Sunday, September 11
09:00 - 12:30
Tutorial Sessions
Chairs: Ton Kalker (Huawei, USA), Jean-Philippe Thiran (École Polytechnique Fédérale de Lausanne, Switzerland)
- Image and Video Analysis using Local Binary Pattern Variants
- Room: 214/216
- Convex Optimization Methods for Image Processing
- Room: 213/215
- Image Analysis in Very High Resolution Optical Remote Sensing
- Room: 211/212
14:00 - 17:30
Tutorial Sessions
Chairs: Ton Kalker (Huawei, USA), Jean-Philippe Thiran (École Polytechnique Fédérale de Lausanne, Switzerland)
- Spatio-temporal Filtering for Multi-object Tracking in Image Sequences
- Room: 213/215
- ToF (Time of Flight) Depth Sensor Image Processing: from Principle to Applications
- Room: 214/216
Monday, September 12
08:30 - 09:00
Opening Ceremony
Room: Gold Hall
09:00 - 10:00
HUMAN MEDIA INTERACTION: Seeing and the Brain
Room: Gold Hall
Chairs: Ann Dooms (Vrije Universiteit Brussel, Belgium), Laurent Jacques (Université catholique de Louvain, Belgium)
 |
Lecturer: Brian Wandell (Stanford University, USA) |
Abstract:
For the past twenty-five
years scientists and engineers have collaborated on a wide variety of
hardware and image processing methods to better image and understand
the brain. These technologies have clarified structures and functions
over an enormous range of spatial and temporal scales, from molecules
to whole brain. One of the important technologies is magnetic resonance
imaging (MRI), which is a non-invasive means for measuring both
activity and structure in the living human brain. Many of the
achievements in human neuroimaging with MRI can be traced to advances
in image and signal processing. I will review some advances in human
neuroimaging using the visual pathways, my own research area, as an
example system. While most of the human visual pathways were
inaccessible to measurement thirty years ago, today we can place a
subject in an MR scanner and measure fifteen visual field maps and
identify the white matter pathways in experiments requiring only
forty-five minutes. These measurements enable us to track brain
activity as children learn to see words, or as people perceive motion,
color and form. While we have learned a great deal from these
technologies, most MRI measurements produce images without units, and
these are analyzed qualitatively or relative to arbitrary baselines. In
the next phase of human neuroimaging we will need to create image
processing tools that are coupled to biological quantities by models.
The generic image processing methods we use now will be replaced by methods that are based on physical models of the measurement instrument and tissue properties. The quantitative image processing may enable us to learn about properties of biological tissue and expand our understanding of brain in health and disease.
Joint work with Michal Ben-Shachar, Alyssa Brewer, Robert Dougherty, Kendrick Kay, Aviv Mezer, L. Michael Perry, Jon Winawer, and Jason Yeatman
The generic image processing methods we use now will be replaced by methods that are based on physical models of the measurement instrument and tissue properties. The quantitative image processing may enable us to learn about properties of biological tissue and expand our understanding of brain in health and disease.
Joint work with Michal Ben-Shachar, Alyssa Brewer, Robert Dougherty, Kendrick Kay, Aviv Mezer, L. Michael Perry, Jon Winawer, and Jason Yeatman
Biography:
Brian A. Wandell is the
first Isaac and Madeline Stein Family Professor. He joined the Stanford
Psychology faculty in 1979 and is a member, by courtesy, of Electrical
Engineering, Ophthalmology, and Radiology.
Wandell is Director of the center of Cognitive and Neurobiological Imaging (CNI). His research projects center on how we see, spanning topics from visual disorders, reading development in children, to digital imaging devices and algorithms.
Educational background. Wandell graduated from the University of Michigan in 1973 with a B.S. in mathematics and psychology. In 1977, he earned a Ph.D. in social science from the University of California at Irvine. After a year as a postdoctoral fellow at the University of Pennsylvania, he joined the faculty of Stanford University in 1979. Professor Wandell was promoted to associate professor with tenure in 1984 and became a full professor in 1988.
Neuroscience Wandell's work in visual neuroscience uses functional and structural MRI along with behavior testing and modeling to understand the action of the visual portions of the brain. His research includes studies of the organization of the visual field maps in the human brain, color and motion processing within these maps, and the potential for reorganization following injury or developmental disorders.
The Wandell lab develops tools for diffusion imaging and functional MRI. Recent years they have carried out a series of studies on brain plasticity and development. In one example, they are carrying out a longitudinal study measuring the development of structures and signals in visual cortex in children, aged 8-12, as they become skilled readers. The lab's measurements of developmental changes during the acquisition of skilled reading are intended to understand how visual signals become rapidly identified and classified in the process of learning to read.
Digital imaging. Brian Wandell's research includes image system engineering and visual neuroscience. In cooperation with Professor Emeritus Joseph Goodman (a faculty member in Stanford's School of Engineering), Professor Wandell founded the university's Stanford Center for Image Systems Engineering Program. As part of this research, Wandell and his team study and build devices used for digital imaging, including image sensors, high dynamic range displays, and software simulations of the digital imaging pipeline.
Teaching. Brian Wandell's teaching at Stanford reflects his multiple areas of expertise. He has taught courses on behavior, perception, cognitive and behavioral neuroscience, image systems and computational He has also led classes on color science and computer applications for engineers and managers from more than 200 companies. In addition to numerous scientific articles, Brian Wandell is the author of the vision science textbook Foundations of Vision. He is an associate editor of the Journal of Vision, the Journal of Neuroscience and Neural Networks. He has served as a consultant and technical advisor for a number of corporations and has patented some of the products of his work.
Wandell is Director of the center of Cognitive and Neurobiological Imaging (CNI). His research projects center on how we see, spanning topics from visual disorders, reading development in children, to digital imaging devices and algorithms.
Educational background. Wandell graduated from the University of Michigan in 1973 with a B.S. in mathematics and psychology. In 1977, he earned a Ph.D. in social science from the University of California at Irvine. After a year as a postdoctoral fellow at the University of Pennsylvania, he joined the faculty of Stanford University in 1979. Professor Wandell was promoted to associate professor with tenure in 1984 and became a full professor in 1988.
Neuroscience Wandell's work in visual neuroscience uses functional and structural MRI along with behavior testing and modeling to understand the action of the visual portions of the brain. His research includes studies of the organization of the visual field maps in the human brain, color and motion processing within these maps, and the potential for reorganization following injury or developmental disorders.
The Wandell lab develops tools for diffusion imaging and functional MRI. Recent years they have carried out a series of studies on brain plasticity and development. In one example, they are carrying out a longitudinal study measuring the development of structures and signals in visual cortex in children, aged 8-12, as they become skilled readers. The lab's measurements of developmental changes during the acquisition of skilled reading are intended to understand how visual signals become rapidly identified and classified in the process of learning to read.
Digital imaging. Brian Wandell's research includes image system engineering and visual neuroscience. In cooperation with Professor Emeritus Joseph Goodman (a faculty member in Stanford's School of Engineering), Professor Wandell founded the university's Stanford Center for Image Systems Engineering Program. As part of this research, Wandell and his team study and build devices used for digital imaging, including image sensors, high dynamic range displays, and software simulations of the digital imaging pipeline.
Teaching. Brian Wandell's teaching at Stanford reflects his multiple areas of expertise. He has taught courses on behavior, perception, cognitive and behavioral neuroscience, image systems and computational He has also led classes on color science and computer applications for engineers and managers from more than 200 companies. In addition to numerous scientific articles, Brian Wandell is the author of the vision science textbook Foundations of Vision. He is an associate editor of the Journal of Vision, the Journal of Neuroscience and Neural Networks. He has served as a consultant and technical advisor for a number of corporations and has patented some of the products of his work.
10:15 - 12:50
MA.L1: Modern Shape from Shading and Beyond (Special Session)
Room: Silver Hall
Chair: Michael Breuss (Saarland University, Germany)
- 10:15 Modern Shape From Shading and Beyond
- 10:35 odels for Shape From Shading
- 10:55 Break
- 11:30 Shape From Shading with Specular Highlights: Analysis of the Phong Model
- 11:50 Shape-from-shading Under Complex Natural Illumination
- 12:10 Reconstruction of non-Lambertian Surfaces by Fusion of Shape From Shading and Active Range Scanning
- 12:30 Shape From Specular Reflection in Calibrated Environments and the Integration of Spatial Normal Fields
MA.L2: Structural Models (Lecture)
Room: 211/212
Chair: Jalal Fadili (GREYC CNRS UMR 6072, ensicaen, France)
- 10:15 Joint Pose Estimation and Action Recognition in Image Graphs
- 10:35 Inferring 3D Body Pose Using Variational Semi-parametric Regression
- 10:55 Break
- 11:30 Automatic Target Recognition Using Discriminative Graphical Models
- 11:50 A Belief Propagation Algorithm for Bias Field Estimation and Image Segmentation
- 12:10 Planarity-Enforcing Higher-Order Graph Cut
- 12:30 Learning Structural Conjunction of Image Content by Sparse Graphical Model
MA.L3: Biomedical Image Analysis (Lecture)
Room: 214/216
Chair: Brian C Lovell (NICTA, Australia)
- 10:15 Automatic Quality Enhancement and Nerve Fibre Layer Artefacts Removal in Retina Fundus Images by Off Axis Imaging
- 10:35 Advanced Statistical Matrices for Texture Characterization: Application to DNA Chromatin and Microtubule Network Classification
- 10:55 Break
- 11:30 Comparison of Energy Minimization Methods for 3-D Brain Tissue Classification
- 11:50 Clump Splitting Via Bottleneck Detection
- 12:10 Texture Classification of Scarred and Non-Scarred Myocardium in Cardiac MRI Using Learned Dictionaries
- 12:30 Automatic IVUS Media-Adventitia Border Extraction Using Double Interface Graph Cut Segmentation
MA.L4: Nonlinear and Linear Filtering (Lecture)
Room: 213/215
Chair: Dinei Florencio (Microsoft Research, USA)
- 10:15 Non-Linearization of Free Schrodinger Equation and Pseudo-Morphological Complex Diffusion Operators
- 10:35 Adaptive Filtering of Raster Map Images Using Optimal Context Selection
- 10:55 Break
- 11:30 FM Processing with Generalized Amplitude & Phase: Application to Modulation Domain Geometric Image Transformations
- 11:50 Approximating Image Filters with Box Filters
- 12:10 Cosine Integral Images for Fast Spatial and Range Filtering
- 12:30 An Optimal Design of FIR Filters with Discrete Coefficients and Image Sampling Application
MA.L5: Image Search and Retrieval (Lecture)
Room: The Arc
Chair: Shin'ichi Satoh (National Institute of Informatics, Japan)
- 10:15 Exploiting Contextual Information for Rank Aggregation
- 10:35 Local Geometric Consistency Constraint for Image Retrieval
- 10:55 Break
- 11:30 Generating Vocabulary for Global Feature Representation Towards Commerce Image Retrieval
- 11:50 Efficient Bag-of-Feature Kernel Representation for Image Similarity Search
- 12:10 Grid-based Local Feature Bundling for Efficient Object Search and Localization
- 12:30 Multiple Dictionaries for Bag of Words Large Scale Image Search
MA.L6: 3D Coding and Representation (Lecture)
Room: Hall 300
Chair: Anthony Vetro (Mitsubishi Electic Research Laboratories, USA)
- 10:15 Block-Adaptive Palette-based Prediction for Depth Map Coding
- 10:35 Region-based Adaptive Bilateral Filter in Depth Map Coding
- 10:55 Break
- 11:30 Object-based Layered Depth Images for Improved Virtual View Synthesis in Rate-Constrained Context
- 11:50 Transform Domain Sparsification of Depth Maps Using Iterative Quadratic Programming
- 12:10 Sparse Stereo Image Coding with Learned Dictionaries
- 12:30 Efficient Compression Method for Integral Images Using Multi-view Video Coding
MA.L7: Error Resilience and Channel Coding for Image & Video Systems (Lecture)
