PSIVT 2010 Program Overview :
The photo and video recordings of all paper presentations and keynotes are now uploaded to http://cklcjl.phanfare.com/PSIVT2010/, accessible by psivt2010 participants only.
14-Nov-10 | Title | |
2:00pm - 5:30pm | Tutorial | Face Recognition |
15-Nov-10 | Session Name | |
09:00-09:05 | Opening of PSIVT 2010 | |
09:05-09:50 | Keynote 1 | Locally Adaptive Regression Kernels (LARK) for Visual Signal Processing and Recognition----Professor Peyman Milanfar |
09:50-10:10 | Break 1 | |
10:10-11:10 | Short Oral 1 (+Poster) | Detection, Recognition, and Image Retrieval |
11:10-12:30 | Oral 1 | Biometrics |
12:30-01:30 | Lunch | |
01:30-02:15 | Keynote 2 | Intelligent Video Surveillance----Professor Stan Z. Li |
02:15-03:35 | Oral 2 | Computer Vision (I) |
03:35-03:55 | Break 2 | |
03:55-04:40 | Short Oral 2 (+Poster) | Computer Vision (II) |
04:40-06:00 | Oral (SP 1) | Social Media Content Mining |
16-Nov-10 | Session Name | |
09:00-09:45 | Keynote 3 | 3DTV and Realistic Broadcasting Services----Professor Yo-Sung Ho |
09:45-10:05 | Break 3 | |
10:05-11:05 | Short Oral 3(+Poster) | Image/Video Coding |
11:05-12:25 | Oral 3 | Video Coding |
12:25-1:30 | Lunch | |
01:30-02:30 | Short Oral 4(+Poster) | Image/Video Processing |
02:30-03:50 | Oral 4 | Object Detection and Recognition |
03:50-04:10 | Break 4 | |
04:10-05:30 | Oral (SP 2) | Multimedia Browsing and Understanding |
07:00-09:00 | Banquet |
17-Nov-10 | Session Name | |
09:00-10:20 | Oral 5 | Super-resolution and Image Enhancement |
10:20-10:40 | Break 5 | |
10:40-12:00 | Oral 6 | Image Enhancement and Image Filter |
12:00-13:00 | Lunch | |
13:00-02:20 | Oral 7 | Video Surveillance |
02:20-03:40 | Oral (SP 3) | Image/Video Technology Meets Art |
03:40-04:00 | Break 6 | |
04:00-05:20 | Oral (SP 4) | Graphics and Visualization |
SP - special session
Day 1 | Morning | 15-Nov-2010 (Monday) | ||
09:00-09:05 | Opening of PSIVT 2010 | |||
09:05-09:50 | Keynote 1 | Locally Adaptive Regression Kernels (LARK) for Visual Signal Processing and Recognition----Professor Peyman Milanfar | ||
Session chair | Kai-Kuang Ma, Nanyang Technological University | |||
09:50-10:10 | Break 1 | |||
Short Oral 1 (+Poster) | 10:10-11:10 | Detection, Recognition, and Image Retrieval | Session chair: Wei-Ta Chu, National Chung Cheng University | |
One-shot Recognition Using Unsupervised Attribute-Learning
|
Zhenyu Guo and Z. Jane Wang | |||
Optimal Training Set Selection for Video Annotation
|
Guo-Xiang Hong, Chung-Lin Huang, Shih-Chung Hsu, and Chi-Hung Tsai | |||
Detecting the Presence of Stationary Objects from Sparse Stereo Disparity Space
|
Tiandi Duan, Wei Huang, and Martin Constable | |||
3D Face Recognition Using Multi-level Multi-Feature Fusion
|
Cuicui Zhang, Keiichi Uchimura, Caiming Zhang, and Gou Koutaki | |||
Vector Quantization Based Index Cube Model for Image Retrieval
|
B. Janet, A.V. Reddy, and S. Domnic | |||
Locating Corresponding Regions in Urban Environments
|
Jimmy Addison Lee and Kin-Choong Yow | |||
Semantic Segmentation and Object Recognition Using Scene-Context Scale
