{ICIP2014}{收录论文列表}
This article come from
HERE
ARS-L1: Learning
ARS-L1: Learning
Tuesday 10:30–12:30; Oral Session; Room: Leonard de Vinci
10:30 ARS-L1.1—GROUP STRUCTURED DIRTY DICTIONARY LEARNING FOR CLASSIFICATION
10:50 ARS-L1.2—A HIERARCHICAL STRUCTURED DISCRIMINATIVE DICTIONARY LEARNING FOR CLASSIFICATION
11:10 ARS-L1.3—DICTIONARY-BASED MULTIPLE INSTANCE LEARNING
11:30 ARS-L1.4—LEARNING VISUAL CATEGORIES THROUGH A SPARSE REPRESENTATION CLASSIFIER BASED CROSS-CATEGORY KNOWLEDGE TRANSFER
11:50 ARS-L1.5—SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING
12:10 ARS-L1.6—A FAST LEARNING ALGORITHM FOR MULTI-LAYER EXTREME LEARNING MACHINE
CIP-L1: Computational Photography
Tuesday 10:30–12:30; Oral Session; Room: Ampere 5+6
10:30 CIP-L1.1—A COMPUTATIONAL PHOTOGRAPHY SHOOTOUT: WAVEFRONT CODING VS. LATTICE FOCAL IMAGING
10:50 CIP-L1.2—COST-AWARE DEPTH MAP ESTIMATION FOR LYTRO CAMERA
11:10 CIP-L1.3—RECONSTRUCTING SCENE DEPTH AND APPEARANCE BEHIND FOREGROUND OCCLUSION USING CAMERA ARRAY
11:30 CIP-L1.4—COMPUTATIONAL 3D AND REFLECTIVITY IMAGING WITH HIGH PHOTON EFFICIENCY
11:50 CIP-L1.5—PLENOPTIC SYSTEM IDENTIFICATION USING RANDOM CALIBRATION PATTERNS
12:10 CIP-L1.6—ILLUMINATION AND DEVICE INVARIANT IMAGE STITCHING
ELI-L1: Multiview and 3D Coding
Tuesday 10:30–12:30; Oral Session; Room: Dickens 3+4
10:30 ELI-L1.1—UNIFIED WEDGELET GENERATION FOR DEPTH CODING IN 3D-HEVC
10:50 ELI-L1.2—MRF-BASED PLANAR CO-SEGMENTATION FOR DEPTH COMPRESSION
11:10 ELI-L1.3—LUMINANCE CODING IN GRAPH-BASED REPRESENTATION OF MULTIVIEW IMAGES
11:30 ELI-L1.4—FULL PARALLAX SUPER MULTI-VIEW VIDEO CODING
11:50 ELI-L1.5—RATE CONTROL TECHNIQUE BASED ON 3D QUALITY OPTIMIZATION FOR 3D VIDEO ENCODING
12:10 ELI-L1.6—GENERAL RATE-ALLOCATION IN FREE-VIEWPOINT TELEVISION
TEC-L1: Medical-Image Segmentation
Tuesday 10:30–12:30; Oral Session; Room: Ampere 1+3
10:30 TEC-L1.1—ROBUST SHAPE-CONSTRAINED ACTIVE CONTOUR FOR WHOLE HEART SEGMENTATION IN 3-D CT IMAGES FOR RADIOTHERAPY PLANNING
10:50 TEC-L1.2—SIMULTANEOUS BIAS CORRECTION AND IMAGE SEGMENTATION VIA $L_0$ REGULARIZED MUMFORD-SHAH MODEL
11:10 TEC-L1.3—4DGVF SEGMENTATION OF VECTOR-VALUED IMAGES
11:30 TEC-L1.4—CROSS MODALITY LABEL FUSION IN MULTI-ATLAS SEGMENTATION
11:50 TEC-L1.5—IDENTIFYING REGIONS OF INTEREST FOR DISCRIMINATING ALZHEIMER’S DISEASE FROM MILD COGNITIVE IMPAIRMENT
12:10 TEC-L1.6—AUTOMATIC DENDRITIC SPINE DETECTION USING MULTISCALE DOT ENHANCEMENT FILTERS AND SIFT FEATURES
SS14: Synthetic-Aperture-Radar Imaging
Tuesday 10:30–12:30; Oral Session; Room: Dickens 1+2
10:30 SS14.1—CLASS EVOLUTION DATA ANALYTICS FROM SAR IMAGE TIME SERIES USING INFORMATION THEORY MEASURES
10:50 SS14.2—MODELING THE DISTRIBUTION OF PATCHES WITH SHIFT-INVARIANCE: APPLICATION TO SAR IMAGE RESTORATION
11:10 SS14.3—ROBUST JOINT DOWN- AND CROSS-RANGE SPARSE RECOVERY OF RAW ULTRA-WIDEBAND SAR DATA
11:30 SS14.4—FRACTAL DIMENSION IMAGES FROM SAR IMAGES
11:50 SS14.5—ESTIMATING BEDROCK AND SURFACE LAYER BOUNDARIES AND CONFIDENCE INTERVALS IN ICE SHEET RADAR IMAGERY USING MCMC
12:10 SS14.6—RADIO-FREQUENCY INTERFERENCE SEPARATION AND SUPPRESSION FROM ULTRA-WIDEBAND RADAR DATA VIA LOW-RANK MODELING
SS16: 3D Multimedia Experience Over the Future Internet
Tuesday 10:30–12:30; Oral Session; Room: Ampere 7+8