Room: 311/312
Chair: Aggelos K Katsaggelos (Northwestern University, USA)
- 10:15 Belief Consensus for Distributed Action Recognition
- 10:35 Content-Aware Utility-Fair Video Streaming in Wireless Broadcasting Networks
- 10:55 Break
- 11:30 Resource Management for Wireless Visual Sensor Networks Based on Individual Video Characteristics
- 11:50 Tracking-Optimized Quantization for H.264 Compression in Transportation Video Surveillance Applications
- 12:10 Dynamic GOP Size Control for Low Delay Distributed Video Coding
- 12:30 Optimal Image Transmission Over Visual Sensor Networks
MA.L8: Radar Imaging and Remote Sensing (Lecture)
Room: 314/316
Chair: Sabine Süsstrunk (EPFL, Switzerland)
- 10:15 Bayesian TV Denoising of SAR Images
- 10:35 SAR Image Classification with Non-stationary Multinomial Logistic Mixture of Amplitude and Texture Densities
- 10:55 Break
- 11:30 Sparsity-driven Image Formation and Space-variant Focusing for SAR
- 11:50 Incremental Evolution of Collective Network of Binary Classifier for Polarimetric SAR Image Classification
- 12:10 Multispectral Interest Points for RGB-NIR Image Registration
- 12:30 Contrast Enhancement and Denoising of Poisson and Gaussian Mixture Noise for Solar Images
MA.PA: Image & Video Representation - Perception and Quality Models for Images & Video (Poster)
Room: Grand Hall 2
Chair: Junyong You (Norwegian University of Science and Technology, Norway)
- An Incremental/Decremental Delaunay Mesh-Generation Framework for Image Representation
- A Symmetric KL Divergence Based Spatiogram Similarity Measure
- Online Sparse Learning Utilizing Multi-Feature Combination for Image Classification
- Evaluation Framework on Translation-Invariant Representation for Cumulative Foot Pressure Image
- Image Pattern Discovery by Using the Spatial Closeness of Visual Code Words
- Action Recognition Using Correlogram of Body Poses and Spectral Regression
- A Discriminative Learning Technique for Mobile Landmark Recognition
- SSIM-based Non-local Means Image Denoising
- Biologically Motivated Feature Extraction Using the Spiral Architecture
- Accurate Distortion Measurement for B-Spline-Based Shape Coding
- Abnormal Motion Selection in Crowds Using Bottom-Up Saliency
- Motion Trajectory Based Visual Saliency for Video Quality Assessment
- Perceptual Noise Shaping in Dual-Tree Complex Wavelet Transform for Image Coding
- Fractal Image Coding Using SSIM
MA.PB: Multi-Resolution Methods for Image Processing (Poster)
Room: Grand Hall 2
Chair: Rashid Ansari (University of Illinois at Chicago, USA)
- Block-Lifting Factorization of M-Channel Biorthogonal Filter Banks with an Arbitrary McMillan Degree
- Multiscale Directional AM-FM Demodulation of Images Using a 2D Optimized Method
- Design of Q-Shift Filters with Improved Vanishing Moments for DTCWT
- Natural Scene Statistics of Color and Range
- Biologically-Inspired Object Recognition System with Features From Complex Wavelets
- Multiple Blind Re-Watermarking with Quantisation-Based Embedding
- Multi-resolution Level Set Image Segmentation Using Wavelet
- Color Monogenic Wavelets for Image Analysis
- An Effective Approach to Corner Point Detection Through Multiresolution Analysis
- Frequency Guided Bilateral Symmetry Gabor Wavelet Network
- A Scale-Space Based Hierarchical Representation of Discrete Data
MA.PC: Image Coding (Poster)
Room: Grand Hall 2
Chair: Joao Ascenso (ISEL & IT, Portugal)
- Random Permutations Based Block Compressive Sensing for Image Compression Applications
- Online Dictionaries for Image Prediction
- Wavelet-Based Quality Constrained Compression Using Binary Search
- Low-Complexity Image Coder/Decoder with an Approaching-Entropy Quad-Tree Search Code for Embedded Computing Platforms
- Preserving Sift Features in Jpeg-Encoded Images
- Very Low-Complexity Coding of Images Using Adaptive modulo-PCM
- Visually Lossless JPEG2000 At Fractional Resolutions
- JPEG XR Optimization with Graph-Based Soft Quantization
- Efficient Wavelet Packet Basis Selection in JPEG2000
- Decoder-Side Dimensionality Determination for Compressive-Projection Principal Component Analysis of Hyperspectral Data
- Improved Entropy Coding for Component-Based Image Coding
- 3D-PMDC: A Parallelized Morphological Wavelet Codec for 3D Medical Datasets and Teleradiology Applications
- Probability Interval Partitioning Entropy Coding Using Systematic Variable-to-variable Length Codes
- An Adaptable Spatial-Temporal Error Concealment Method for Multiple Description Coding Based on Error Tracking
- Coupled Distributed Arithmetic Coding
MA.PD: Hardware and GPU Issues in Video / High Dynamic Range Imaging and Shape Estimation (Poster)
Room: Grand Hall 2
Chair: Oscar Au (HKUST, Hong Kong)
- Curve-Based and Image-based JND Contrast Analysis for Inverse Tone Mapping Operators
- Hybrid Light Coding for Fast and High-accuracy Shape Acquisition
- Motion Artifact-free HDR Imaging Under Dynamic Environments
- Geometrical Transformation-Based Ghost Artifacts Removing for High Dynamic Range Image
- Fully Automated Exposure Fusion Algorithm for Mobile Platforms
- Fast Movement Detection for High Dynamic Range Imaging
- One-Round Renormalization Based 2-bin/Cycle H.264/AVC CABAC Encoder
- An Efficient VLSI Architecture for 4×4 Intra Prediction in the High Efficiency Video Coding (HEVC) Standard
- Ultra High Definition Video Decoding with Motion JPEG XR Using the GPU
- H.264/AVC UHD Decoder Implementation on Multi-Cluster Platform Using Hybrid Parallelization Method
- A Novel Energy Reduction Technique for H.264 Intra Mode Decision
- Fast FPGA-Based Architecture for Pedestrian Detection Based on Covariance Matrices
- A High-Throughput Parallel Hardware Architecture for H.264/AVC CAVLC Encoding
- ReVC: Computationally Reliable Video Coding on Unreliable Hardware Platforms: A Case Study on Error-Tolerant H.264/AVC CAVLC Entropy Coding
MA.PE: CT Image Processing Methods (Poster)
Room: Grand Hall 2
Chair: Yongyi Yang (Illinois Institute of Technology, USA)
- Synthetic OCT Data for Image Processing Performance Testing
- A Comparative Evaluation of Ring Artifacts Reduction Filters for X-ray Computed Microtomography Images
- A Novel Alternative Algorithm for Limited Angle Tomography
- A Novel Coupled Transmission-Reflection Tomography and the V-line Radon Transform
- PET Image Reconstruction: GPU-Accelerated Particle Filter Framework
- Sensitivity to Error of the Truncated Hilbert Transform Technique for Interior Reconstruction
- Interactive CT Image Segmentation with Online Discriminative Learning
- An Algorithm for Simultaneous Image Segmentation and Nonrigid Registration, with Clinical Application in Image Guided Radiotherapy
- Integrated Framework for Simultaneous Segmentation and Registration of Carpal Bones
- Automated Delineation of Tree-Rings in X-ray Computed Tomography Images of Wood
- Multiscale Sparse Representation of High-Resolution Computed Tomography (HRCT) Lung Images for Diffuse Lung Disease Classification
- Modeling a Parallelism Constraint in Active Contours. Application to the Segmentation of Eye Vessels and Retinal Layers
- Sparsity-based Retinal Layer Segmentation of Optical Coherence Tomography Images
- Direct Reconstruction of Parametric Images From Cardiac Gated Dynamic SPECT Data
- Effects of Piecewise Smoothing on Cardiac SPECT Reconstruction
- A New 3D Paradigm for Metal Artifact Reduction in Dental CT
MA.PF: Tracking (Poster)
Room: Grand Hall 2
Chair: R. (Inald) L. Lagendijk (Delft University of Technology, The Netherlands)
- An Improved Occlusion Handling for Appearance-Based Tracking
- A Snake Algorithm for Automatically Tracking Multiple Objects
- Mean-shift Tracking Algorithm with Weight Fusion Strategy
- Complementary Visual Tracking
- A Cost Function Approach for Multi-Human Tracking
- Robust Visual Tracking Via Transfer Learning
- Visual Tracking Using Compensated Motion Model for Mobile Cameras
- Region Tracking with Narrow Perception of Background
- Adaptive Multi-Resolution CRF-based Contour Tracking
- Monte Carlo Sampling for Visual Pose Tracking
- SnooperTrack: Text Detection and Tracking for Outdoor Videos
- Robust Visual Tracking Via Context Objects Computing
- Particle-Based Tracking Model for Automatic Anomaly Detection
- Robust Visual Tracking Via Ranking SVM
- Vanishing Point-Based Line Sampling for Efficient Axis-Based People Localization
MA.PG: Preprocessing and Features for Biometrics (Poster)
Room: Grand Hall 2
Chair: Jian Zhang (The University of New South Wales & NICTA, Australia)
- A Markerless Motion Capture System with Automatic Subject-Specific Body Model Acquisition and Robust Pose Tracking From 3D Data
- Robust Body Parts Tracking Using Particle Filter and Dynamic Template
- Action Recognition Using Partial Least Squares and Support Vector Machines
- Augmented Fingerprint Minutiae Vicinity
- Multi-view Multi-stance Gait Identification
- Speed-Invariant Gait Recognition Based on Procrustes Shape Analysis Using Higher-Order Shape Configuration
- Hybrid Hand Tracking System
- Exploiting Color SIFT Features for 2D Ear Recognition
- GPU-based Face Tracking At 500 Fps
- A Comparison of Techniques for Robust Gender Recognition
- Multi-task GLOH Feature Selection for Human Age Estimation
- Pose Invariant Facial Component Landmark Detection
- Spatial and Probabilistic Codebook Template Based Head Pose Estimation From Unconstrained Environments
- Newton Optimization Based Congealing for Facial Image Alignment
14:20 - 17:35
MP.L1: Compression of High-Dimensional Media Data for Interactive Navigation (Special Session)
Room: Silver Hall
Chairs: Gene Cheung (National Institute of Informatics, Japan), Vladan Velisavljevic (Deutsche Telekom Laboratories, Germany)
- 14:20 Efficient Communication of Video Using Metadata
- 14:40 Mapping Data on a Rotated Grid in High-dimensions for Lossless Compression
- 15:00 Interactive Multiview Video System with Low Decoding Complexity
- 15:20 Frame Structure Optimization for Interactive Multiview Video Streaming with Bounded Network Delay
- 15:40 break
- 16:15 Using Distributed Source Coding and Depth Image Based Rendering to Improve Interactive Multiview Video Access
- 16:35 Interactive Multiview Image Coding
- 16:55 A Trellis-based Approach for Robust View Synthesis
- 17:15 Adaptive pixel/patch-based Synthesis for Texture Compression
MP.L2: Image & Video Sensing (Lecture)
Room: 211/212
Chair: Homer Chen (National Taiwan University, Taiwan)
- 14:20 Single Image Local Blur Identification
- 14:40 Lens Distortion Correction with a Calibration Harp
- 15:00 Effective Autofocus Decision Using Reciprocal Focus Profile
- 15:20 Automatic Video Deshearing for Skew Sequences Captured by Rolling Shutter Cameras
- 15:40 break
- 16:15 Robust Video Stabilization Approach Based on a Voting Strategy
- 16:35 An Auto-Focus Sharpness Function for Stereo Image Pairs
- 16:55 Calibration of Central Catadioptric Camera with One-Dimensional Object Undertaking General Motions
- 17:15 Paracatadioptric Camera Calibration Using Sphere Images
MP.L3: Saliency and Object Recognition (Lecture)
Room: 214/216
Chair: Riccardo Leonardi (University of Brescia, Italy)
- 14:20 Visual Saliency Detection Based on Bayesian Model
- 14:40 High Resolution Biologically Inspired Salient Region Detection
- 15:00 Simultaneous Detection and Segmentation for Generic Objects
- 15:20 Sparse Representation Based Visual Element Analysis
- 15:40 break
- 16:15 Spatial Coordinate Coding to Reduce Histogram Representations, Dominant Angle and Colour Pyramid Match
- 16:35 Multivariate log-Gaussian Cox Models of Elementary Shapes for Recognizing Natural Scene Categories
- 16:55 Improving Image Similarity with Vectors of Locally Aggregated Tensors
- 17:15 Recognizing 3D Objects in Cluttered Scenes Using Projection Images
MP.L4: Image Restoration (Lecture)
Room: 213/215
Chair: Jorge S. Marques (Instituto Superior Técnico & Instituto de Sistemas e Robotica, Portugal)
- 14:20 Single Image Spatially Variant Out-Of-Focus Blur Removal
- 14:40 Patch-based Image Deconvolution Via Joint Modeling of Sparse Priors
- 15:00 Variational Image Restoration Based on Poisson Singular Integral and Curvelet-Type Decomposition Space Regularization
- 15:20 Two Constrained Formulations for Deblurring Poisson Noisy Images
- 15:40 break
- 16:15 A Convex Minimization Model in Image Restoration Via One-Dimensional Sobolev Norm Profiles
- 16:35 Adaptive Regularization for Multiple Image Restoration Using an Extended Total Variations Approach
- 16:55 A New Image Deblurring Algorithm with Less Ringing Artifacts Via Error Variance Estimation and Soft Decision
- 17:15 A Second-order Extension of TV Regularization for Image Deblurring
MP.L5: Best Student Paper Award Session (Lecture)
Room: The Arc
Chairs:
Pascal Frossard (Swiss Federal Institute of Technology - EPFL,
Switzerland), Béatrice Pesquet (Ecole Nationale Supérieure des
Télécommunications, France)
- 14:20 2D to 3D Conversion of Sports Content Using Panoramas
- 14:40 Countering JPEG Anti-Forensics
- 15:00 Online Dictionaries for Image Prediction
- 15:20 Convex Approaches to Model Wavelet Sparsity Patterns
- 15:40 break
- 16:15 Video Encoder Based on Lifting Transforms on Graphs