|
Yousun Kang, Hiroshi Nagahashi, and Akihiro Sugimoto | |||
Automated Detection of Fish Bones in Salmon Fillets Using X-ray Testing
|
Domingo Mery, Iván Lillo, Hans Loebel, Vladimir Riffo, Alvaro Soto, Aldo Cipriano, and José Miguel Aguilera | |||
View-invariant Fall Detection for Elderly in Real Home Environment
|
Muhammad Shoaib, Ralf Dragon, and Jörn Ostermann | |||
Error Analysis of Geometric Ellipse Detection Methods due to Quantization
|
Dilip Kumar Prasad and Maylor K.H. Leung | |||
Ellipse Detection by Combining Division and Model Selection based Integration of Edge Points
|
Yasuyuki Sugaya |
Oral 1 | 11:10-12:30 | Biometrics | Session chair:Kwoh Chee Keong, Nanyang Technological University | |
Bit Reliability-driven Template Matching in Iris Recognition
|
Christian Rathgeb and Andreas Uhl | |||
Recombination of 2D and 3D Images for Multimodal 2D + 3D Face Recognition
|
Gede Putra Kusuma, Chin-Seng Chua, and Hock-Lye Toh | |||
A Novel Facial Expression Recognition based on the Curvelet Features
|
Juxiang Zhou, Yunqiong Wang, Tianwei Xu, and Wanquan Liu | |||
Age Regression based on Local Image Features
|
Azza Mokadem, Maurice Charbit, Gérard Chollet, and Kevin Bailly |
12:30-01:30 | Lunch |
Day 1 | Afternoon | |||
01:30-02:15 | Keynote 2 | Intelligent Video Surveillance----Professor Stan Z. Li | ||
Session chair | Yasuyuki Matsushita, Microsoft | |||
Oral 2 | 02:15-03:35 | Computer Vision (I) | Session chair:Domingo Mery, Pontificia Universidad Catolica de Chile | |
Towards Generalized Benthic Species Recognition and Quantification Using Computer Vision
|
Adam F. Gobi | |||
Mismatch Removal for Wide-baseline Image Matching via Coherent Region-to-Region Correspondence
|
Chen Wang, Kai-Kuang Ma, Teck-Khim Ng, and Dong Guo | |||
One-shot Entire Shape Acquisition Method Using Multiple Projectors and Cameras
|
Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki, Kazuhiro Sakashita, Yasushi Yagi, and Naoki Asada | |||
Shape Classification Using Local and Global Features
|
Kart-Leong Lim and Hamed Kiani Galoogahi |
03:35-03:55 | Break 2 |
Short Oral 2 (+Poster) | 03:55-04:40 | Computer Vision (II) | Session chair: Yasuyuki Matsushita, Microsoft | |
Modeling of Unbounded Long-Range Drift in Visual Odometry
|
Ruyi Jiang, Reinhard Klette, and Shigang Wang | |||
Human Behaviour Analysis and Event Recognition at A Point of Sale
|
R. Sicre and H. Nicolas | |||
A Robust Method for License Plate Detection
|
Jian Luo, Su Yang, Ruimin Guan, and Haijun Niu | |||
Object Tracking based on Covariance Descriptors and On-Line Naive Bayes Nearest Neighbor Classifier
|
Pedro Manuel Cortez Cargill, Domingo Mery Quiroz, and Luis Enrique Sucar | |||
An Online Learning Method for Shadow Detection
|
Chung-Hsien Huang and Ruei-Cheng Wu | |||
Cart Auditor: A Compliance and Training Tool for Cashiers at Checkout
|
Unsang Park, Charles A. Otto, and Sharath Pankanti | |||
A Level-set Based Tracking Approach for Surveillance Video with Fusion and Occlusion
|
Chaoqun Hong, Na Li, Mingli Song, Jiajun Bu, and Chun Chen | |||