Session Chairs: Safak Dogan,
University of Surrey; Ahmet Kondoz,
Loughborough University
10:30 SS16.1—3D VIDEO STREAMING TRANSMISSION OVER OFDMA-BASED SYSTEMS
10:50 SS16.2—QOE MODEL OF SCALABLE MDC STEREOSCOPIC VIDEO OVER IP NETWORKS
11:10 SS16.3—DEPTH-ASSISTED STEREO VIDEO ENHANCEMENT USING GRAPH-BASED APPROACHES
11:30 SS16.4—AN APPROACH TO IMMERSIVE AUDIO RENDERING WITH WAVE FIELD SYNTHESIS FOR 3D MULTIMEDIA CONTENT
11:50 SS16.5—TOWARDS A FREE VIEWPOINT AND A 3D INTENSITY ADJUSTMENT ON MULTI-VIEW DISPLAY
12:10 SS16.6—ANALYSIS AND OPTIMIZATION OF PIXEL USAGE OF LIGHT-FIELD CONVERSION FROM MULTI-CAMERA SETUPS TO 3D LIGHT-FIELD DISPLAYS
ARS-P1: Motion Estimation
Tuesday 10:30–12:30; Poster Session; Poster Area A
ARS-P1.1—CARDIAC MOTION ANALYSIS USING WAVELET PROJECTIONS FROM TAGGED MR SEQUENCES
ARS-P1.2—HYBRID VISUAL AND INERTIAL RANSAC FOR REAL-TIME MOTION ESTIMATION
ARS-P1.3—PRESERVING ACCURATE MOTION CONTOURS WITH RELIABLE PARAMETER SELECTION
ARS-P1.4—BLOCK MOTION MATCHING ON DIRECTIONAL SUBBANDS WITH INTERBAND SUPPRESSION
ARS-P1.5—AGGREGATED MAPPING OF DRIVER ATTENTION FROM MATCHED OPTICAL FLOW
ARS-P1.6—REAL-TIME MOTION ESTIMATION BASED ON EVENT-BASED VISION SENSOR
ARS-P1.7—MODELLING THE OPTICAL-FLOW WITH PROJECTIVE-TRANSFORM APPROXIMATION FOR LARGE CAMERA MOVEMENTS
ARS-P1.8—RECOVERY OF MOTION PATTERNS AND DOMINANT PATHS IN VIDEOS OF CROWDED SCENES
ARS-P1.9—3-D MOTION ESTIMATION FOR VISUAL SALIENCY MODELING
ARS-P1.10—A PARTICLE FILTERING APPROACH TO SALIENT VIDEO OBJECT LOCALIZATION
ARS-P2: Face Detection and Recognition
Tuesday 10:30–12:30; Poster Session; Poster Area B
ARS-P2.1—NOVEL PRESENTATION ATTACK DETECTION ALGORITHM FOR FACE RECOGNITION SYSTEM: APPLICATION TO 3D FACE MASK ATTACK
ARS-P2.2—DLBP: A NOVEL DESCRIPTOR FOR DEPTH IMAGE BASED FACE RECOGNITION
ARS-P2.3—COUPLED DICTIONARIES FOR THERMAL TO VISIBLE FACE RECOGNITION
ARS-P2.4—PATCH BASED LOCAL PHASE QUANTIZATION OF MONOGENIC COMPONENTS FOR FACE RECOGNITION
ARS-P2.5—PERSON-SPECIFIC DOMAIN ADAPTATION WITH APPLICATIONS TO HETEROGENEOUS FACE RECOGNITION
ARS-P2.6—AN IMPROVED RETINAL MODELING FOR ILLUMINATION FACE RECOGNITION
ARS-P2.7—LOCAL VECTOR PATTERN IN HIGH-ORDER DERIVATIVE SPACE FOR FACE RECOGNITION
ARS-P2.8—TRANSFORM-INVARIANT DICTIONARY LEARNING FOR FACE RECOGNITION
ARS-P2.9—MAKEUP-INSENSITIVE FACE RECOGNITION BY FACIAL DEPTH RECONSTRUCTION AND GABOR FILTER BANK FROM WOMEN’S REAL-WORLD IMAGES
ARS-P2.10—ROBUST BLURRED FACE RECOGNITION USING SAMPLE-WISE KERNEL ESTIMATION AND RANDOM COMPRESSED MULTI-SCALE LOCAL BINARY PATTERN HISTOGRAMS
ARS-P2.11—DEPTH-BASED FACE RECOGNITION USING LOCAL QUANTIZED PATTERNS ADAPTED FOR RANGE DATA
ARS-P2.12—LIKELIHOOD-ENHANCED BAYESIAN CONSTRAINED LOCAL MODELS
ARS-P2.13—ON USING HOUGH FORESTS FOR ROBUST FACE DETECTION
ARS-P2.14—ENHANCED OMNIDIRECTIONAL IMAGE UNWRAPPING FOR FACE DETECTION
ARS-P2.15—HOG ACTIVE APPEARANCE MODELS
ARS-P2.16—VIDEO FACE NAMING USING GLOBAL SEQUENCE ALIGNMENT
ARS-P2.17—FACE IDENTIFICATION FROM OVERLAID TEXTS USING LOCAL FACE RECURRENT PATTERNS AND CRF MODELS
ARS-P2.18—CLEANING UP AFTER A FACE TRACKER: FALSE POSITIVE REMOVAL
ARS-P2.19—FRACTIONAL EIGENFACES
ARS-P2.20—DIRICHLET-TREE DISTRIBUTION ENHANCED RANDOM FORESTS FOR FACIAL FEATURE DETECTION