- 16:35 Salient Covariance for Near-duplicate Image and Video Detection
- 16:55 Cosine Integral Images for Fast Spatial and Range Filtering
- 17:15 Patch-based Locally Optimal Denoising
14:20 - 17:15
MP.L6: Biomedical Image Shape Segmentation (Lecture)
Room: Hall 300
Chair: David Dagan Feng (University of Sydney & Hong Kong Polytechnic University, Australia)
- 14:20 Learning-Based Non-Rigid Image Registration Using Prior Joint Intensity Distributions with Graph-Cuts
- 14:40 Putting Images on a Manifold for Atlas-based Image Segmentation
- 15:00 A Probabilistic Framework for Automatic Prostate Segmentation with a Statistical Model of Shape and Appearance
- 15:20 A New Shape Based Segmentation Framework Using Statistical and Variational Methods
- 15:40 break
- 16:15 Segmenting Human Knee Cartilage Automatically From Multi-contrast MR Images Using Support Vector Machines and Discriminative Random Fields
- 16:35 A Fuzzy Framework with Prior Information Unifying Registration, Segmentation, and Bias Field Correction of Brain MRI
- 16:55 Elastic Shape Registration Using an Incremental Free Form Deformation Approach with the ICP Algorithm
MP.L7: Reduced-Complexity Video Coding (Lecture)
Room: 311/312
Chair: Andrew Segall (Sharp Labs, USA)
- 14:20 HEVC ALF Decode Complexity Analysis and Reduction
- 14:40 Low Complexity Deblocking Filter Perceptual Optimization for the HEVC Codec
- 15:00 Complexity-Aware Adaptive Spatial Pre-Processing for Roi Scalable Video Coding with Dynamic Transition Region
- 15:20 Video Compression Complexity Reduction with Adaptive Down-Sampling
- 15:40 break
- 16:15 A Multi-Level Dynamic Complexity Reduction Scheme for Multiview Video Coding
- 16:35 Reduced-complexity Entropy Coding of Transform Coefficient Levels Using Truncated Golomb-Rice Codes in Video Compression
- 16:55 Frame Buffer Compression for Low-power Video Coding
14:20 - 17:35
MP.L8: Face Recognition (Lecture)
Room: 314/316
Chair: Alberto Albiol (Universidad Politecnica de Valencia, Spain)
- 14:20 Locality-constrained Group Sparse Representation for Robust Face Recognition
- 14:40 Face Recognition Using Multi-Scale Local Phase Quantisation and Linear Regression Classifier
- 15:00 MAP-MRF Based Lip Segmentation Without True Segment Number
- 15:20 3D Facial Expression Recognition Using Zernike Moments on Depth Images
- 15:40 break
- 16:15 Illumination Robust Dictionary-based Face Recognition
- 16:35 Face Tracking in Low Resolution Videos Under Illumination Variations
- 16:55 Color HOG-EBGM for Face Recognition
- 17:15 Feature Selection Via Simultaneous Sparse Approximation for Person Specific Face Verification
MP.PA: Geometry Texture and Object-based Representation (Poster)
Room: Grand Hall 2
Chair: Trac D. Tran (Johns Hopkins University, USA)
- Tensor-Directed Simulation of Strokes for Image Stylization with Hatching and Contours
- Pattern Recognition by Affine Legendre Moment Invariants
- Spatiogram Features to Characterize Pearls in Paintings
- Anisotropic and Spatio-Temporal Extension of Color ETV Based Decomposition Model
- MPL-Boosted Integrable Features Pool for Pedestrian Detection
- A Combined Texture-Shape Descriptor for Enhanced 3D Feature Matching
- Moving Object Selection Based on an Active Curve Approach
- Image Analysis Using Separable Two-Dimensional Discrete Orthogonal Moments
- Ensemble of Furthest Subspace Pairs for Enhanced Image Set Matching
- From Universal Bag-of-Words to Adaptive Bag-of-Phrases for Mobile Scene Recognition
- Generic Polar Harmonic Transforms for Invariant Image Description
- Combining Sorted Random Features for Texture Classification
- LSP: Local Similarity Pattern, a New Approach for Rotation Invariant Noisy Texture Analysis
- Local Binary Pattern Histogram Based Texton Learning for Texture Classification
- Fast Facial Landmark Detection Using Cascade Classifiers and a Simple 3D Model
MP.PB: 3D Modeling and Synthesis (Poster)
Room: Grand Hall 2
Chair: Kiyoharu Aizawa (University of Tokyo, Japan)
- Intrinsic Geometric Distortions in a Type of Multi-Projector Light Field Display
- Optimal Conditions for Camera Calibration Using a Planar Template
- Zhang's One-Dimensional Calibration Revisited with the Heteroscedastic Error-In-Variables Models
- Blind Correction of Lens Aberration Using Zernike Moments
- Semi-Automatic 2D to 3D Image Conversion Using Scale-Space Random Walks and a Graph Cuts Based Depth Prior
- Dense Interpolation of 3D Points Based on Surface and Color
- Robust Albedo Estimation From a Facial Image with Cast Shadow
- Generating Compact Meshes Under Planar Constraints: An Automatic Approach for Modeling Buildings From Aerial LiDAR
- Patch-Sweeping with Robust Prior for High Precision Depth Estimation in Real-Time Systems
- Marker-less Human Pose Estimation and Surface Reconstruction Using a Segmented Model
- A Dynamic Approach for Approximate Pairwise Alignment Based on 4-Points Congruence Sets of 3D Points
- Implicit B-Spline Fitting Using the 3L Algorithm
- Surface Completion of Shape and Texture Based on Energy Minimization
- Dense Point-To-Point Correspondences Between 3D Faces with Large Variations for Constructing 3D Morphable Models
- 3D Mesh Compression Based on Dual-Ring Prediction and MMSE Prediction
- Visual Pertinent 2D-to-3D Video Conversion by Multi-cue Fusion
MP.PC: Image & Video Communication (Poster)
Room: Grand Hall 2
Chair: Amy Reibman (AT&T Labs - Research, USA)
- QoE-driven Resource Optimization for User Generated Video Content in Next Generation Mobile Networks
- Secure Transcoding for Compressive Multimedia Sensing
- Scalable Compressive Video
- Synchronization of Presentation Slides and Lecture Videos Using Bit Rate Sequences
- Effect of a Synthesized Depth View on Multi-View Rendering Quality
- Capacity Improvement in eMBMS Using SVC and Layer-Aware Bearer Allocation
- Robust Video Transmission Using Pyramid Vector Quantisation
- An Improved Cross-layer Mapping Mechanism for Packet Video Delivery Over Wlan
- Fairness and QoS Guaranteed User Scheduling for Multi-user MIMO Broadcasting Channel
- Performance of H.264 with Isolated Bit Error: Packet Decode or Discard?
- Efficient Iterative Receiver for LDPC Coded Wireless IPTV System
- High Performance H.264/AVC Encoding Motion Prediction Algorithm
- Spatial Prediction Based on Self-Similarity Compensation for 3D Holoscopic Image and Video Coding
MP.PD: Stereo Processing (Poster)
Room: Grand Hall 2
Chair: Fernando Jaureguizar (Universidad Politécnica de Madrid, Spain)
- Robust Color Correction in Stereo Vision
- Accurate Depth Estimation Using Structured Light and Passive Stereo Disparity Estimation
- Cryo-Balloon Reconstruction From Two Views
- Image Rectification for Single Camera Stereo System
- Stereoscopic Vision Through Epipolarization Without Orientation Parameters
- Assisting System of Visually Impaired in Touch Panel Operation Using Stereo Camera
- Effect of Brightness on the Quality of Visual 3D Perception
- Exploiting Spatial Consistency for Object Classification and Pose Estimation
- Model-Based Multiview Stereo Via Level Sets with Statistical Shape Prior
- Joint Multi-view Foreground Segmentation and 3D Reconstruction with Tolerance Loop
- Dynamic Voxel Carving in Tennis Based on Player Localisation Using a Low Cost Camera Network
- A Convex-Optimization Approach to Dense Stereo Matching
- Two-View Geometry Estimation Using the Rodrigues Rotation Formula
- A New Fast Motion Estimation and Mode Decision Algorithm for H.264 Depth Maps Encoding in Free Viewpoint TV
MP.PE: Features for Image Analysis (Poster)
Room: Grand Hall 2
Chair: Michael H.F. Wilkinson (University of Groningen, The Netherlands)
- Bounded Multivariate Surfaces on Monovariate Internal Functions
- A Fast Component-Tree Algorithm for High Dynamic-Range Images and Second Generation Connectivity
- Corner Detection on Hexagonal Pixel Based Images
- A Novel Region-Based Active Contour Approach Relying on Local and Global Information
- A Novel Feature Descriptor Based on the Shearlet Transform
- A Robust Parametric Active Contour Based on Fourier Descriptors
- A SIFT-LBP Image Retrieval Model Based on Bag-of-Features
- A DAISY-like Compass Operator
- Ellipse Detection Using Sampling Constraints
- A Shape Contour Descriptor Based on Salience Points
- Boosting Global Scene Classification Accuracy by Discriminative Region Localization
- Color-based Lips Extraction Applied to Voice Activity Detection
- High-performance ASIC Architecture for Hysteresis Thresholding and Component Feature Extraction in Limited-Resource Applications
- Application of Complex Networks for Automatic Classification of Damaging Agents in Soybean Leaflets
- Free-Form Anisotropy: A New Method for Crack Detection on Pavement Surface Images
- Efficient Quantization of Color Sift for Image Classification
MP.PF: Image & Video Synthesis (Poster)
Room: Grand Hall 2
Chair: Muhittin Gokmen (Istanbul Technical University & Faculty of Computer and Informatics, Turkey)
- Time-Variant Modeling for General Surface Appearance
- Feature-preserving Thumbnail Generation Based on Graph Cuts
- Synthesis of Two-Dimensional Fractional Brownian Motion Via Circulant Embedding
- Bi-layer Inpainting for Novel View Synthesis
- Augmented Reality Mirror for Virtual Facial Alterations
- 2D/3D Virtual Face Modeling
- Synthesizing for Face Recognition
- Efficient Rendering Distortion Estimation for Depth Map Compression
- On the Use of Hemispherical Harmonics for Modeling Images of Objects Under Unknown Distant Illumination
- Aesthetic Enhancement of Landscape Photographs as Informed by Paintings Across Depth Layers
- Virtual Ads Insertion in Street Building Views for Augmented Reality
- Color Style Transfer by Constraint Locally Linear Embedding
- Face Sketch-Photo Synthesis Based on Support Vector Regression
- Efficient Face Hallucination by Using Shape and Texture Dependency
- Adaptive KPCA-Based Missing Texture Reconstruction Approach Including Classification Scheme Via Difference Subspaces
MP.PG: Interpolation, Resizing and Super-resolution (Poster)
Room: Grand Hall 2
Chair: Javier Mateos (University of Granada, Spain)
- Isotropic Huber MRFs for Structure Super-Resolution
- Single Image Super Resolution with High Resolution Dictionary
- Super-Resolution Interpolation with a Quasi Blur-Hypothesis
- Adaptive Incremental Video Super-Resolution with Temporal Consistency
- Superfast Superresolution
- Video Coding with Wavelet Image Size Reduction and Wavelet Super Resolution Reconstruction
- Single Image Super Resolution Via Texture Constrained Sparse Representation
- Fast Edge-Filtered Image Upsampling
- A Structure-guided Conditional Sampling Model for Video Resolution Enhancement
- Bayesian Frame Interpolation by Fusing Multiple Motion-compensated Prediction Frames
- Similarity Modulated Block Estimation for Image Interpolation
- Springs-based Simulation for Image Retargeting
- Fast and High Quality Learning-based Super-Resolution Utilizing TV Regularization Method
- A Hidden Markov Model-based Methodology for Intra-field Video Deinterlacing
- Transform Domain Semi-Super Resolution
- Efficient Super-Resolution Driven by Saliency Selectivity
Tuesday, September 13
09:00 - 10:00
ASTRONOMY: Sparsity and Astronomical Data Analysis
Room: Gold Hall
Chairs: Ann Dooms (Vrije Universiteit Brussel, Belgium), Laurent Jacques (Université catholique de Louvain, Belgium)
 |
Lecturer: Jean-Luc Starck (Service d’Astrophysique, CEA-Saclay, France) |
Abstract:
Wavelets have been very
successfull for many astronomical applications such filtering,
deconvolution, source detection or compression. Wavelets have however
some limitations when the data present anisotropic features, and other
sparse representations such as ridgelet or curvelet can also be used in
some specific applications. We will first review some of the sparsity
based methods which have been proposed and we will show how such
approaches can be used in important spatial projects such as PLANCK or
EUCLID.
Biography:
J.-L. Starck has a Ph.D. from
Nice Observatory and an Habilitation from University Paris XI. He was a
visitor
at the European Southern Observatory (ESO) in 1993, at UCLA in 2004 and
at Stanford’s statistics department in 2000 and 2005.
Since 1994, he is a researcher at Commission for Atomic Energy (CEA), France, where he is leader of the multiresolution project and a core team member of the Planck European Space Agency project. His research interests include image processing, statistical methods in astrophysics, and cosmology. Coauthor of four monographs on astronomical image analysis, and coeditor of ten conferences including Astronomical Data Analysis conferences, he is an expert in multiscale methods such as wavelets and curvelets.
Since 1994, he is a researcher at Commission for Atomic Energy (CEA), France, where he is leader of the multiresolution project and a core team member of the Planck European Space Agency project. His research interests include image processing, statistical methods in astrophysics, and cosmology. Coauthor of four monographs on astronomical image analysis, and coeditor of ten conferences including Astronomical Data Analysis conferences, he is an expert in multiscale methods such as wavelets and curvelets.