Camera Calibration Using Lengths of Corresponding Line Segments
|
Ruiyan Wang, Guang Jiang, Long Quan, and Chengke Wu | |||
A Linear-time Algorithm for the Generation of Random Digital Curves
|
Partha Bhowmick, Oishee Pal, and Reinhard Klette | |||
Shape Matching by Region Grouping
|
Yan Gao and Wei-Yun Yau |
Oral (SP 1) | 04:40-06:00 | Social Media Content Mining | Session chair:Richang Hong, National University of Singapore | |
Travel Video Scene Detection by Search
|
Wei-Ta Chu, Cheng-Jung Li, and Tsung-Che Lin | |||
Multi-Modality Transfer based on Multi-Graph Optimization for Domain Adaptive Video Concept Annotation
|
Shaoxi Xu, Sheng Tang, Yongdong Zhang, and Jintao Li | |||
A Collaborative Approach for Image Annotation
|
Fuming Sun, Yong Ge, Dongxia Wang, and Xueming Wang | |||
Mash-Up Approach for Web Video Category Recommendation
|
Yicheng Song and Haojie Li |
Day 2> | Morning | 16-Nov-2010 (Tuesday) | ||
09:00-09:45 | Keynote 3 | 3DTV and Realistic Broadcasting Services----Professor Yo-Sung Ho | ||
Session chair | Han Wang, Nanyang Technological University | |||
09:45-10:05 | Break 3 | |||
Short Oral 3 (+Poster) | 10:05-11:05 | Image/Video Coding | Session chair:Yo-Sung Ho, Gwangju Institute of Science and Technology | |
Region Adaptive Inter-Color Prediction Approach to RGB 4:4:4 Intra Coding
|
Lili Zhao and Mingjing Ai | |||
An extension of CCSDS Algorithm by ROI capability
|
Shen-Chuan Tai, Tse-Ming Kuo, and Ng Keng San/td> | |||
An Object-based Full Frame Concealment Strategy for H.264/AVC Using True Motion Estimation
|
Shen-Chuan Tai, Chien Shiang Hong, and Cheng-An Fu | |||
A Perceptually Lossless Image Compression Scheme Based On JND Refinement by Neural Network
|
Wen-Nung Lie and Wen-Ching Liu | |||
High-Level Synthesis of a Unified 2-D DWT System Architecture for JPEG2000 Using FPGAs
|
Ishmaiel Sameen, Yoong Choon Chang, Mow Song Ng, Bok-Min Goi, and Chee Siong Lee | |||
A Perceptually Scalable and JPEG Compression Tolerant Image Encryption Scheme
|
Fawad Ahmed, M Y Siyal, and Vali Uddin Abbas | |||
N Way Video Communication over Enterprise Networks based on Adaptive Bit Stream Extraction in SVC
|
Ramanathan Palaniappan and Nikil Jayant |
Oral 3 | 11:05-12:25 | Video Coding | Session chair:Kai-Kuang Ma, Nanyang Technological University | |
Zero-block Mode Decision Algorithm for High Bit-Rate Coding in H.264/AVC | Yu-Ming Lee, Shen-Hsien Liu, Wei-Yao Chiu, and Yinyi Lin | |||
Low Complexity Hierarchical Prediction Algorithm for H.264/SVC | Abdelrahman Abdelazim, Stephen Mein, Martin Varley, and Djamel Ait-Boudaoud | |||
An Improved Detection Method for Zero Quantized Blocks on H.264/AVC | Bo-Jhih Chen and Shen-Chuan Tai | |||
Robust Motion-Compensated Orthogonal Video Coding Using EBCOT | Ousmane Barry, Du Liu, Stefan Richter, and Markus Flierl |
12:25-01:30 | Lunch |
Day 2 | Afternoon | |||
Short Oral 4 (+Poster) | 01:30-02:30 | Image/Video Processing | Session chair:Ramakrishna Kakarala, Nanyang Technological University | |
Group Segmentation During Object Tracking Using Optical Flow Discontinuities