ARS-P2.21—SELECTIVE PART MODELS FOR DETECTING PARTIALLY OCCLUDED FACES IN THE WILD
ARS-P2.22—MULTI-SCALE MULTI-DESCRIPTOR LOCAL BINARY FEATURES AND EXPONENTIAL DISCRIMINANT ANALYSIS FOR ROBUST FACE AUTHENTICATION
ARS-P2.23—PHYSIOLOGICALLY-BASED DETECTION OF COMPUTER GENERATED FACES IN VIDEO
ARS-P2.24—A DATA-DRIVEN APPROACH TO CLEANING LARGE FACE DATASETS
ARS-P2.25—FACIAL ALIGNMENT BY USING SPARSE INITIALIZATION AND RANDOM FOREST
ARS-P2.26—NULL SPACE CLUSTERING WITH APPLICATIONS TO MOTION SEGMENTATION AND FACE CLUSTERING
ARS-P2.27—HEAD-SHOULDER HUMAN CONTOUR ESTIMATION IN STILL IMAGES
ARS-P3: Tracking
Tuesday 10:30–12:30; Poster Session; Poster Area C
ARS-P3.1—VISUAL TRACKING BASED ON WEIGHTED SUBSPACE RECONSTRUCTION ERROR
ARS-P3.2—3D OBJECT TRACKING VIA BOUNDARY CONSTRAINED REGION-BASED MODEL
ARS-P3.3—CONTOUR TRACKING VIA ON-LINE DISCRIMINATIVE ACTIVE CONTOURS
ARS-P3.4—ROBUST TRACKING VIA WEIGHTED SPATIO-TEMPORAL CONTEXT LEARNING
ARS-P3.5—STRUCTURE-AWARE MULTI-OBJECT DISCOVERY FOR WEAKLY SUPERVISED TRACKING
ARS-P3.6—A TOOL FOR FAST GROUND TRUTH GENERATION FOR OBJECT DETECTION AND TRACKING FROM VIDEO
ARS-P3.7—ROBUST OBJECT TRACKING VIA ONLINE INFORMATIVE FEATURE SELECTION
ARS-P3.8—CELL TRACKING USING PARTICLE FILTERS WITH IMPLICIT CONVEX SHAPE MODEL IN 4D CONFOCAL MICROSCOPY IMAGES
ARS-P3.9—GREEDY ALGORITHM FOR REAL-TIME MULTI-OBJECT TRACKING
ARS-P3.10—OBJECT TRACKING BASED ON ONLINE PARTIAL INSTANCE LEARNING WITH MULTIPLE LOCAL STRONG CLASSIFIERS
ARS-P3.11—DIRECT VISUAL TRACKING UNDER EXTREME ILLUMINATION VARIATIONS USING THE SUM OF CONDITIONAL VARIANCE
ARS-P3.12—ONLINE MULTI-PERSON TRACKING VIA ROBUST COLLABORATIVE MODEL
ARS-P3.13—COLLABORATING FRAMES: TEMPORALLY WEIGHTED SPARSE REPRESENTATION FOR VISUAL TRACKING
ARS-P3.14—A CONDITIONAL RANDOM FIELD MODEL FOR TRACKING IN DENSELY PACKED CELL STRUCTURES
ARS-P3.15—A TRACK-BEFORE-DETECT ALGORITHM USING JOINT PROBABILISTIC DATA ASSOCIATION FILTER AND INTERACTING MULTIPLE MODELS
ARS-P3.16—ASSESSING TRACKING ASSESSMENT MEASURES
ARS-P3.17—INTEGRATING HUMAN CONTEXT AND OCCLUSION REASONING TO IMPROVE HANDHELD OBJECT TRACKING
ARS-P3.18—MULTI-LEAF TRACKING FROM FLUORESCENCE PLANT VIDEOS
ARS-P3.19—MARKERLESS IDENTIFICATION AND TRACKING FOR SCALABLE IMAGE DATABASE
ARS-P3.20—REAL-TIME OBJECT TRACKING VIA OPTIMAL FEATURE SUBSPACE
ARS-P3.21—ROBUST TRACKING VIA SALIENCY-BASED APPEARANCE MODEL
ARS-P3.22—EXEMPLAR-BASED LINEAR DISCRIMINANT ANALYSIS FOR ROBUST OBJECT TRACKING
ARS-P3.23—ROBUST OBJECT TRACKING VIA MULTI-TASK DYNAMIC SPARSE MODEL
ARS-P3.24—OBJECT SEGMENTATION FROM A DYNAMIC BACKGROUND USING A PIXELWISE RIGIDITY CRITERION AND APPLICATION TO MARITIME TARGET RECOGNITION
ARS-P3.25—A PARTICLE SWARM OPTIMIZATION INSPIRED TRACKER APPLIED TO VISUAL TRACKING
ARS-P3.26—POINT MATCHING VIA AFFINE REGION EXPANSION
ARS-P3.27—A LOW RESOLUTION MULTI-CAMERA SYSTEM FOR PERSON TRACKING
ELI-P1: Color and Multispectral Imaging
Tuesday 10:30–12:30; Poster Session; Poster Area E
ELI-P1.1—DEMOSAICKING ALGORITHM FOR THE FUJIFILM X-TRANS COLOR FILTER ARRAY
ELI-P1.2—COLOR CORRECTION THROUGH REGION MATCHING LEVERAGED BY POINT CORRESPONDENCES
ELI-P1.3—A COLOR MORPHOLOGICAL ORDERING METHOD BASED ON ADDITIVE AND SUBTRACTIVE SPACES