10:15 - 12:50
TA.L1: Advances in Motion Representation for Video Coding (Special Session)
Room: Silver Hall
Chairs: Andreas Krutz (Technische Universität Berlin, Germany), Thomas Sikora (Technische Universität Berlin, Germany)
- 10:15 A Block-adaptive Skip Mode for Inter Prediction Based on Parametric Motion Models
- 10:35 Fast Encoding Algorithms for Geometry-Adaptive Block Partitioning
- 10:55 break
- 11:30 Efficient Coding of Video Sequences by Non-Local In-Loop Denoising of Reference Frames
- 11:50 Generalized Interpolation for Motion Compensated Prediction
- 12:10 Picture-level Parameteric Motion Representation for Efficient Motion Compensation
- 12:30 Bi-prediction Combining Template and Block Motion Compensations
TA.L2: Sparse Representation and Sparse Coding (Lecture)
Room: 211/212
Chair: Nick Geoffrey Kingsbury (University of Cambridge, United Kingdom)
- 10:15 Learning Complex Image Patterns with Scale and Shift Invariant Sparse Coding
- 10:35 On Sparse Representations of Color Images
- 10:55 break
- 11:30 Hyperspectral Image Classification Via Kernel Sparse Representation
- 11:50 Improved Sparse Coding Using Manifold Projections
- 12:10 Learning Invariant Color Features with Sparse Topographic Restricted Boltzmann Machines
- 12:30 Learning Dictionary Via Subspace Segmentation for Sparse Representation
10:15 - 12:30
TA.L3: Image Classification (Lecture)
Room: 214/216
Chair: Andrea Cavallaro (Queen Mary, University of London, United Kingdom)
- 10:15 CW-SSIM Based Image Classification
- 10:35 Tree Trunk Detection Using Contrast Templates
- 10:55 break
- 11:30 Human Skin Detection in Images by MSER Analysis
- 11:50 HMAX-S: Deep Scale Representation for Biologically Inspired Image Categorization
- 12:10 Stochastic Minimum Spanning Forest Approach for Spectral-Spatial Classification of Hyperspectral Images
10:15 - 12:50
TA.L4: Image Analysis Using Multi-Scale and Hierarchical Methods (Lecture)
Room: 213/215
Chair: Marc Antonini (I3S-CNRS-University of Nice Sophia Antipolis, France)
- 10:15 Optimized Butterfly-based Lifting Scheme for Semi-Regular Meshes
- 10:35 Hyperspectral Image Segmentation Using Binary Partition Trees
- 10:55 break
- 11:30 Testing a Multivariate Model for Wavelet Coefficients
- 11:50 3D Facial Expression Analysis by Using 2D and 3D Wavelet Transforms
- 12:10 Detecting Gestures in Medieval Images
- 12:30 Pose Estimation and Body Segmentation Based on Hierarchical Searching Tree
TA.L5: Astronomy and Cosmology (Special Session)
Room: The Arc
Chair: Yves Wiaux (EPFL, Switzerland)
- 10:15 Bayesian MAP Detection of Extragalactic Point Sources in Microwave Astronomical Images
- 10:35 Source Separation in Cosmology, From Global to Local Models
- 10:55 break
- 11:30 Data Augmentation for Galaxy Density Map Reconstruction
- 11:50 Image Processing Challenges in Weak Gravitational Lensing
- 12:10 Scale Invariant Images in Astronomy Through the Lens of Multifractal Modeling
- 12:30 Compressed Sensing for Radio Interferometric Imaging: Review and Future Direction
TA.L6: High Dynamic Range Imaging and Compression (Lecture)
Room: Hall 300
Chair: Jan Allebach (Purdue University, USA)
- 10:15 Spatially Adaptive Filtering for Registration Artifact Removal in HDR Video
- 10:35 Perception-Based High Dynamic Range Video Compression with Optimal Bit-depth Transformation
- 10:55 break
- 11:30 A Single Algorithm Combining Exposure and Focus Fusion
- 11:50 SDALA: Simultaneous Dynamic Range Compression and Local Contrast Enhancement Algorithm
- 12:10 High Dynamic Range Imaging Under Noisy Observations
- 12:30 De-ghosting of HDR Images with Double-credit Intensity Mapping
TA.L7: Interpolation and Super-resolution (Lecture)
Room: 311/312
Chair: Rafael Molina (Universidad de Granada, Spain)
- 10:15 Fast Video Interpolation/Upsampling Using Linear Motion Model
- 10:35 Parameter Estimation in Bayesian Super-Resolution Pansharpening Using Contourlets
- 10:55 break
- 11:30 Learning Context-Aware Sparse Representation for Single Image Super-Resolution
- 11:50 Multi-scale Non-Local Kernel Regression for Super Resolution
- 12:10 Two-step Super-resolution Technique Using Bounded Total Variation and Bisquare M-estimator Under Local Illumination Changes
- 12:30 Discrete Infinity Harmonic Functions: Towards a Unified Interpolation Framework on Graphs
TA.L8: Tomographic Imaging (Lecture)
Room: 314/316
Chair: Birsen Yazici (Rensselaer Polytechnic Institute, USA)
- 10:15 Sparse Reconstruction Methods for Fluorescence Diffuse Optical Tomography
- 10:35 On the Efficiency of Proximal Methods in CBCT and PET
- 10:55 break
- 11:30 Regularized Polychromatic Reconstruction for Transmission Tomography
- 11:50 A Discrete-Continuous Bayesian Model for Emission Tomography
- 12:10 Bayesian Data Fusion and Inversion in X-ray Multi-Energy Computed Tomography
- 12:30 Improved Kernel-based Limited-View CT Reconstruction Via Anisotropic Diffusion
TA.PA: Statistical-Model-Based Processing and Tracking (Poster)
Room: Grand Hall 2
Chair: Rudolf Mester (Goethe University, Frankfurt & VSI Lab, Germany)
- Efficient Joint Poisson-Gauss Restoration Using Multi-Frame L2-relaxed-L0 Analysis-based Sparsity
- Image-based Object Detection Under Varying Illumination in Environments with Specular Surfaces
- Hybrid Parametric-Nonparametric Modeling with Application to Natural Image Upsampling
- Batch-incremental Principle Component Analysis with Exact Mean Update
- Model Shared Semi-Supervised Learning for Multi-Label Image
- A Method for Discontinuous Neurite Reconstruction Based on Diffusion Tensor, Hessian Eigenvector, and Diffused Gradient Vector Fields
- Boosting Segmentation Results by Contour Relaxation
- Improved DCT Coefficient Distribution Modeling for H.264-like Video Coders Based on Block Classification
- Flexible Trajectory Modeling Using a Mixture of Parametric Motion Fields for Video Surveillance
- Fast Incremental Method for Matrix Completion: An Application to Trajectory Correction
- Liver Tumor Detection in CT Images by Adaptive Contrast Enhancement and the EM/MPM Algorithm
- RANSAC-LEL: An Optimized Version with Least Entropy Like Estimators
- Discriminative Model Selection Using a Modified Bayesian Criterion: Application to Trajectory Modeling
- Visual Tracking and Dynamic Learning on the Grassmann Manifold with Inference From a Bayesian Framework and State Space Models
- Bayesian Visual Surveillance: a Model for Detecting and Tracking a Variable Number of Moving Objects
- Human Identification Using Body Prior and Generalized EMD
TA.PB: Filtering (Poster)
Room: Grand Hall 2
Chair: Aleksandra Pižurica (Ghent University, Belgium)
- Region-based Thresholding Using Component Tree
- Interactive Collection of Training Samples From the Max-Tree Structure
- A Method to Determine the Size of the Structuring Element in Morphological Correction of Non-uniform Illumination
- Three Kinds of Color Total-Variation Semi-norms and Its Application to Color-Image Denoising
- Fast Algorithm for Total Variation Minimization
- Structural-Context-Preserving Image Abstraction by Using Space-Filling Curve Based on Minimum Spanning Tree
- Color Space Influence on Mean Shift Filtering
- Adaptive Grid Pattern Artifact Reduction in Radiography Imaging Based on the Significant-Signal Bandwidth
- A New Infrared Image Fusion Method Using Empirical Mode Decomposition and Inpainting
- Improved Optimal Seam Selection Blending for Fast Video Stitching of Videos Captured From Freely Moving Devices
- Fast and Robust Isotropic Scaling Iterative Closest Point Algorithm
- Fusion of Panchromatic and Multispectral Images Using Multiscale Dual Bilateral Filter
- Video Mosaicing Using a Mutual Information-based Motion Estimation Process
- Seam Carving in Wavelet Transform Domain
- Variable Remapping of Images From Very Different Sources
TA.PC: Image Processing: Analysis, Modeling, Enhancement (Poster)
Room: Grand Hall 2
Chair: Bart Goossens (Ghent University, Belgium)
- Bayesian Stereoscopic Image Resolution Enhancement
- Post Processing for Blocking Artifact Reduction
- Separable Bilateral Nonlocal Means
- Multi-resolution Missing Data Interpolation in SST Image Series
- Same Frame Rate IR to Enhance Visible Video Conference Lighting
- An Augmented Lagrangian Method for Fast Gradient Vector Flow Computation
- High Frequency Compensated Face Hallucination
- Detail Preserving Multiple Bit-Depth Image Representation and Coding
- Recovering Missing Coefficients in DCT-Transformed Images
- Wasserstein Regularization of Imaging Problem
- An Adaptive Total Variation Method for Speckle Reduction in Medical Ultrasound Imaging
- A Monotonic Constrained Regression Framework for Histogram Equalization and Specification
- Interactive Motion Deblurring Using Light Streaks
- Fusion-based Restoration of the Underwater Images
- Chi-Square Unbiased Risk Estimate for Denoising Magnitude MR Images
TA.PD: Biomedical Image Processing and Applications (Poster)
Room: Grand Hall 2
Chair: Alexander Behrens (RWTH Aachen University, Germany)
- Computer-aided Cataract Detection Using Enhanced Texture Features on Retro-Illumination Lens Images
- 3D Protein-Protein Docking Using Shape Complementarity and Fast Alignment
- Detection of Pelvic Fractures Using Graph Cuts and Curvatures
- Automated Nuclei Clump Decomposition for Image Analysis in Neuronal Cell Fluorescent Microscopy
- Automatic Labeling and Classification of Brain CT Images
- Histogram Analysis of CT Scans for Patients with Post-Mastectomy Lymphedema
- A GPU Accelerated Interactive Interface for Exploratory Functional Connectivity Analysis of fMRI Data
- Application of Computational Anatomy Methods to MRI Data for the Diagnosis of Alzheimer's Disease
- Medical Image Denoising Using Kernel Ridge Regression
- Extended Whole Mesh Deformation Model: Full 3D Processing
- Automatic Boundary Detection and Symmetry Calculation in Dermoscopy Images of Skin Lesions
- Cancer Detection From Biopsy Images Using Probabilistic and Discriminative Features
- A Robust Feature Selection Approach Using Low Rank Matrices for Breast Tumors in Ultrasonic Images
- An Effective Method of Searching for Subregions in Chromosome Images
- A 3D Human Teeth Database Construction Based on a Point-Based Shape Registration
- An Ensemble-based Microaneurysm Detector for Retinal Images
TA.PE: Video Coding and Motion Estimation (Poster)
Room: Grand Hall 2
Chair: Antonio Ortega (USC, USA)
- Optimal Rate Adaptation with Integer Linear Programming in the Scalable Extension of H.264/AVC
- Rate-Distortion Analysis of Super-Resolution Image/Video Decoding
- Temporal Trajectory Filtering for Bi-Directional Predicted Frames
- Chroma Intra Prediction Using Template Matching with Reconstructed Luma Components
- Practical Rate Control Algorithm for Temporal Scalability in Scalable Video Coding
- Intra-WZ Quantization Mismatch in Distributed Video Coding
- Segmentation-Based Motion Compensation for Enhanced Video Coding
- Visual Perception Based Lagrangian Rate Distortion Optimization for Video Coding
- SSIM-inspired Divisive Normalization for Perceptual Video Coding
- Combining Open- and Closed-Loop Architectures for H.264/AVC-to-SVC Transcoding
- Adaptive Intra Modes Reduction by Clustering for H.264/AVC
- Efficient P-frame Complexity Estimation for Frame Layer Rate Control of H.264/AVC
- Decoder Side True Motion Estimation for Very Low Bitrate B-frame Coding
- Motion Compensated Prediction Using Partial Mesh Generation
- High Definition Video Intra-Only Coding Based on Node-Cell Macroblock Pixel Structure and 2-D Interleaved DCT
- Mode Dependent Dct/Dst for Intra Prediction in Block-Based Image/Video Coding
TA.PF: Color/Multispectral Imaging and Rendering (Poster)
Room: Grand Hall 2
Chair: Xin Li (West Virginia University, USA)
- Modeling and Application of Color Noise Perception Dependent on Background Color and Spatial Frequency
- Compressive Demosaicing for Periodic Color Filter Arrays
- Color Distribution Matching Using a Weighted Subspace Descriptor
- Optimum Features Discovery by Criteria Minimum-Redundancy-Maximum-Relevance
- Real-time Visual Saliency by Division of Gaussians
- NEURAL GRAY EDGE: Improving Gray Edge Algorithm Using Neural Network
- Dimensionality Reduction of Hyperspectral Images with Wavelet Based Empirical Mode Decomposition
- Removing Shadows From Images Using Color and Near-infrared
- Inverse Halftoning with Nonlocal Regularization
- Electro-Photographic Model Based Stochastic Clustered-Dot Halftoning with Direct Binary Search
- High Resolution Subpixel and Subframe Rendering for Color Flatpanel and Projector Displays
- Color Quantization Using C-Means Clustering Algorithms