|
Simon Denman, Clinton Fookes, and Sridha Sridharan | |||
Modeling and Detection of Blurred Illumination Edges
|
Cheng Wen, Chih-Hung Huang, and Kuang-Chiung Chang | |||
High-quality Non-blind Image Deconvolution
|
Jong-Ho Lee and Yo-Sung Ho | |||
SAR Image Speckle Noise Suppression based on DFB Hidden Markov Models Using Immune Clonal Selection Thresholding
|
Haiyan Jin and Xueming Sun | |||
Hierarchal Predefined Codebook for High-Frequency Component Augmentation Image Enlargement
|
Hakaru Tamukoh, Hideaki Kawano, Noriaki Suetake, Masatoshi Sekine, Byungki Cha, and Takashi Aso | |||
Blurred Image Registration by Combined Invariant of Legendre Moment and Harris-Laplace Detector
|
Xiubin Dai, Hui Zhang, Huazhong Shu, Limin Luo, and Tianliang Liu | |||
A hierarchical multi-classifier Framework for Landform Segmentation Using Multi-spectral Satellite Images - A case study over the Indian subcontinent
|
Utthara Gosa Mangai, Suranjana Samanta, Sukhendu Das, Pinaki Roy Chowdhury, Koshy Varghese, and Manisha Kalra | |||
Fast, High-Quality Line Antialiasing by Prefiltering with an Optimal Cubic Polynomial
|
Jan Wassenberg | |||
Adaptive Weighting Scheme for Edge-based Line Interpolation
|
Sang-Jun Park, Changki Min, Jechang Jeong, and Gwanggil Jeon | |||
Fast and Enhanced Algorithm for Exemplar Based Image Inpainting
|
Anupam, Pulkit Goyal, and Sapan Diwakar | |||
DWT and TSVQ-based Semi-fragile Watermarking Scheme for Tampering Detection in Remote Sensing Images
|
Jordi Serra-Ruiz and David Megías | |||
Color to Gray: Attention Preservation
|
Yezhou Yang, Mingli Song, Jiajun Bu, Chun Chen, and Cheng Jin |
Oral 4 | 02:30-03:50 | Object Detection and Recognition | Session chair:Yousun Kang, National Institute of Informatics |
Cascade of Complementary Features for Fast and Accurate Pedestrian Detection | Alaa Leithy, Mohamed N. Moustafa, and Ayman Wahba | ||
Object Recognition in 3D Scenes with Occlusions and Clutter by Hough Voting | Federico Tombari and Luigi Di Stefano | ||
Object Extraction Using Novel Region Merging and Multidimensional Features | Tanima Dutta, Debi Prosad Dogra, and Biswapati Jana | ||
Head Pose Classification from Low Resolution Images Using Pairwise Non-Local Intensity and Color Differences | Teera Siriteerakul, Daisuke Sugimura, and Yoichi Sato |
03:50-04:10 | Break 4 |
Oral (SP 2) | 04:10-05:30 | Multimedia Browsing and Understanding | Session chair:Reinhard Klette, The University of Auckland | |
Attention Based Album Slideshow | Huiying Liu, Qingming Huang, and Shuqiang Jiang | |||
Compact Codebook Generation Towards Scale-Invariance | Si Liu, Shuicheng Yan, Changsheng Xu, and Hanqing Lu | |||
Video Concept Detection Using Support Vector Machine with Augmented Features | Xinxing Xu, Dong Xu, and Ivor W. Tsang | |||
Automatic Image Annotation Using Multi-Object Identification | Yin-Fu Huang and Hsin-Yun Lu |
07:00-09:00 | Banquet |
Day 3> | Morning | 17-Nov-2010 (Wensday) | ||
Oral 5 | 09:00-10:20 | Super-resolution and Image Enhancement | Session chair: Shuicheng Yan, National University of Singapore | |
