peking Univ. (China)
Perception-driven
watermarking with evolutionary block mapping
L. Cao, C. Men, J. Sun,
Harbin Engineering Univ. (China)
A fast and efficient
framework for indexing and detection of modified copies in video
L. Chaisorn,
C. Manders, Institute for Infocomm
Research. (Singapore); J. Sainui, Prince of Songkla Univ. (Thailand)
Detecting critical
configurations for euclidean 3D reconstruction by
analyzing the scaled measurement matrix
P. Li, ASML. (Netherlands); R. K. Gunnewiek, Philips
Research. (Netherlands); P. D. With, CycloMedia Technology B.V. (Netherlands)
Detection of illegal
transfer of videos over the internet
L. Chaisorn,
Institute for Infocomm Research (Singapore); J. Sainui, Prince of Songkla Univ.
(Thailand); C. Manders, Institute for Infocomm Research (Singapore)
Cell blade based H.264
video encoding engine for large scale video surveillance applications
L. Lu, IBM Watson
Research Center (United States)
Regular Lecture
Session-7: IMAGE PROCESSING
Image super-resolution
with sparse representation prior on primitive patches
H. Li, H. Xiong, L. Qian, Shanghai Jiao Tong University (China)
Image denoising using local tangent space alignment
J. Feng, L. Song,
Shanghai (China); X. Huo, Georgia Inst. of Tech.
(United States); X. Yang, W. Zhang, Shanghai (China)
Image restoration with
surface-based fourth order partial direrential
equation
B. Lu, Henan Polytechnic
University (China); Q. Liu, Shenzhen University (China)
CW-SSIM kernel based
random forest for image classification
G. Fan, Z. Wang, J.
Wang, University of Waterloo (Canada)
Fovea based image
quality assessment
A. Guo,
D. Zhao, S. Liu, G. Cao, Harbin Institute of Technology (China)
Regular Lecture
Session-8: MULTIVIEW VIDEO
Free viewpoint video
generation based on coding information of H.264/AVC
C.-K Lin,
Y.-C. Hong, C.-T. Tang,
J.-N. Hwang, J.-F. Yang, National Cheng Kung
University (Taiwan)
Template based
illumination compensation algorithm for multiview
video coding
X. Li, Harbin Institute
of Technology (China); L. Jiang, S. Ma, Peking Univ. (China); D. Zhao, Harbin
Institute of Technology (China); W. Gao, Peking Univ.
(China)
An improved depth map
estimation algorithm for view synthesis and multiview
video coding
X. Xiu,
J. Liang, Simon Fraser University (Canada)
An efficient coding
scheme for surveillance videos captured by stationary cameras
X. Zhang, Peking
University (China)
A semi-automatic
multi-view depth estimation method
M. Wildeboer,
Nagoya University (Japan); N. Fukushima, Nagoya Institute of Technology
(Japan); T. Yendo, M.-P. Tehrani,
T. Fujii, M. Tanimoto,
Nagoya University (Japan)
Regular Poster
Session-1: IMAGE AND VIDEO CODING
JPEG2000 Part 2 wavelet
packet subband structures in fingerprint recognition
A. Uhl,
B. Mühlbacher, T. Stütz,
Univ. Salzburg (Austria)
Two-dimensional
orthogonal DCT expansion in triangular and trapezoid regions
S.-C. Pei,
J.-J. Ding, T.-H. Henry Lee, National Taiwan
University (Taiwan)
Side information
enhancement via texture and motion activity analysis in distributed video
coding
X. Liu, D. Zhao, Harbin
Institute of Technology (China); S. Ma, W. Gao, Peking University (China)
Adaptive fast matching
algorithm based on sub-block ordering
S. Jin, C. Choi, J. Lee,
J. Jeong, Hanyang
University (Korea)
An adaptive mode driven
spatiotemporal motion vector prediction for wavelet video coding
F. Zhao, Xi'an
University of Technology (China); G. Liu, Y. Qi, Xi'an Jiaotong
University (China)
a fast intra 4x4 mode decision algorithm for H.264/AVC down rate
transcoding
Z. Wang, L. Liang,
Institute of Computing Technology Chinese Academy of Sciences (China); S. Dong,
W. Gao, Peking University (China); D. Zhao, Harbin
Institute of Technology (China); Q. Huang Graduate University of Chinese
Academy of Sciences
(China)