ELI-P1.4—MULTISPECTRAL DEMOSAICKING WITH NOVEL GUIDE IMAGE GENERATION AND RESIDUAL INTERPOLATION
ELI-P1.5—EXEMPLAR-BASED COLORIZATION IN RGB COLOR SPACE
ELI-P1.6—COLOR DISTORTION CORRECTION WITHOUT NOISE BOOST USING MULTI-RESOLUTION ANALYSIS
ELI-P1.7—CAPTURING COLOR AND NEAR-INFRARED IMAGES WITH DIFFERENT EXPOSURE TIMES FOR IMAGE ENHANCEMENT UNDER EXTREMELY LOW-LIGHT SCENE
ELI-P1.8—COMPRESSED HYPERSPECTRAL IMAGE RECOVERY VIA TOTAL VARIATION REGULARIZATION ASSUMING LINEAR MIXING
ELI-P1.9—ADAPTIVE SPECTRAL REFLECTANCE RECOVERY USING SPATIO-SPECTRAL SUPPORT FROM HYPERSPECTRAL IMAGES
ELI-P1.10—SPECTRAL UNMIXING OF FLUORESCENCE FINGERPRINT IMAGERY FOR VISUALIZATION OF CONSTITUENTS IN PIE PASTRY
ELI-P1.11—A MODEL FOR ESTIMATING SPECTRAL PROPERTIES OF WATER FROM RGB IMAGES
ELI-P1.12—COLORED CODED APERTURES OPTIMIZATION IN COMPRESSIVE SPECTRAL IMAGING BY RESTRICTED ISOMETRY PROPERTY
ELI-P1.13—GAMUT MAPPING WITH IMAGE LAPLACIAN COMMUTATORS
ELI-P1.14—IMPROVING THE WHITE PATCH METHOD BY SUBSAMPLING
ELI-P1.15—IMAGE CLASSIFICATION IN NATURAL SCENES: ARE A FEW SELECTIVE SPECTRAL CHANNELS SUFFICIENT?
ELI-P1.16—GETTING A MORPHOLOGICAL TREE OF SHAPES FOR MULTIVARIATE IMAGES: PATHS, TRAPS, AND PITFALLS
ELI-P1.17—COLOR AND MULTISPECTRAL TEXTURE CHARACTERIZATION USING PSEUDO-MORPHOLOGICAL TOOLS
SMR-P1: Quality Assessment
Tuesday 10:30–12:30; Poster Session; Poster Area D
SMR-P1.1—MYSTERY BEHIND SIMILARITY MEASURES MSE AND SSIM
SMR-P1.2—NO-REFERENCE PERCEPTUAL BLUR MODEL BASED ON INHERENT SHARPNESS
SMR-P1.3—AN EFFICIENT COLOR IMAGE QUALITY METRIC WITH LOCAL-TUNED-GLOBAL MODEL
SMR-P1.4—QUALITY ASSESSMENT OF POLARIZATION ANALYSIS IMAGES IN FOGGY CONDITIONS
SMR-P1.5—A CONSISTENT PIXEL-WISE BLUR MEASURE FOR PARTIALLY BLURRED IMAGES
SMR-P1.6—OPTIMIZING FEATURE POOLING AND PREDICTION MODEL OF VQA ALGORITHMS
SMR-P1.7—DEEP LEARNING NETWORK FOR BLIND IMAGE QUALITY ASSESSMENT
SMR-P1.8—A PARAMETRIC VIDEO QUALITY MODEL BASED ON SOURCE AND NETWORK CHARACTERISTICS
SMR-P1.9—PERCEPTUAL COLOR DIFFERENCE ASSESSMENT USING HISTOGRAM DISTANCE ON HUE HISTOGRAM DESCRIPTOR
SMR-P1.10—TOWARDS A NEW IMAGE QUALITY METRIC FOR EVALUATING THE EFFECTS OF TILED DISPLAYS
SMR-P1.11—NO-REFERENCE BLUR ASSESSMENT IN NATURAL IMAGES USING FOURIER TRANSFORM AND SPATIAL PYRAMIDS
SMR-P1.12—NO-REFERENCE VIDEO QUALITY ASSESSMENT VIA FEATURE LEARNING
SMR-P1.13—FUSION OF IMPRECISE DATA APPLIED TO IMAGE QUALITY ASSESSMENT
SMR-P1.14—A REDUCED REFERENCE PERCEPTUAL QUALITY METRIC FOR TEXTURE SYNTHESIS
SMR-P1.15—NO-REFERENCE QUALITY ASSESSMENT OF JPEG IMAGES VIA A QUALITY RELEVANCE MAP
SMR-P1.16—IMAGE QUALITY/DISTORTION METRIC BASED ON Α-STABLE MODEL SIMILARITY
SMR-P1.17—REDUCED-REFERENCE METRIC BASED ON THE QUATERNIONIC WAVELET COEFFICIENTS MODELING BY INFORMATION CRITERIA
SMR-P1.18—SYNTHESIS QUALITY PREDICTION MODEL BASED ON DISTORTION INTOLERANCE
SMR-P1.19—AESTHETIC QUALITY CLASSIFICATION VIA SUBJECT REGION EXTRACTION
SMR-P1.20—COMPRESSED IMAGE QUALITY ASSESSMENT: APPLICATION TO AN INTERACTIVE UPPER LIMB RADIOLOGY ATLAS
SMR-P1.21—ASSESSMENT OF VIDEO NATURALNESS USING TIME-FREQUENCY STATISTICS
SMR-P1.22—A COMPARATIVE STUDY OF COMPUTATIONAL AESTHETICS
SMR-P1.23—FINDING YOUR SPOT: A PHOTOGRAPHY SUGGESTION SYSTEM FOR PLACING HUMAN IN THE SCENE
ARS-L2: Deep Networks