- Design of Color Screen Sets for Robustness to Color Plane Misregistration
TA.PG: Applications of Image & Video Interpretation and Understanding (Poster)
Room: Grand Hall 2
Chair: Narciso García (Universidad Politécnica de Madrid, Spain)
- Face Recognition Using Maximum Local Fisher Discriminant Analysis
- A Non-Temporal Texture Driven Approach to Real-time Fire Detection
- Temporal Trimap Propagation for Video Matting Using Inferential Statistics
- A Biologically Inspired System for Fast Handwritten Digit Recognition
- Joint Optimization of Background Subtraction and Object Detection for Night Surveillance
- Automatic Bandwidth Estimation Strategy for High-Quality Non-Parametric Modeling Based Moving Object Detection
- Face Recognition Through Regional Weight Estimation
- Ultrasound Video Analysis for Understanding Infant Breastfeeding
- Exploiting Feature Correspondence Constraints for Image Recognition
- Sparse Cost-sensitive Classifier with Application to Face Recognition
- Hierarchical Bag-of-Features for Hand Posture Recognition
- Context-driven Moving Object Detection in Aerial Scenes with User Input
- Human Face Classification Based on Localized Blur Descriptors
- Combining Global and Local Features for Food Identification in Dietary Assessment
- Human Detection Using Multi-camera and 3D Scene Knowledge
- Multimodal Learning for Multi-Label Image Classification
14:20 - 17:35
TP.L1: Distributed Compression: Multimedia Applications (Special Session)
Room: Silver Hall
Chairs: Samuel Cheng (University of Oklahoma, USA), Vladimir Stankovic (University of Strathclyde, United Kingdom)
- 14:20 Distributed Compression: Overview of Current and Emerging Multimedia Applications
- 14:40 Quality-Controlled View Interpolation for Multiview Video
- 15:00 A Comparison of the Error Resiliency of Bit-Plane Based and Symbol Based Pixel-Domain Distributed Video Coding
- 15:20 Distributed Coding of Endoscopic Video
- 15:40 break
- 16:15 Wyner-Ziv Coding for Depth Maps in Multiview Video-Plus-Depth
- 16:35 Distributed Compression of Zerotrees of Wavelet Coefficients
- 16:55 Distributed Source Coding for Securing a Hand-Based Biometric Recognition System
- 17:15 Distributed Transforms for Efficient Data Gathering in Arbitrary Networks
TP.L2: Image and Noise Models for Restoration (Lecture)
Room: 211/212
Chair: Javier Portilla (Consejo Superior de Investigaciones Científicas, Spain)
- 14:20 Resolution-invariant Separable ARMA Modeling of Images
- 14:40 CONDY: Ultra-Fast High Performance Restoration Using Multi-Frame L2-Relaxed-L0 Sparsity and Constrained Dynamic Heuristics
- 15:00 Sparsity-based Image Deblurring with Locally Adaptive and Nonlocally Robust Regularization
- 15:20 Patch Similarity Under Non Gaussian Noise
- 15:40 break
- 16:15 Generalized Subspace Based High Dimensional Density Estimation
- 16:35 Ising Field Parameter Estimation From Incomplete and Noisy Data
- 16:55 Noise Estimation Using Statistics of Natural Images
- 17:15 Hazy Image Modeling Using Color Ellipsoids
TP.L3: Motion Analysis and Object Tracking (Lecture)
Room: 214/216
Chair:
Tamas Szirányi (Computer and Automation Research Institute of the
Hungarian Academy of Sciences & Pázmány Péter Catholic University,
Hungary)
- 14:20 A Fast Object Tracking Approach Based on Sparse Representation
- 14:40 Efficiently Selecting Spatially Distributed Keypoints for Visual Tracking
- 15:00 Simultaneous 3D Object Tracking and Camera Parameter Estimation by Bayesian Methods and Transdimensional MCMC Sampling
- 15:20 Multi-person Tracking Based on Vertical Reference Lines and Dynamic Visibility Analysis
- 15:40 break
- 16:15 Local Complexity Adaptable Trajectory Partitioning Via Minimum Message Length
- 16:35 Fast TV-L1 Optical Flow for Interactivity
- 16:55 Co-occurrence Flow for Pedestrian Detection
- 17:15 Hierarchical Fusion of Descriptor Matching and L-K Optical Flow
TP.L4: Sparse Image Recovery (Lecture)
Room: 213/215
Chair: Pier-Luigi Dragotti (Imperial College, United Kingdom)
- 14:20 Increasing Imaging Resolution by Covering Your Sensor
- 14:40 Inverse Problems with Poisson Noise: Primal and Primal-Dual Splitting
- 15:00 Sparse Image Restoration Using Iterated Linear Expansion of Thresholds
- 15:20 Cutset Sampling and Reconstruction of Images
- 15:40 break
- 16:15 A Graph Cut Method for Linear Inverse Problems
- 16:35 Convex Approaches to Model Wavelet Sparsity Patterns
- 16:55 Weighted Fidelity in Non-Uniformly Quantized Compressed Sensing
- 17:15 Refractive Index Estimation Using Photometric Stereo
TP.L5: Image Forensics (Lecture)
Room: The Arc
Chair: Alex Kot (Nanyang Technological University, Singapore)
- 14:20 Detection of Non-Aligned Double JPEG Compression with Estimation of Primary Compression Parameters
- 14:40 Identifying Computer Generated Graphics Via Histogram Features
- 15:00 Eye Specular Highlights Telltales for Digital Forensics: a Machine Learning Approach
- 15:20 An Application of Sparse Code Shrinkage to Image Steganalysis Based on Supervised Learning
- 15:40 break
- 16:15 Modeling the EXIF-Image Correlation for Image Manipulation Detection
- 16:35 Countering JPEG Anti-Forensics
- 16:55 Exploring Compression Effects for Improved Source Camera Identification Using Strongly Compressed Video
- 17:15 Passive Spread-Spectrum Steganalysis
14:20 - 17:15
TP.L6: 3D Image Generation and Analysis (Lecture)
Room: Hall 300
Chair: Thrasyvoulos N. Pappas (Northwestern University, USA)
- 14:20 2D to 3D Conversion of Sports Content Using Panoramas
- 14:40 Hole Filling with Random Walks Using Occlusion Constraints in View Synthesis
- 15:00 A Triangular-Warping Based View Synthesis Scheme with Enhanced Artifact Reduction for FTV
- 15:20 Super-Resolution Plane Sweeping for Free-Viewpoint Image Synthesis
- 15:40 break
- 16:15 Depth Map Reconstruction Using Color-based Region Merging
- 16:35 Recovering Depth From a Single Image Using Spectral Energy of the Defocused Step Edge Gradient
- 16:55 3D Surface Registration Using Z-SIFT
14:20 - 17:35
TP.L7: Lossless and Predictive Coding (Lecture)
Room: 311/312
Chair: David Taubman (University of New South Wales, Australia)
- 14:20 $L_2$ Restoration of $l_\infty$-decoded Images with Context Modeling
- 14:40 Image Similarity Using the Normalized Compression Distance Based on Finite Context Models
- 15:00 On Lossless Image Compression Using the Burrows-Wheeler Transform
- 15:20 Lossless Video Coding Using Grid-Gradient Classification
- 15:40 break
- 16:15 Exploitation of Context Classification for Parallel Pixel Coding in JPEG-LS
- 16:35 Improved H.264/AVC Lossless Intra Compression Using Multiple Partition Prediction for 4X4 Intra Block
- 16:55 Improved Lossless Coding Algorithm in H.264/AVC Based on Hierarchical Intra Prediction
- 17:15 Adaptive Least Squares Prediction for Stereo Image Coding
TP.L8: Ultrasound and Microscopic Imaging (Lecture)
Room: 314/316
Chair: Jan P.H. Cornelis (Vrije Universiteit Brussel, Belgium)
- 14:20 Elastographic Image Reconstruction: A Stochastic State Space Approach
- 14:40 Reducing the Training Set Using Semi-Supervised Self-Training Algorithm for Segmenting the Left Ventricle in Ultrasound Images
- 15:00 Enhanced Classification of Focal Hepatic Lesions in Ultrasound Images Using Novel Texture Features
- 15:20 Realistic Log-Compressed Law for Ultrasound Image Recovery
- 15:40 break
- 16:15 Compact Rotation Invariant Image Descriptors by Spectral Trimming
- 16:35 Modeling of PSF for Refractive Index Variation in Fluorescence Microscopy
- 16:55 Image Filtering Using Anisotropic Structure Tensor for Cell Membrane Enhancement in 3D Microscopy
- 17:15 ALL-IDB: The Acute Lymphoblastic Leukemia Image Database for Image Processing
14:20 - 16:55
TP.L9: Object and Human Detection (Lecture)
Room: 313/315
Chair: Antonius Kalker (Hewlett-Packard, USA)
- 14:20 Detecting Humans Under Occlusion Using Variational Mean Field Method
- 14:40 Local Binary Pattern Features for Pedestrian Detection At Night/Dark Environment
- 15:00 Effective Discretization of Gabor Features for Real-time Face Detection
- 15:20 Robust Crowd Counting Using Detection Flow
- 15:40 break
- 16:15 Direction-based Stochastic Matching for Pedestrian Recognition in Non- Overlapping Cameras
- 16:35 Robust Shape-From-Image-Focus by 3-D Multivariate Statistical Analyses
14:20 - 17:35
TP.PA: Image & Video Representations and Applications (Poster)
Room: Grand Hall 2
Chair: Sei-ichiro Kamata (Waseda university, Japan)
- Robust View Transformation Model for Gait Recognition
- Incremental Orthogonal Projective Non-negative Matrix Factorization and Its Applications
- Error Concealment Via 3-Mode Tensor Approximation
- Relative Depth From Monocular Optical Flow
- Vector Field Analysis for Motion Pattern Identification in Video
- Video Resolution Enhancement by Using Complex Wavelet Transform
- Space-Time Template Matching for Human Action Detection Using Volume-Based Generalized Hough Transform
- An Improved Depth Map Estimation for Coding and View Synthesis
- Multi-Scale 3D Representation Via Volumetric Quasi-Random Scale Space
- Motion Re-estimation for H.264/AVC Video Downscaling Transcoding Using EPZS Algorithm
- Generalized Selective Data Pruning for Video Sequence
- HyperComplex Polar Fourier Analysis for Color Image
- Analysis of Solder Paste Scooping with Hierarchical Point Processes
- Image Segmentation with Hierarchical Topic Assignment
- Color Correction Via Robust Reference Selection and Recovery Using a Low-Rank Matrix Model
TP.PB: Biomedical Image Registration and Segmentation (Poster)
Room: Grand Hall 2
Chair: Peter Faltin (RWTH Aachen University, Germany)
- Weighting Function in Random Walk Based Left Ventricle Segmentation
- Brain Structure Segmentation From Diffusion Tensor Imaging
- Topological Vascular Tree Segmentation for Retinal Images Using Shortest Path Connection
- 2D-GE Image Segmentation Based on Level-Sets
- Multiresolution Localization and Segmentation of the Optical Disc in Fundus Images Using Inpainted Background and Vessel Information
- Efficient Multi-Object Segmentation of 3D Medical Images Using Clustering and Graph Cuts
- Cellsnake: a New Active Contour Technique for cell/fibre Segmentation
- Variational Approach for Segmentation of Lung Nodules
- A Novel Probabilistic Simultaneous Segmentation and Registration Using Level Set
- Efficient Cell Segmentation and Tracking of Developing Plant Meristem
- Retinal Image Registration Using Bifurcation Structures
- Lung Tumor Delineation in PET-CT Images Using a Downhill Region Growing and a Gaussian Mixture Model
- Temporal Registration of Partial Data Using Particle Filtering
- Markov-Gibbs Model Based Registration of CT Lung Images Using Subsampling for the Follow-Up Assessment of Pleural Thickenings
- Ultrasound-based Surgical Navigation for Percutaneous Renal Intervention: In Vivo Measurements and in Vitro Assessment
- Learning Shape Statistics for Hierarchical 3D Medical Image Segmentation
TP.PC: Image/Video Coding, Streaming and Recovery (Poster)
Room: Grand Hall 2
Chair: John Apostolopoulos (Hewlett-Packard Labs, USA)
- HTTP-Based Scalable Video Streaming Over Mobile Networks
- Joint Source-Channel Coding Optimization with Packet Loss Resilience for Video Transmission
- Joint Space-Time-View Error Concealment Algorithms for 3D Multi-View Video
- Expanding Window Random Linear Codes for Data Partitioned H.264 Video Transmission Over DVB-H Network
- Temporal Adaptation Strategies for Spatio-Temporal Image Alignment in Inter-Sequence Error Concealment of Digital TV
- An Improved Error Concealment by Diminishing the Edge Discontinuity
- High-Frequency Error Recovery in JPEG XR Coded Images
- Joint Source-Channel Decoding of Motion-Information Using Maximum-a-Posteriori
- New TCP Video Streaming Proxy Design for Last-Hop Wireless Networks
- Pixel Domain Referenceless Visual Degradation Detection and Error Concealment for Mobile Video
- Contribution-based Peer Selection for Packet Protection for P2P Video Streaming Over Mesh-based Networks
- Channel Protection for H.264 Compression in Transportation Video Surveillance Applications
- Scalable Video Streaming Over OpenFlow Networks:An Optimization Framework for QoS Routing
- Error Recovery of Image-Based Depth Maps Using Bézier Curve Fitting
- Adaptive Policies for Real-Time Video Transmission: A Markov Decision Process Framework
- Adaptive Frame and QP Selection for Temporally Super-Resolved Full-Exposure-Time Video
TP.PD: Computational and Magnetic Resonance Imaging (Poster)
Room: Grand Hall 2
Chair: Jean-Philippe Thiran (École Polytechnique Fédérale de Lausanne & Signal Processing Laboratory, Switzerland)