Inter-mode decision with
varied computational complexity
J. Lu, P. Zhang, H.
Chao, Sun Yat-Sen University (China); P. Fisher,
Winston-Salem State University (United States)
Efficient intra mode
selection using motion affected region tracking
C. Lai, Huawei (China),
J. Jiang, Xi'an (China), P. Zhang, Huawei (China)
Enhancements to MPEG4
MVC for depth compression
K. Iyer,
K. Maiti, B. Navathe, A.
Sharma, A. Bopardikar, Samsung India Software
Operations (India)
Frame rate up conversion
via Bayesian motion estimation
Y. Wang, S. Ma, W. Gao, Institute of Digital Media,
Peking University (China)
A coprocessor for
real-time motion estimation in HD video coding
H. Gu, S. Sun, S. Chen, National University of Defense
Technology (China)
Rate control algorithm
based on frame complexity estimation for MVC
T. Yan, P. An, L. Shen, Z. Zhang, Shanghai (China)
Rate control based on
intermediate description
M. Liu, Y. Guo, H. Li, Univ. of Science and Technology of China
(China)
error concealment in the network abstraction layer for medium grain
scalability of SVC
Z. Zhao, J. Ostermann, Leibniz Universitaet
Hannover (Germany)
Efficient architecture
for adaptive directional lifting-based wavelet transform
G. Shi, Xidian Univ. (China)
Regular Poster
Session-2: MEDIA PROCESSING AND ANALYSIS
Robust object tracking
combining color and scale invariant features
S. Zhang, H.
Yao, P. Gao, Harbin Institute of
Technology (China)
Automatic segmentation
of pupil using local histogram and standard deviation
M.T. Ibrahim, Ryerson Unviersity (Canada); T.M. Khan, M.A. Khan, COMSATS
Institute of Information Technology (Pakistan); L. Guan, Ryerson Unviersity (Canada)
A rotation and scale
invariant texture description approach
P. Xu, H. Yao, R. Ji, X. Sun, X. Liu, Harbin Institute of Technology (China)
Partial occlusion robust
object tracking using an effective appearance model
S. Zhang, H. Yao, S.
Liu, Harbin Institute of Technology (China)
Optical
flow based finger stroke detection
Z. Zhu, B. Li, Univ. of Sci.
and Tech. of China (China); K. Wang,Nokia Research
Center (China)
3D silhouette tracking
with occlusion inference
W. li, H. Yao, R. Ji, T. Liu, D. Zhao,
Harbin Institute of Technology (China)
Perceptually fractural
pixel values in rendering high dynamic range images
Y. Wu, B. Qiu, Institute for Infocomm Research (Singapore)
Model-assisted face
reconstruction based on binocular stereo
X. Sun, Z. Wang, Univ. of Sci. and Tech. of China (China)
image matting based high quality stereo view synthesis
H. Kannan, K. Iyer,
K. Maiti, D. Purbiya, A. Bopardikar, A. Sharma, Samsung India Software Operations
(India)
Adaptive sample map for monte carlo ray tracing
J. Teng, Technicolor Research &
Innovation (China); L.-X. Luo, Beihang Univ.; Z.-B. Chen,
Technicolor Research & Innovation (China)
Compressed image
restoration based on edge enhancement field of experts
H. Yu, F. Jiang, D. Zhao, Harbin Institute of Technology (China)
Robust video
super-resolution with registration efficiency adaptation
X. Zhang, Institute of Computing Technology (China); R. Xiong,
S. Ma, L. Zhang, W. Gao, Peking Univ. (China)
A passive scheme for
tampering detection based on quantization table estimation
G.-S. Lin, Da-Yeh Univ. (Taiwan); M.-K. Chang,
National Chung Hsing Univ. (Taiwan)
Perception-based
reversible watermarking for 2D-Vector maps
C. Men, L. Cao, X. Li, Harbin Engineering Univ. (China)
MAP spatial pyramid mean
shift for object tracking
X. Han, P. Zhang, H. Li, Univ. of Sci. and Tech. of China
(China)
Image registration by
blur and rotation invariants of Legendre moments
H. Zhang, X. Dai, H. Shu, Southeast U