Tuesday 14:00–16:00; Oral Session; Room: Leonard de Vinci
14:00 ARS-L2.1—DA-CCD: A NOVEL ACTION REPRESENTATION BY DEEP ARCHITECTURE OF LOCAL DEPTH FEATURE
14:20 ARS-L2.2—LEARNING DEEP FEATURES FOR MULTIPLE OBJECT TRACKING BY USING A MULTI-TASK LEARNING STRATEGY
14:40 ARS-L2.3—AN ENSEMBLE OF DEEP NEURAL NETWORKS FOR OBJECT TRACKING
15:00 ARS-L2.4—SEMI-SUPERVISED DEEP LEARNING FOR OBJECT TRACKING AND CLASSIFICATION
15:20 ARS-L2.5—HAND POSTURE RECOGNITION BASED ON BOTTOM-UP STRUCTURED DEEP CONVOLUTIONAL NEURAL NETWORK WITH CURRICULUM LEARNING
15:40 ARS-L2.6—DEEP CONVOLUTIONAL NEURAL NETWORK BASED IMAGE CLASSIFICATION FOR WILD ANIMAL MONITORING
ARS-L3: Face Recognition
Tuesday 14:00–16:00; Oral Session; Room: Ampere 5+6
14:00 ARS-L3.1—LOCAL STRUCTURE BASED SPARSE REPRESENTATION FOR FACE RECOGNITION WITH SINGLE SAMPLE PER PERSON
14:20 ARS-L3.2—EXTENDED LOCAL BINARY PATTERN FUSION FOR FACE RECOGNITION
14:40 ARS-L3.3—IS BLOCK-MATCHING AN ALTERNATIVE TOOL TO LBP FOR FACE RECOGNITION?
15:00 ARS-L3.4—3D ASSISTED FACE RECOGNITION VIA PROGRESSIVE POSE ESTIMATION
15:20 ARS-L3.5—DICTIONARY-BASED VIDEO FACE RECOGNITION USING DENSE MULTI-SCALE FACIAL LANDMARK FEATURES
15:40 ARS-L3.6—SCENARIO ORIENTED DISCRIMINANT ANALYSIS FOR STILL-TO-VIDEO FACE RECOGNITION
TEC-L2: Image Denoising
Tuesday 14:00–16:00; Oral Session; Room: Dickens 3+4
14:00 TEC-L2.1—LEARNING OVERCOMPLETE SPARSIFYING TRANSFORMS WITH BLOCK COSPARSITY
14:20 TEC-L2.2—IMAGE DENOISING THROUGH MULTI-SCALE LEARNT DICTIONARIES
14:40 TEC-L2.3—NON-LOCAL DUAL IMAGE DENOISING
15:00 TEC-L2.4—GLOBAL DENOISING IS ASYMPTOTICALLY OPTIMAL
15:20 TEC-L2.5—AN EFFECTIVE EXAMPLE-BASED LEARNING METHOD FOR DENOISING OF MEDICAL IMAGES CORRUPTED BY HEAVY GAUSSIAN NOISE AND POISSON NOISE
15:40 TEC-L2.6—DEPTH MAP DENOISING USING COLLABORATIVE GRAPH WAVELET SHRINKAGE ON CONNECTED IMAGE PATCHES
SS19: Image Processing for the Detection of Road-Surface Degradations
Tuesday 14:00–16:00; Oral Session; Room: Dickens 1+2
Session Chair: Henrique Oliveira,
Instituto de Telecomunicações
14:00 SS19.1—IMPLEMENTATION OF AUTOMATIC CRACK EVALUATION USING CRACK FUNDAMENTAL ELEMENT
14:20 SS19.2—ENHANCED AUTOMATIC DETECTION OF ROAD SURFACE CRACKS BY COMBINING 2D/3D IMAGE PROCESSING TECHNIQUES
14:40 SS19.3—2D IMAGE BASED ROAD PAVEMENT CRACK DETECTION BY CALCULATING MINIMAL PATH AND DYNAMIC PROGRAMMING
15:00 SS19.4—A NEW MINIMAL PATH SELECTION ALGORITHM FOR AUTOMATIC CRACK DETECTION ON PAVEMENT IMAGES
15:20 SS19.5—PAVEMENT PATHOLOGIES CLASSIFICATION USING GRAPH-BASED FEATURES
15:40 SS19.6—CRACKIT – AN IMAGE PROCESSING TOOLBOX FOR CRACK DETECTION AND CHARACTERIZATION
SS5: Hyperspectral Image Processing
Tuesday 14:00–16:00; Oral Session; Room: Ampere 1+3
Session Chairs: Jocelyn Chanussot,
Grenoble Institute of Technology; Saurabh Prasad,
University of Houston
14:00 SS5.1—COMPRESSIVE PUSHBROOM AND WHISKBROOM SENSING FOR HYPERSPECTRAL REMOTE-SENSING IMAGING
14:20 SS5.2—GRAPH MBO METHOD FOR MULTICLASS SEGMENTATION OF HYPERSPECTRAL STAND-OFF DETECTION VIDEO
14:40 SS5.3—HYPERSPECTRAL UNMIXING USING AN ACTIVE SET ALGORITHM
15:00 SS5.4—BAYESIAN FUSION OF MULTISPECTRAL AND HYPERSPECTRAL IMAGES WITH UNKNOWN SENSOR SPECTRAL RESPONSE
15:20 SS5.5—HYPERSPECTRAL SUPER-RESOLUTION OF LOCALLY LOW RANK IMAGES FROM COMPLEMENTARY MULTISOURCE DATA