- An Exploration Framework for Segmentation Parameter Spaces
- Parallel Quadratic Programming for Image Processing
- Low Visual Difference Virtual High Dynamic Range Image Synthesizer From a Single Legacy Image
- Towards a Diffusion Image Processing Validation and Accuracy Prediction Framework
- A New Similarity Measure for Multi-Modal Image Registration
- Segmented Rapid Magnetic Resonance Imaging Using Structured Sparse Representations
- Extended Kalman Filtering for MR-thermometry Guided High Intensity Focused Ultrasound Using the Bio Heat Transfer Equation
- A New 3D Automatic Segmentation Framework for Accurate Extraction of Prostate From Diffusion Imaging (DW-MRI)
- A New Framework for Automated Segmentation of Left Ventricle Wall From Contrast Enhanced Cardiac Magnetic Resonance Images
- Dynamic Compressive Magnetic Resonance Imaging Using a Gaussian Scale Mixtures Model
- Orthonormal Expansion $\ell_1$-Minimization for Compressed Sensing in MRI
TP.PE: Tracking and Motion Detection (Poster)
Room: Grand Hall 2
Chair: Andreas Krutz (Technische Universität Berlin, Germany)
- Human Pose Tracking in Low Dimensional Space Enhanced by Limb Correction
- Human Tracking by Structured Body Parts
- Real-Time Moving Object Segmentation and Tracking for H.264/AVC Surveillance Videos
- Tracking Pedestrians Using Smoothed Colour Histograms in an Interacting Multiple Model Framework
- Contour Tracking Via On-line Discriminative Appearance Modeling Based Level Sets
- Lip Contour Tracking Using Multiple Dynamic Models on a Manifold
- PFT: a Protocol for Evaluating Video Trackers
- Real-time Human Tracking Based on Swtching Linear Dynamic System Combined with Adaptive Meanshift Tracker
- A Structured Learning-based Graph Matching for Dynamic Multiple Object Tracking
- Motion Detection in Old Film Sequences Using Adaptive Gaussian Mixture Model
- Gradient Sparsity for Piecewise Continuous Optical Flow Estimation
- Efficient Real-Time Local Optical Flow Estimation by Means of Integral Projections
- Video Motion Detection Algorithm Using Probabilistic Time Integrated Ransac
- Identifying Salient Poses in Lecture Videos
- Feature Selection with Geometric Constraints for Vision-Based Unmanned Aerial Vehicle Navigation
TP.PF: Scene Analysis (Poster)
Room: Grand Hall 2
Chair: Nam-Ik Cho (Seoul National University, Korea)
- Two-phase Approach for Multi-view Object Extraction
- Alignment of Uncalibrated Images for Multi-View Classification
- Dynamic Background Subtraction Using Moments
- Belief Propagation with Local Edge Detection-based Cost Aggregation for Stereo Matching
- Discrimination and Description of Repetitive Patterns for Enhancing Object Recognition Performance
- Sparse Regression Analysis for Object Recognition
- Intelligent Filtering by Semantic Importance for Single-View 3D Reconstruction From Snooker Video
- Pattern Recognition Using Rotation-invariant Filter-driven Template Matching
- 3D Spatio-temporal Graph Cuts for Video Objects Segmentation
- Hierarchical Invariant Sparse Modeling for Image Analysis
- Multi-scale Analysis of Color and Texture for Salient Object Detection
- Object Detection Using Discriminative Photogrammetric Context
- Severity Classification of Abnormal Traffic Events At Intersections
- Soft Assignment of Visual Words as Linear Coordinate Coding and Optimisation of Its Reconstruction Error
- One Step Beyond Bags of Features: Visual Categorization Using Components
- Linear SVM Classification Using Boosting HOG Features for Vehicle Detection in Low-Altitude Airborne Videos
TP.PG: Image Retrieval (Poster)
Room: Grand Hall 2
Chair: Avideh Zakhor (University of California at Berkeley, USA)
- Semantic Clusters Based Manifold Ranking for Image Retrieval
- Browsing Catalogue Graphs: Content Caching Supercharged!!
- MPEG-7 Compliant Generalized Structure Descriptor for Still Image Indexing
- Key Frame Extraction From Consumer Videos Using Sparse Representation
- On the Use of Conceptual Information in a Concept-Based Image Indexing and Retrieval Framework
- Improving Image Tag Recommendation Using Favorite Image Context
- Query Sensitive Dynamic Web Video Thumbnail Generation
- Graph-Based Multiple-Instance Learning with Instance Weighting for Image Retrieval
- Image Database Categorization Using Robust Unsupervised Learning of Finite Generalized Dirichlet Mixture Models
- Weakly Supervised Locality Sensitive Hashing for Duplicate Image Retrieval
- Fast Common Visual Pattern Detection Via Radiate Geometric Model
- A Novel Image Importance Model for Content-Aware Image Resizing
- Multi-Keyframe Abstraction From Videos
- Select Informative Features for Recognition
- A Balanced Semi-supervised Hashing Method for CBIR
Wednesday, September 14
09:00 - 10:00
CULTURAL HERITAGE: Distinguishing the "Hand" of the Master?
Room: Gold Hall
Chairs: Ann Dooms (Vrije Universiteit Brussel, Belgium), Laurent Jacques (Université catholique de Louvain, Belgium)
 |
Lecturer: Ingrid Daubechies (Duke University, USA) |
Abstract:
Paintings by Goossen van
der Weyden, an early 16th century Flemish painter, have long been known
not all to be entirely of the hand of the master himself -- it was
customary in his time that artists employed one or more apprentices in
their workshops, who could be given the task to execute (less crucial)
parts of some paintings.
As is customary in 16th century paintings as well, many show underdrawings, which can be made visible by infrared reflectometry. In the case of Goosen van der Weyden, some of these underdrawings are much more structured than others, giving more technical guidance for the subsequent operation of painting; different underdrawing styles can occur within the same painting.
An interesting question, from the art historical point of view, is whether the painting style, as characterized by an analysis of the visible detail of the painted surface, can be classified "blindly" (i.e. without a priory knowledge of the underdrawing style) in accordance with the underdrawing classification. We studied this question, and found that this was indeed the case.
Work done in collaboration with Robert Calderbank, Sina Jafarpour, Maximiliaan Martens and Josephine Wolff.
As is customary in 16th century paintings as well, many show underdrawings, which can be made visible by infrared reflectometry. In the case of Goosen van der Weyden, some of these underdrawings are much more structured than others, giving more technical guidance for the subsequent operation of painting; different underdrawing styles can occur within the same painting.
An interesting question, from the art historical point of view, is whether the painting style, as characterized by an analysis of the visible detail of the painted surface, can be classified "blindly" (i.e. without a priory knowledge of the underdrawing style) in accordance with the underdrawing classification. We studied this question, and found that this was indeed the case.
Work done in collaboration with Robert Calderbank, Sina Jafarpour, Maximiliaan Martens and Josephine Wolff.
Biography:
Daubechies was born in
Houthalen, Belgium, as the daughter of Marcel Daubechies (a civil
mining engineer) and Simonne Duran (then a homemaker, later a
criminologist). Daubechies completed her undergraduate studies in
physics at the Vrije Universiteit Brussel in 1975. She obtained her
Ph.D. in theoretical physics in 1980, and continued her research career
at that institution until 1987, rising through the ranks to positions
roughly equivalent with research assistant-professor in 1981 and
research associate-professor 1985.
In 1985 Daubechies met mathematician Robert Calderbank, then on a 3-month exchange visit from AT&T Bell Laboratories, New Jersey to the Brussels-based mathematics division of Philips Research; they married in 1987. Daubechies then moved to the United States, taking a position at the Murray Hill AT&T Bell Laboratories' New Jersey facility. Earlier that same year, she had made her best-known discovery: the construction of compactly supported continuous wavelets.
Since 1993, Daubechies has been a full professor at Princeton University, where she is active especially within the Program in Applied and Computational Mathematics. She was the first female full professor of Mathematics at Princeton. In January 2011 she moved to Duke University to serve as a professor of Mathematics. She is the president of the International Mathematical Union (2011–2014).
The name Daubechies is widely associated with the orthogonal Daubechies wavelet and the biorthogonal CDF wavelet. A wavelet from this latter family of wavelets is now used in the JPEG 2000 standard.
In 1985 Daubechies met mathematician Robert Calderbank, then on a 3-month exchange visit from AT&T Bell Laboratories, New Jersey to the Brussels-based mathematics division of Philips Research; they married in 1987. Daubechies then moved to the United States, taking a position at the Murray Hill AT&T Bell Laboratories' New Jersey facility. Earlier that same year, she had made her best-known discovery: the construction of compactly supported continuous wavelets.
Since 1993, Daubechies has been a full professor at Princeton University, where she is active especially within the Program in Applied and Computational Mathematics. She was the first female full professor of Mathematics at Princeton. In January 2011 she moved to Duke University to serve as a professor of Mathematics. She is the president of the International Mathematical Union (2011–2014).
The name Daubechies is widely associated with the orthogonal Daubechies wavelet and the biorthogonal CDF wavelet. A wavelet from this latter family of wavelets is now used in the JPEG 2000 standard.
10:15 - 12:30
WA.L1: Recent Advances in Web-scale Image Annotation (Special Session)
Room: Silver Hall
Chair: Jinjun Wang (Epson Research and Development, USA)
- 10:15 Learning the Trip Suggestion From Landmark Photos on the Web
- 10:35 Online Vicept Learning for Web-Scale Image Understanding
- 10:55 break
- 11:30 Representative Sampling with Certainty Propagation for Image Retrieval
- 11:50 Learning Semantic Embedding At a Large Scale
- 12:10 Descriptive Local Feature Groups for Image Classification
10:15 - 12:50
WA.L2: Video Quality Assessment (Lecture)
Room: 211/212
Chair: Marco Tagliasacchi (Politecnico di Milano, Italy)
- 10:15 A Spatiotemporal Most-Apparent-Distortion Model for Video Quality Assessment
- 10:35 Spatio-temporal Quality Pooling Accounting for Transient Severe Impairments and Egomotion
- 10:55 break
- 11:30 Machine Learning Based Modeling of Spatial and Temporal Factors for Video Quality Assessment
- 11:50 A Novel Full-Reference Video Quality Metric and Its Application to Wireless Video Transmission
- 12:10 3D-DCT Based Perceptual Quality Assessment of Stereo Video
- 12:30 A Perceptual Quality Assessment Metric Using Temporal Complexity and Disparity Information for Stereoscopic Video
WA.L3: Copy and Near-Duplicate Detection (Lecture)
Room: 214/216
Chair: Ebroul Izquierdo (Queen Mary, University of London, United Kingdom)
- 10:15 Commercial Mining Based on Temporal Recurrence Hashing Algorithm and Bag-Of-Fingerprints Model
- 10:35 Copy Detection Towards Semantic Mining for Video Retrieval
- 10:55 break
- 11:30 Salient Covariance for Near-duplicate Image and Video Detection
- 11:50 Shape Context Based Image Hashing Using Local Feature Points
- 12:10 PKUBench: A Context Rich Mobile Visual Search Benchmark
- 12:30 Fast Face Sequence Matching in Large-scale Video Databases
WA.L4: Image Denoising (Lecture)
Room: 213/215
Chair: Joel Trussell (NC State University, USA)
- 10:15 Patch-based Locally Optimal Denoising
- 10:35 Nonlinear Curvelet Diffusion for Noisy Image Enhancement
- 10:55 break
- 11:30 MMSE Nonlocal Means Denoising Algorithm for Poisson Noise Removal
- 11:50 Learning a Wavelet Tree for Multichannel Image Denoising
- 12:10 Robust Sparse Image Denoising
- 12:30 Video Denoising Based on Transform Domain Minimum Mean Square Error
WA.L5: 3D Video Processing and Rendering (Lecture)
Room: The Arc
Chair: Lina Karam (Arizona State University, USA)
- 10:15 Scribble Based Interactive 3D Reconstruction Via Scene Co-segmentation
- 10:35 Adaptive Plenoptic Sampling
- 10:55 break
- 11:30 Efficient Depth Blurring with Occlusion Handling
- 11:50 A New Multidirectional Extrapolation Hole-Filling Method for Depth-Image-Based Rendering
- 12:10 Parameterization and Appearance Preserving on Cubic Cells for 3D Digital Preservation of Cultural Heritage
- 12:30 Can 3D Synthesized Views Be Reliably Assessed Through Usual Subjective and Objective Evaluation Protocols?