Selecting High Quality Frames for Super Resolution Reconstruction Using Perceptual Quality Metrics | Amit Prabhudesai, Ajit Bopardikar, and Chandra Sekhar Reddy | |||
Blind Super-resolution for Single Image Reconstruction | Fei Han, Xiangzhong Fang, and Ci Wang | |||
Image Enlargement with Lost High-Frequency Components Estimation Using Clustered Eigenspace-BPLP | Hideaki Orii, Hideaki Kawano, Noriaki Suetake, and Hiroshi Maeda | |||
Adaptive Histogram Analysis for Image Enhancement | Qieshi Zhang, Hirosi Inaba, and Sei-ichiro Kamata |
10:20-10:40 | Break 5 |
Oral 6 | 10:40-12:00 | Image Enhancement and Image Filter | Session chair: Akihiro Sugimoto, National Institute of Informatics | |
On the Transfer of Painting Style to Photographic Images through Attention to Colour Contrast | Xiaoyan Zhang, Martin Constable, and Ying He | |||
Color Image Enhancement in HSV Space Using Nonlinear Transfer Function and Neighborhood Dependent Approach with Preserving Details | Deepak Ghimire and Joonwhoan Lee | |||
Threshold Tuning of Switching Median Filter Employing Distribution Distance | Ryosuke Kubota and Noriaki Suetake | |||
Descreening Using HOG-based Adaptive Smoothing Filter | Kyu-Sung Hur, Yeul-Min Baek, and Whoi-Yul Kim |
12:00-13:00 | Lunch |
Day 3 | Afternoon | |||
Oral 7 | 13:00-02:20 | Video Surveillance | Session chair: Terence Sim, National University of Singapore | |
Tracking Groups of People in Presence of Occlusion | Hamed Kiani Galoogahi | |||
Motion Detection for Rapidly Moving Cameras in Fully 3D Scenes | Dong Zhang and Ping Li | |||
Video Surveillance Traffic Analysis Using Scene Geometry | M. Brulin, H. Nicolas, and C. Maillet | |||
Moving Objects Detection and Tracking Framework for UAV-Based Surveillance | Aryo Wiman Nur Ibrahim, Pang Wee Ching, G.L. Gerald Seet, W.S. Michael Lau, and Witold Czajewski |
Oral (SP 3) | 02:20-03:40 | Image/Video Technology Meets Art | Session chair: Kap Luk Chan, Nanyang Technological University |
Artistic Emulation - Filter Blending for Painterly Rendering | Crystal Valente and Reinhard Klette | ||
What Makes Motion Meaningful? Exploring the Affective Properties of Abstract Motion | Lyn Bartram and Ai Nakatani | ||
Depth-Aware Video Abstraction | Jianbing Shen and Ying He | ||
Depth-based Analyses of Landscape Paintings and Photographs According to Itten's Contrasts | Martin Constable and Xiaoyan Zhang |
03:40-04:00 | Break 6 |
Oral (SP 4) | 04:00-05:20 | Graphics and Visualization | Session chair: He Ying, Nanyang Technological University |
Sophisticated Construction and Search of 2D Motion Graphs for Synthesizing Videos | Jun Kobayashi, Chongke Bi, and Shigeo Takahashi | ||
Real-Time GPU-Aided Lung Tumor Tracking | Yin Yang, Zichun Zhong, Guodong Rong, Xiaohu Guo, Jing Wang, Timothy Solberg, and Weihua Mao | ||
Subband Architecture Based Exposure Fusion | Ying Zhao, Jianbing Shen, and Ying He | ||
Detail Preserving 3D Motion Compression based on Local Transformation | Chang Liu, Zhaoqiang Lai, Jiaxi Hu, and Jing Hua |
END |