15:40 SS5.6—TOWARD A FULL-BAND TEXTURE FEATURES FOR SPECTRAL IMAGES
SS8: Quality of Experience in 3D Multimedia Systems
Tuesday 14:00–16:00; Oral Session; Room: Ampere 7+8
Session Chairs: Janko Calic,
Surrey University; Patrick Le Callet,
Polytechnique Nantes
14:00 SS8.1—CROWD-BASED QUALITY ASSESSMENT OF MULTIVIEW VIDEO PLUS DEPTH CODING
14:20 SS8.2—QUALITY OF INTERACTION EXPERIENCE IN STEREOSCOPIC 3D TV
14:40 SS8.3—EXPLORING THE EFFECTS OF 3D VISUAL DISCOMFORT ON VIEWERS’ EMOTIONS
15:00 SS8.4—DEEP LEARNING FOR OBJECTIVE QUALITY ASSESSMENT OF 3D IMAGES
15:20 SS8.5—NO-REFERENCE LIGHTWEIGHT ESTIMATION OF 3D VIDEO OBJECTIVE QUALITY
15:40 SS8.6—MEASUREMENT OF PERCEIVED SPATIAL RESOLUTION IN 3D LIGHT-FIELD DISPLAYS
ARS-P4: Scene Analysis
Tuesday 14:00–16:00; Poster Session; Poster Area B
ARS-P4.1—TRAJECTORY CLUSTERING FOR MOTION PATTERN EXTRACTION IN AERIAL VIDEOS
ARS-P4.2—SCENE TEXT RECOGNITION USING SPARSE CODING BASED FEATURES
ARS-P4.3—GEOMETRY-CONSTRAINED SPATIAL PYRAMID ADAPTATION FOR IMAGE CLASSIFICATION
ARS-P4.4—CLASSIFICATION OF 2D AND 3D IMAGES USING PYRAMID SCALE DECISION VOTING
ARS-P4.5—INTERSECTING 2D LINES: A SIMPLE METHOD FOR DETECTING VANISHING POINTS
ARS-P4.6—ROBUST REAR-VIEW GROUND SURFACE DETECTION WITH HIDDEN STATE CONDITIONAL RANDOM FIELD AND CONFIDENCE PROPAGATION
ARS-P4.7—IMAGE-BASED FLOOR DETECTION FOR INDOOR SCENE ANALYSIS
ARS-P4.8—MONOCULAR ALBEDO RECONSTRUCTION
ARS-P4.9—TRUNCATED ISOTROPIC PRINCIPAL COMPONENT CLASSIFIER FOR IMAGE CLASSIFICATION
ARS-P4.10—A NOVEL AND EFFECTIVE METHOD FOR SPECULAR DETECTION AND REMOVAL BY TENSOR VOTING
ARS-P4.11—SELF-LOCALIZATION ON TEXTURE STATISTICS
ARS-P4.12—COARSE INDOOR LOCALIZATION USING SPACE-TIME AND SEMANTIC-CONTEXT REPRESENTATIONS OF GEO-REFERENCED VIDEO SEQUENCES
ARS-P4.13—SEMANTIC SEGMENTATION AS IMAGE REPRESENTATION FOR SCENE RECOGNITION
ARS-P4.14—DETECTION OF DYNAMIC OBJECTS FOR ENVIRONMENT MAPPING BY TIME-OF-FLIGHT CAMERAS
ARS-P4.15—VIDEO BACKGROUND MODELING UNDER IMPULSE NOISE
ARS-P4.16—LINE-BASED GLOBAL DESCRIPTOR FOR OMNIDIRECTIONAL VISION
ARS-P4.17—AFFINE-INVARIANT SCENE CATEGORIZATION
ARS-P4.18—VANISHING POINT ESTIMATION FOR CHALLENGING ROAD IMAGES
ARS-P4.19—ANALYZING SEDENTARY BEHAVIOR IN LIFE-LOGGING IMAGES
ARS-P4.20—SUM-MAX VIDEO POOLING FOR COMPLEX EVENT RECOGNITION
ARS-P4.21—NOVEL FRAMEWORK FOR SPORTS VIDEO ANALYSIS: A BASKETBALL CASE STUDY
ARS-P4.22—GENRE CATEGORIZATION OF AMATEUR SPORTS VIDEOS IN THE WILD
ARS-P4.23—IT’S ALL ABOUT HABITS: EXPLOITING MULTI-TASK CLUSTERING FOR ACTIVITIES OF DAILY LIVING ANALYSIS
ARS-P4.24—MULTI-LEVEL SCENE UNDERSTANDING VIA HIERARCHICAL CLASSIFICATION
ARS-P4.25—POSELET-BASED MULTIPLE HUMAN IDENTIFICATION AND COSEGMENTATION
ELI-P2: Hardware and Software Image-Processing Systems
Tuesday 14:00–16:00; Poster Session; Poster Area D
ELI-P2.1—FAST SAO ESTIMATION ALGORITHM AND ITS VLSI ARCHITECTURE
ELI-P2.2—HIGH-THROUGHPUT MQ CODER ARCHITECTURE BASED ON DEPENDENCE EXTRACTION METHOD
ELI-P2.3—VLSI ARCHITECTURE OF HEVC INTRA PREDICTION FOR 8K UHDTV APPLICATIONS
ELI-P2.4—A SCALABLE ARCHITECTURE FOR IMPLEMENTING THE FAST DISCRETE PERIODIC RADON TRANSFORM FOR PRIME SIZED IMAGES
ELI-P2.5—HIGH SPEED SAD ARCHITECTURES FOR VARIABLE BLOCK SIZE MOTION ESTIMATION IN HEVC VIDEO CODING