WA.L6: Exploiting and Analyzing Text in Electronic Images (Lecture)
Room: Hall 300
Chair: Vishal Monga (Pennsylvania State University, USA)
- 10:15 Mobile Visual Search on Printed Documents Using Text and Low Bit-Rate Features
- 10:35 A New Hybrid Method to Detect Text in Natural Scene
- 10:55 break
- 11:30 Robust Text Detection in Natural Images with Edge-enhanced Maximally Stable Extremal Regions
- 11:50 Handwritten Connected Digits Detection: An Approach Using Instance Selection
- 12:10 A Robust Skew Detection Method Based on Maximum Gradient Difference and R-signature
- 12:30 Automated Image Quality Assessment for Camera-Captured OCR
WA.L7: Distributed Video Coding (Lecture)
Room: 311/312
Chair: Ricardo de Queiroz (University of Brasil, Brazil)
- 10:15 Progressive Correlation Noise Refinement for Transform Domain Wyner-Ziv Video Coding
- 10:35 Scalable Distributed Video Coding Using Compressed Sensing in Wavelet Domain
- 10:55 break
- 11:30 Global Motion Guided Adaptive Temporal Inter- / Extrapolation for Side Information Generation in Distributed Video Coding
- 11:50 Parallel Iterative Decoding of Transform Domain Wyner-Ziv Video Using Cross Bitplane Correlation
- 12:10 Improved Wyner-ziv Video Coding Efficiency Using Bit Plane Prediction
- 12:30 Onboard Low-Complexity Compression of Solar Images
WA.L8: MRI: Cardiac and Neural Applications (Lecture)
Room: 314/316
Chair: Ali Bilgin (ECE Dept, The University of Arizona, USA)
- 10:15 A Novel Approach for Accurate Estimation of Left Ventricle Global Indexes From Short-Axis Cine MRI
- 10:35 Identification of Continuous Cardiac Dynamics and Abnormal Material Properties
- 10:55 break
- 11:30 Aorta Segmentation Using the Watershed Algorithm for an Augmented Reality System in Laparoscopic Surgery
- 11:50 Automatic Subcortical Tissue Segmentation of MR Images Using Optimum-Path Forest Clustering
- 12:10 3D Shape Analysis of the Brain Cortex with Application to Dyslexia
- 12:30 Detection of Resting-State Brain Activity in Magnetic Resonance Images Through Wavelet Feature Cluster Analysis
WA.PA: Sparse Estimation (Poster)
Room: Grand Hall 2
Chair: Joseph P. Havlicek (University of Oklahoma, USA)
- Total Variation-Wavelet-Curvelet Regularized Optimization for Image Restoration
- Image Reconstruction From Compressed Linear Measurements with Side Information
- Multitemporal Image Change Detection with Compressed Sparse Representation
- Single-View Reconstruction From an Unknown Spherical Mirror
- Optical Flow Estimation Using Sparse Gradient Representation
- Luminance Constrained Total Variation and Its Application for Optimized Decoding of JPEG 2000
- Modified-CS-residual for Recursive Reconstruction of Highly Undersampled Functional MRI Sequences
- Sparse Representation Based Band Selection for Hyperspectral Images
- Total-Variation Regularized Motion Estimation in a Periodic Image Sequence
- 3D Image Reconstruction From Sparse Measurement of Wideband Millimeter Wave SAR Experiments
- Compressive Passive Millimeter-Wave Imaging
- Hybrid Blind Deconvolution of Images Using Variable Splitting and Proximal Point Methods
- A New Block Compressive Sensing to Control the Number of Measurements
- A Memory Gradient Algorithm for L2-L0 Regularization with Applications to Image Restoration
WA.PB: Data Hiding and Media Security (Poster)
Room: Grand Hall 2
Chair: Alessandro Piva (University of Florence, Italy)
- An Effective Image Steganalysis Method Based on Neighborhood
- Frequency Domain Infrared Watermarking for Printed CMYK Image
- Affine Transformation Invariant Image Watermarking Using Moment Normalization and Radial Symmetry Transform
- Compression and Protection of JPEG Images
- Secure JPEG Steganography by LSB+ Matching and Multi-Band Embedding
- Reversible Watermarking Based on Generalized Histogram Shifting
- Robust Watermark Extraction Using SVD-based Dynamic Stochastic Resonance
- Improved Multiplicative Spread Spectrum Embedding for Image Data Hiding
- Countermeasure of Re-recording Prevention Against Attack with Short Wavelength Pass Filter
- A New Blind Robust Image Watermarking Scheme in SVD-DCT Composite Domain
- Virtual View Invariant Domain for 3D Video Blind Watermarking
- A Novel Approach to Adaptive Image Authentication
- A Collusion Resilient Key Management Scheme for Multi-dimensional Scalable Media Access Control
- Synchronization of Texture and Depth Map by Data Hiding for 3D H.264 Video
WA.PC: Remote Sensing an Geophysical Imaging (Poster)
Room: Grand Hall 2
Chair: James Fowler (Mississippi State University, USA)
- A New Approach to the Automated Mapping of Pockmarks in Multi-Beam Bathymetry
- Radio Astronomical Image Deconvolution Using Prolate Spheroidal Wave Functions
- Globally Optimal Reconstruction of Millimeter-Wave Radiometric Images with Belief Propagation
- Adaptive Patches for Change Detection
- Cascaded Active Learning for Object Retrieval Using Multiscale Coarse to Fine Analysis
- Component-based Restoration of Speckled Images
- Estimation of an Optimal Spectral Band Combination to Evaluate Skin Disease Treatment Efficacy Using Multi-Spectral Images
- Segmenting Extended Structures in Radio Astronomical Images by Filtering Bright Compact Sources and Using Wavelets Decomposition
- Ground Topography Estimation Over Forests Using PolInSAR Image by Means of Coherence Set
- A Fast Multiple Birth and Cut Algorithm Using Belief Propagation
- Fast Model of Space-Variant Blurring and Its Application to Deconvolution in Astronomy
- Robust Airplane Detection in Satellite Images
- Extracting Salient Contour Groups From Cluttered Solar Images Via Markov Random Fields
- Resolution Assessment in Dynamic Image Formation
WA.PD: Image Segmentation (Poster)
Room: Grand Hall 2
Chair: Josiane Zerubia (INRIA, Sophia Antipolis, France)
- Tensor Vector Field Based Active Contours
- EDLines: Realtime Line Segment Detection by Edge Drawing (ED)
- Incremental Local Hough Transform for Line Segment Extraction
- General Adaptive Distance Transforms on Gray Tone Images: Application to Image Segmentation
- Image Super-segmentation: Segmentation with Multiple Labels From Shuffled Observations
- Improved Force Field for Vector Field Convolution Method
- Semi-Automatic 3-D Segmentation of Computed Tomographic Imagery by Iterative Gradient-Driven Volume Growing
- Robust Segmentation of Relevant Regions in Low Depth of Field Images
- Multicolor Image Segmentation Using Ambrosio-Tortorelli Approximation
- Supervised Texture Segmentation Through a Multi-Level Pixel-Based Classifier Based on Specifically Designed Filters
- A New Information Fusion Approach for Image Segmentation
- Robust Free Space Segmentation Using Active Contours and Monocular Omnidirectional Vision
- Higher Order Potentials with Superpixel Neighbourhood (Hsn) for Semantic Image Segmentation
- Semi-automatic Texture Segmentation for Single Images
- An Intensity-Gradient-Texture Guided Methodology for Spatial Segmentation of Remotely Sensed Multi/Hyperspectral Imagery
WA.PE: Image Analysis (Poster)
Room: Grand Hall 2
Chair: Tsuhan Chen (Cornell University, USA)
- Nonparametric Polygonal and Multimodel Approximation of Digital Curves with Rate-Distortion Curve Modeling
- Concentric Ring Signature Descriptor for 3D Objects
- Edgelet Tracking Using Gauss-Laguerre Circular Harmonic Filters
- Graph-based Shape Matching for Deformable Objects
- Change-detection Based on Support Vector Data Description Handling Dependency
- BOSSA: Extended BoW Formalism for Image Classification
- Object Color Categorization in Surveillance Videos
- Reconstructing the Drawing Process of Reproductions From Medieval Images
- Preliminary Study on Statistical Shape Model Applied to Diagnosis of Liver Cirrhosis
- Fast Approximation for Geometric Classification of LiDAR Returns
- Extraction of Road Network Using a Modified Active Contour Approach
- Regression-based Object Shape Estimation Using a Shape-manifold
- Uniqueness for Shape From Shading Via Photometric Stereo Technique
WA.PF: Video Surveillance and Video Conferencing (Poster)
Room: Grand Hall 2
Chair: Ed Delp (Purdue University, USA)
- Real-time Clothing Recognition in Surveillance Videos
- Real-Time Traffic Analysis At Night-Time
- A Video Analytics Framework for Amorphous and Unstructured Anomaly Detection
- PTZ Camera-Based Adaptive Panoramic and Multi-layered Background Model
- Background Subtraction Through Multiple Life Span Modeling
- Common Visual Pattern Discovery Via Directed Graph Model
- Visual Framing Feedback for Desktop Video Conferencing
- An Unorthodox Approach Towards Shape From Focus
- A Novel Framework for Automatic Passenger Counting
- Fire Scene Segmentations for Forest Fire Characterization: a Comparative Study
- Semi-supervised Learning with Kernel Locality-constrained Linear Coding
- Softferns for Homography Estimation
- Automatic Image Orientation Detection with Prior Hierarchical Content-Based Classification
- Blackboard Content Classification for Lecture Videos
- Real-time Affine Invariant Patch Matching Using DCT Descriptor and Affine Space Quantization
WA.PG: Image Processing Methods for Face Recognition (Poster)
Room: Grand Hall 2
Chair: Jean-Luc Dugelay (Institut EURECOM, France)
- Local Color Vector Binary Pattern for Face Recognition
- Facial Expression Recognition Using Clustering Discriminant Non-negative Matrix Factorization
- A Novel Kernel Discriminant Feature Extraction Framework Based on Mapped Virtual Samples for Face Recognition
- Kernel Sparse Representation with Local Patterns for Face Recognition
- Discriminant Subclass-center Manifold Preserving Projection for Face Feature Extraction
- Texture Classification Based Low Order Local Binary Pattern for Face Recognition
- Manifold Learning for Simultaneous Pose and Facial Expression Recognition
- Multi-view Face Recognition Via Joint Dynamic Sparse Representation
- Local Primitive Code Mining for Fast and Accurate Face Recognition
- Robust Low-Rank Subspace Recovery and Face Image Denoising for Face Recognition
- A Mixture of Gated Experts Optimized Using Simulated Annealing for 3D Face Recognition
- Semi-supervised Face Recognition with LDA Self-training
- Robust Facial Expression Tracking Based on Composite Constraints AAM
- Face Recognition Based on Local Uncorrelated and Weighted Global Uncorrelated Discriminant Transforms
- Expression Robust 3D Face Recognition Via Mesh-based Histograms of Multiple Order Surface Differential Quantities
14:00 - 15:00
Round Table on Reproducible Research
Room: The Arc
Chairs:
Jean-Luc Dugelay (Institut EURECOM, France), Moncef Gabbouj (Tampere
University of Technology & Tampere, Finland, Finland)
14:20 - 17:35
WP.L1: Analysis of Microscopy and Reconstructive Images for Applications in Medicine and Biology (Special Session)
Room: Silver Hall
Chairs:
Bogdan J Matuszewski (University of Central Lancashire, United
Kingdom), Christopher Moore (The Christie NHS Foundation Trust, United
Kingdom)
- 14:20 3D Microscopic Imaging by Synchrotron Radiation micro/nano-CT
- 14:40 The Formulation of a Non-Linear Hertzian Model in Order to Assess the Mechanical Strength of Human Cells Based on Data From an Atomic Force Microscope
- 15:00 A Novel Technique for the Restoration of Atomic Force Microscope Images Enabling an Approximation of AFM Impulse Response
- 15:20 Analysis of Microscopy and Reconstructive Images for Applications in Medicine and Biology
- 15:40 break
- 16:15 Numerical Evaluation of Sampling Bounds for Near-Optimal Reconstruction in Compressed Sensing
- 16:35 Confocal Microscopy Segmentation Using Active Contour Based on Alpha-Divergence
- 16:55 Segmentation of Cellular Structures in Actin Tagged Fluorescence Confocal Microscopy Images
- 17:15 Quantifying Structure Regularity in Fluorescence Microscopy Cell Images Using a Novel Multi-Dimensional Approximate Entropy Metric
WP.L2: Image Quality Assessment (Lecture)
Room: 211/212
Chair: Touradj Ebrahimi (EPFL, Switzerland)
- 14:20 No-reference Image Quality Assessment Based on Visual Codebook
- 14:40 DCT Statistics Model-Based Blind Image Quality Assessment
- 15:00 Crowdsourcing Subjective Image Quality Evaluation
- 15:20 Systematic Stress Testing of Image Quality Estimators
- 15:40 break
- 16:15 Objective Metrics for Quality of Experience in Stereoscopic Images
- 16:35 Assessing the Quality of Compressed Images Using EEG
- 16:55 Image Quality Assessment of Endoscopic Panorama Images
- 17:15 Comprehensive Assessment of Iris Image Quality
WP.L3: Video and Multichannel Segmentation (Lecture)
Room: 214/216
Chair: Scott Acton (University of Virginia, USA)