ELI-P2.6—A HIGH SPEED CONFIGURABLE FPGA ARCHITECTURE FOR BILATERAL FILTERING
ELI-P2.7—A 610 MBIN/S CABAC DECODER FOR H.265/HEVC LEVEL 6.1 APPLICATIONS
ELI-P2.8—RECONFIGURABLE DATA FLOW ENGINE FOR HEVC MOTION ESTIMATION
ELI-P2.9—HARDWARE ARCHITECTURE OF THE FAST MODE DECISION ALGORITHM FOR H.265/HEVC
ELI-P2.10—CORDIC BASED FAST RADIX-2 DCT ALGORITHM
ELI-P2.11—COLLABORATIVE INTER-PREDICTION ON CPU+GPU SYSTEMS
ELI-P2.12—POWER EFFICIENT AND WORKLOAD BALANCED TILING FOR PARALLELIZED HIGH EFFICIENCY VIDEO CODING
ELI-P2.13—AN SMPUMHEXAGONS-BASED MOTION ESTIMATION ALGORITHM FOR HETEROGENEOUS ARCHITECTURES
ELI-P2.14—OPENCL BASED HIGH-QUALITY HEVC MOTION ESTIMATION ON GPU
ELI-P2.15—A PARALLEL TRUE MOTION ESTIMATION METHOD BASED ON BINARIZED CROSS CORRELATION
ELI-P2.16—A FAST MIXED-BAND LIFTING WAVELET TRANSFORM ON THE GPU
ELI-P2.17—A HIGHLY PARALLELIZED H.265/HEVC REAL-TIME UHD SOFTWARE ENCODER
ELI-P2.18—A SENSOR AIDED H.264 ENCODER TESTED ON AERIAL IMAGERY FOR SFM
ELI-P2.19—ENERGY CONSUMPTION ANALYSIS AND MODELLING OF A H.264/AVC INTRA-ONLY BASED ENCODER DEDICATED TO WVSNS
ELI-P2.20—A LOW ENERGY HEVC SUB-PIXEL INTERPOLATION HARDWARE
SMR-P2: Visual Saliency
Tuesday 14:00–16:00; Poster Session; Poster Area C
SMR-P2.1—VISUAL SALIENCY DETECTION USING FEATURE ACTIVITY WEIGHTED DECORRELATION CUES
SMR-P2.2—VIDEO SALIENCY DETECTION BASED ON SPATIOTEMPORAL FEATURE LEARNING
SMR-P2.3—A PRIOR-BASED GRAPH FOR SALIENT OBJECT DETECTION
SMR-P2.4—COMPARISON OF VISUAL SALIENCY MODELS FOR COMPRESSED VIDEO
SMR-P2.5—A SCALABLE AND EFFICIENT METHOD FOR SALIENT REGION DETECTION USING SAMPLED TEMPLATE COLLATION
SMR-P2.6—LEARNING VISUAL SALIENCY USING TOPOGRAPHIC INDEPENDENT COMPONENT ANALYSIS
SMR-P2.7—INFLUENCE OF COLOR ON VISUAL SALIENCY IN SHORT VIDEOS
SMR-P2.8—SPATIO-TEMPORAL ANALYSIS OF EYE FIXATIONS DATA IN IMAGES
SMR-P2.9—SALIENT REGION DETECTION USING BACKGROUND CONTRAST
SMR-P2.10—EXPLORING COVERT ATTENTION FOR GENERIC BOOSTING OF SALIENCY MODELS
SMR-P2.11—HOW DOES DISTORTION AFFECT SALIENCY APPLIED TO IMAGE QUALITY ASSESSMENT?
SMR-P2.12—AN AUDIOVISUAL ATTENTION MODEL FOR NATURAL CONVERSATION SCENES
SMR-P2.13—A PSYCHOPHYSICAL EVALUATION OF THE A CONTRARIO DETECTION THEORY
SMR-P2.14—ANALYSIS OF IMAGE INFORMATIVENESS MEASURES
SMR-P2.15—DEPTH SALIENCY BASED ON ANISOTROPIC CENTER-SURROUND DIFFERENCE
SMR-P2.16—SEMIAUTOMATIC VISUAL-ATTENTION MODELING AND ITS APPLICATION TO VIDEO COMPRESSION
SMR-P2.17—SALIENT OBJECT DETECTION USING BIPARTITE DICTIONARY
SMR-P2.18—SALIENT REGION DETECTION VIA COLOR SPATIAL DISTRIBUTION DETERMINED GLOBAL CONTRASTS
SMR-P2.19—GMM-BASED SALIENCY AGGREGATION FOR CALIBRATION-FREE GAZE ESTIMATION
SMR-P2.20—FOREGROUND OBJECT DETECTION IN HIGHLY DYNAMIC SCENES USING SALIENCY
SMR-P2.21—IMAGE SEAM CARVING USING DEPTH ASSISTED SALIENCY MAP
SMR-P2.22—SALIENCY DETECTION USING SUPERPIXEL BELIEF PROPAGATION
TEC-P1: Segmentation of Medical and Biomedical Images
Tuesday 14:00–16:00; Poster Session; Poster Area A
TEC-P1.1—A MUTUAL REFERENCE SHAPE BASED ON INFORMATION THEORY
TEC-P1.2—ACTIVE CONTOURS BASED ON WEIGHTED GRADIENT VECTOR FLOW AND BALLOON FORCES FOR MEDICAL IMAGE SEGMENTATION
TEC-P1.3—A NON-LOCAL CHAN-VESE MODEL FOR SPARSE, TUBULAR OBJECT SEGMENTATION