- 14:20 Towards Real-Time 3D Region-Based Segmentation: B-Spline Explicit Active Surfaces
- 14:40 Segmentation by Temporal Detection Integration
- 15:00 Image Labeling by Multiple Segmentation
- 15:20 The Riverbed Approach for User-steered Image Segmentation
- 15:40 break
- 16:15 Clothing Segmentation and Recoloring Using Background Subtraction and Back Projection Method
- 16:35 Harmonic Active Contours for Multichannel Image Segmentation
- 16:55 Automatic Fish Segmentation Via Double Local Thresholding for Trawl-Based Underwater Camera Systems
- 17:15 Automatic People Segmentation with a Template-Driven Graph Cut
WP.L4: Color/Multispectral Imaging and Demosaicking (Lecture)
Room: 213/215
Chair: Theo Gevers (University of Amsterdam, The Netherlands)
- 14:20 New Color Filter Arrays of High Light Sensitivity and High Demosaicking Performance
- 14:40 Multispectral Demosaicking Using Adaptive Kernel Upsampling
- 15:00 Disregarding Spectral Overlap - a Unified Approach for Demosaicking, Compressive Sensing and Color Filter Array Design
- 15:20 Correlation-based Joint Acquisition and Demosaicing of Visible and Near-Infrared Images
- 15:40 break
- 16:15 Increasing Camera Dynamic Range Through In-Sensor Multi-Exposure White Balancing
- 16:35 Multi-dimensional Earth Mover's Distance Active Contours
- 16:55 Good Looking Green Images
- 17:15 Edge Detection in Multispectral Images Using the N-Dimensional Self-Organizing Map
WP.L6: Hand and Iris-based Biometrics (Lecture)
Room: Hall 300
Chair: Patrizio Campisi (University of ROMA TRE, Italy)
- 14:20 Contact-Free Hand Geometry Identification System
- 14:40 Deformable DAISY Matcher for Robust Iris Recognition
- 15:00 Incorporating Color Information for Reliable Palmprint Authentication
- 15:20 Feature-domain Super-Resolution for Iris Recognition
- 15:40 break
- 16:15 A Novel Fingerprint Matching Algorithm Using Minutiae Phase Difference Feature
- 16:35 Fast and Accurate Iris Segmentation Based on Linear Basis Function and RANSAC
- 16:55 Front View Gait Recognition Using Spherical Space Model with Human Point Clouds
- 17:15 Security Analysis of a Cancelable Iris Recognition System Based on Block Remapping
WP.L7: Video Streaming and Error-Resilient Coding (Lecture)
Room: 311/312
Chair: Kenneth Rose (University of California, Santa Barbara, USA)
- 14:20 Fast Mode Decision for H.264 Video Coding in Packet Loss Environment
- 14:40 A Unified Framework for Spectral Domain Prediction and End-To-End Distortion Estimation in Scalable Video Coding
- 15:00 Face Recovery in Conference Video Streaming Using Robust Principal Component Analysis
- 15:20 Enhanced Error Resiliency for Video with Cyclic Intra-Refresh Lines
- 15:40 break
- 16:15 Prioritized Packet Fragmentation for H.264 Video
- 16:35 Rate-distortion-optimized Content-adaptive Coding for Immersive Networked Experience of Sports Events
- 16:55 A Robust Content-Based JPWL Transmission Over a Realistic MIMO Channel Under Perceptual Constraints
- 17:15 Cross-Layer Design for Video Streaming with Dynamic Antenna Selection
WP.L8: Human Behavior Analysis and Foreground/Background Separation (Lecture)
Room: 314/316
Chair: Anastasios D. Doulamis (National Technical University of Athens, Greece)
- 14:20 A Dataset for Workflow Recognition in Industrial Scenes
- 14:40 Active Learning for Human Action Recognition with Gaussian Processes
- 15:00 System for the Automated Segmentation of Heads From Arbitrary Background
- 15:20 Robust Density Modelling Using the Student's T-Distribution for Human Action Recognition
- 15:40 break
- 16:15 Incorporating Estimated Motion in Real-time Background Subtraction
- 16:35 Foreground Estimation Based on Robust Linear Regression Model
- 16:55 Selective Subtraction When the Scene Cannot Be Learned
- 17:15 Selective Eigenbackgrounds Method for Background Subtraction in Crowed Scenes
WP.PA: Multimedia Quality Assessment and Modeling of Visual Perception (Poster)
Room: Grand Hall 2
Chair: Matteo Naccari (Instituto de Telecomunicações, Portugal)
- Image Complexity Measure Based on Visual Attention
- Robustness and Repeatability of Saliency Models Subjected to Visual Degradations
- Visual Attention: Effects of Blur
- Tracking Failure Detection by Imitating Human Visual Perception
- Visual Attention Based Image Quality Assessment
- Fusion of Visual Attention Cues by Machine Learning
- Edge-Based Objective Evaluation of Image Quality
- An Image Quality Assessment Metric Based on Non-Shift Edge
- RRAR: A Novel Reduced-Reference IQA Algorithm for Facial Images
- Calibrating MS-SSIM for Compression Distortions Using MLDS
- Modeling of Rate and Perceptual Quality of Video and Its Application to Frame Rate Adaptive Rate Control
- No-Reference Video Quality Metric for HDTV Based on H.264/AVC Bitstream Features
- No-Reference Cross-Layer Video Quality Estimation Model Over Wireless Networks
- No Reference Metric of Video Coding Quality Based on Parametric Analysis of Video Bitstream
- Audiovisual Quality Fusion Based on Relative Multimodal Complexity
WP.PB: Partial Differential Equations (Poster)
Room: Grand Hall 2
Chair: Ayman Sabry El-Baz (University of Louisville, USA)
- An Improved Region-Based Model with Local Statistical Feature
- Active Contours with a Novel Distribution Metric for Complex Object Segmentation
- Texture Segmentation Based on Local Feature Histograms
- Snake Based Unsupervised Texture Segmentation Using Gaussian Markov Random Field Models
- Effective Image Noise Removal Based on Difference Eigenvalue
- Level Set Evolution with Locally Linear Classification for Image Segmentation
- Cost Aggregation with Anisotropic Diffusion in Feature Space for Hybrid Stereo Matching
- New Optimization Scheme for L2-Norm Total Variation Semi-Supervised Image Soft Labeling
- Non-local Segmentation and Inpainting
- PDEs Level Sets on Weighted Graphs
- Affine Morphological Shape Stable Boundary Regions (SSBR) for Image Representation
- Discontinuous Seismic Horizon Tracking Based on a Poisson Equation with Incremental Dirichlet Boundary Conditions
- Reducing Aliasing in Images: a Simple Diffusion Equation Based on the Inverse Diffusivity
- A New Deformable Model-Based Segmentation Approach for Accurate Extraction of the Kidney From Abdominal CT Images
- Level Set Segmentation with Robust Image Gradient Energy and Statistical Shape Prior
WP.PC: Image Restoration and Enhancement (Poster)
Room: Grand Hall 2
Chair: Christine Guillemot (INRIA, France)
- Examplar-based Inpainting Based on Local Geometry
- Wide-band Image Guided Visible-band Image Enhancement
- Image Inpainting Via Weighted Sparse Non-Negative Matrix Factorization
- Fragmented Aperture Imaging for Motion and Defocus Deblurring
- Image Enhancement Based on Retinex and Lightness Decomposition
- Image Contrast Enhancement in Compressed Wavelet Domain
- Color Histogram Diffusion for Image Enhancement
- Reconstruction of High Dynamic Range Images with Poisson Noise Modeling and Integrated Denoising
- Gradient Domain Contrast Enhancement with Histogram-Guided Boundary Conditions
- Noiseless No-Flash Photo Creation by Color Transform of Flash Image
- Fast Image Inpainting Using Similarity of Subspace Method
- Automatic Foreground-Background Refocusing
- Depth Map Super Resolution
- Decoupled Inverse and Denoising for Image Deblurring: Variational BM3D-frame Technique
- A Novel Iterative Image Restoration Algorithm Using Nonstationary Image Priors
- Reconstructing Static Scene Viewed Through Smoke Using Video
WP.PD: Scalable and Adaptive Methods for Video Coding (Poster)
Room: Grand Hall 2
Chair: Sheila Hemami (Cornell University, USA)
- A Novel Rate-Distortion Optimization Method of H.264/AVC Intra Coder
- Intra-prediction with Adaptive Sub-sampling
- Theoretical Consideration of Global Motion Temporal Filtering
- Adaptive Loop Filter Technology Based on Analytical Design Considering Local Image Characteristics
- An Efficient Key-Frame-Free Prediction Method for MGS of H.264/SVC
- One Dimensional Prediction and Transform for Intra Coding
- Parallel Processing for Combined Intra Prediction in High Efficiency Video Coding
- Extending SVC by Content-adaptive Spatial Scalability
- Rate Control Initialization Algorithm for Scalable Video Coding
- Directional Adaptive Loop Filter for Video Coding
- Improved for/sor-Based Video Coding and Its Performance Analysis
- Video Encoder Based on Lifting Transforms on Graphs
- A Denoising Approach for Iterative Side Information Creation in Distributed Video Coding
- Periodic Entropy Coder Initialization for Wavefront Decoding of Video Bitstream
- McFis in Hierarchical Bipredictve Pictures-Based Video Coding for Referencing the Stable Area in a Scene
WP.PE: Electronic Imagery: Detection, Classification and Restoration (Poster)
Room: Grand Hall 2
Chair: Anderson Rocha (State University of Campinas, Brazil)
- Image Categorization Through Optimum Path Forest and Visual Words
- Automatic Segmentation for Arabic Characters in Handwriting Documents
- Point Object Detection Using a NL-means Type Filter
- Removing the Artifacts From Artwork Cross-Section Images
- Hierarchical Hybrid MLP/HMM or Rather MLP Features for a Discriminatively Trained Gaussian HMM: A Comparison for Offline Handwriting Recognition
- Computerized Paleography: Tools for Historical Manuscripts
- Edge Noise Removal in Bilevel Graphical Document Images Using Sparse Representation
- Fast Detection of Small Infrared Objects in Maritime Scenes Using Local Minimum Patterns
- Face Liveness Detection Under Bad Illumination Conditions
WP.PF: Object Detection and Recognition (Poster)
Room: Grand Hall 2
Chair: Andre Kaup (University of Erlangen-Nuremberg, Germany)
- Beyond Straight Lines - Object Detection Using Curvature
- Partial Least Squares Based Subwindow Search for Pedestrian Detection
- Boosting Based Object Detection Using a Geometric Model
- Nonlinear L1-norm Minimization Learning for Human Detection
- Automatic Nesting Seabird Detection Based on Boosted HOG-LBP Descriptors
- Hollow TV Logo Detection
- Pose Estimation by Local Procrustes Regression
- Fast Human Detection Using Node-Combined Part Detector
- Real-time Detection Via Homography Mapping of Foreground Polygons From Multiple Cameras
- Robust Abandoned Object Detection Using Region-Level Analysis
- Canonical Correlation Analysis of Local Feature Set for View-based Object Recognition
- Hand Shape Recognition Using Distance Transform and Shape Decomposition
- Human Detection with Contour-based Local Motion Binary Patterns
- Pictorial Structures for Object Recognition and Part Labeling in Drawings
- Robust Head Pose Estimation Via Convex Regularized Sparse Regression
WP.PG: Video Retrieval (Poster)
Room: Grand Hall 2
Chair: Moncef Gabbouj (Tampere University of Technology & Tampere, Finland, Finland)
- Towards a Better Understanding of Model-Free Semantic Concept Detection for Annotation and Near-Duplicate Video Clip Detection
- Quadtree Classified Vector Quantization Based Image Retrieval Scheme
- A Multimodal Video Copy Detection Approach with Sequential Pyramid Matching
- Retrieving Video Shots in Semantic Brain Imaging Space Using Manifold-Ranking
- Multivariate Texture Retrieval Using the Geodesic Distance Between Elliptically Distributed Random Variable
- Action Scene Detection From Motion and Events
- Multi-dimensional Evolutionary Feature Synthesis for Content-based Image Retrieval
- Integrating Distance Metric Learning Into Label Propagation Model for Multi-label Image Annotation
- Using Context Saliency for Movie Shot Classification
- View-based 3D Model Retrieval Using Two-Level Spatial Structure
- A Bag-of-Regions Approach to Sketch-Based Image Retrieval
- Image Coding with Face Descriptors Embedding
- On the Surprisingly Accurate Transfer of Image Parameters Between Medical and Solar Images
- Comparison of Video Sequences with Histograms of Motion Patterns
- Location-Based Image Retrieval for Urban Environments
15:00 - 17:55
WP.L5: Advances in Transforms for Video Coding (Special Session)
Room: The Arc
Chairs: Robert Cohen (Mitsubishi Electric Research Laboratories, USA), Marta Mrak (BBC, United Kingdom)
- 15:00 One-Dimensional Directional Unified Transform for Intra Coding
- 15:20 Low-complexity Mode-Dependent KLT for Block-Based Intra Coding
- 15:40 break
- 16:15 Rotational Transform for Image and Video Compression
- 16:35 Transform Coding in the HEVC Test Model
- 16:55 Design of Non-Separable Transforms for Directional 2-D Sources
- 17:15 Distortion Estimates for Adaptive Temporal Decompositions of Video Under Displacement Errors and Quantization Noise
- 17:35 Inter Prediction Using Lapped Transforms for Advanced Video Coding