TEC-P1.4—NEW DATA MODEL FOR GRAPH-CUT SEGMENTATION: APPLICATION TO AUTOMATIC MELANOMA DELINEATION
TEC-P1.5—ON RETINAL BLOOD VESSEL EXTRACTION USING CURVELET TRANSFORM AND DIFFERENTIAL EVOLUTION BASED MAXIMUM FUZZY ENTROPY
TEC-P1.6—A ROBUST CONVERGENCE INDEX FILTER FOR BREAST CANCER CELL SEGMENTATION
TEC-P1.7—ONE-SHOT SEGMENTATION OF BREAST, PECTORAL MUSCLE, AND BACKGROUND IN DIGITISED MAMMOGRAMS
TEC-P1.8—A FORMAL METHOD FOR SELECTING EVALUATION METRICS FOR IMAGE SEGMENTATION
TEC-P1.9—A LEVEL-SET APPROACH FOR TRACKING OBJECTS IN IMAGE SEQUENCES USING A LEVEL CONSERVATION CONSTRAINT: APPLICATION TO CARDIAC SEQUENCES
TEC-P1.10—AUTOMATIC BLASTOMERE DETECTION IN DAY 1 TO DAY 2 HUMAN EMBRYO IMAGES USING PARTITIONED GRAPHS AND ELLIPSOIDS
TEC-P1.11—AUTOMATIC METHOD FOR TUMOR SEGMENTATION FROM 3-POINTS DYNAMIC PET ACQUISITIONS
TEC-P1.12—FAST AND ROBUST IMAGE SEGMENTATION USING AN SUPERPIXEL BASED FCM ALGORITHM
TEC-P1.13—LUNG SEGMENTATION BASED ON NONNEGATIVE MATRIX FACTORIZATION
TEC-P1.14—VFCCV SNAKE: A NOVEL ACTIVE CONTOUR MODEL COMBINING EDGE AND REGIONAL INFORMATION
TEC-P1.15—COMPARATIVE PERFORMANCE OF TEXTON BASED VASCULAR TREE SEGMENTATION IN RETINAL IMAGES
TEC-P1.16—GRAPH-BASED SKIN LESION SEGMENTATION OF MULTISPECTRAL DERMOSCOPIC IMAGES
TEC-P1.17—SPATIAL DENSITY ESTIMATION BASED SEGMENTATION OF SUPER-RESOLUTION LOCALIZATION MICROSCOPY IMAGES
TEC-P1.18—UNDECIMATED HIERARCHICAL ACTIVE CONTOURS FOR OCT IMAGE SEGMENTATION
TEC-P1.19—3D INTERACTIVE CORONARY ARTERY SEGMENTATION USING RANDOM FORESTS AND MARKOV RANDOM FIELD OPTIMIZATION
TEC-P2: Compressive Sensing
Tuesday 14:00–16:00; Poster Session; Poster Area E
TEC-P2.1—RECONSTRUCTION OF COMPRESSIVELY SAMPLED ULTRASOUND IMAGES USING DUAL PRIOR INFORMATION
TEC-P2.2—BLIND SPECTRAL UNMIXING FOR COMPRESSIVE HYPERSPECTRAL IMAGING OF HIGHLY MIXED DATA
TEC-P2.3—A SPARSE KACZMARZ SOLVER AND A LINEARIZED BREGMAN METHOD FOR ONLINE COMPRESSED SENSING
TEC-P2.4—DETAIL-PRESERVING COMPRESSIVE SENSING RECOVERY BASED ON CARTOON TEXTURE IMAGE DECOMPOSITION
TEC-P2.5—PHASE RETRIEVAL OF SPARSE SIGNALS USING OPTIMIZATION TRANSFER AND ADMM
TEC-P2.6—DOWNWARD SPATIALLY-SCALABLE IMAGE RECONSTRUCTION BASED ON COMPRESSED SENSING
TEC-P2.7—SPARSE IMAGE RECOVERY USING COMPRESSED SENSING OVER FINITE ALPHABETS
TEC-P2.8—REAL-TIME COMPRESSED IMAGING OF SCATTERING VOLUMES
TEC-P2.9—RECURSIVE PROJECTED SPARSE MATRIX RECOVERY (REPROSMR) WITH APPLICATION IN REAL-TIME VIDEO LAYER SEPARATION
TEC-P2.10—GENERALIZED-KFCS: MOTION ESTIMATION ENHANCED KALMAN FILTERED COMPRESSIVE SENSING FOR VIDEO
TEC-P2.11—RECONSTRUCTION OF COMPRESSIVELY SAMPLED TEXTURE IMAGES IN THE GRAPH-BASED TRANSFORM DOMAIN
TEC-P2.12—ADAPTIVE MEASUREMENT RATE ALLOCATION FOR BLOCK-BASED COMPRESSED SENSING OF DEPTH MAPS
TEC-P2.13—SPLIT BREGMAN ALGORITHMS FOR SPARSE / JOINT-SPARSE AND LOW-RANK SIGNAL RECOVERY: APPLICATION IN COMPRESSIVE HYPERSPECTRAL IMAGING
TEC-P2.14—COMPRESSED SENSING RECONSTRUCTION OF 3D ULTRASOUND DATA USING DICTIONARY LEARNING
TEC-P2.15—A HIERARCHICAL BAYESIAN-MAP APPROACH TO COMPUTATIONAL IMAGING
ARS-L4: Manifold Learning
Tuesday 16:30–18:10; Oral Session; Room: Ampere 5+6
16:30 ARS-L4.1—UNSUPERVISED MANIFOLD LEARNING BY CORRELATION GRAPH AND STRONGLY CONNECTED COMPONENTS FOR IMAGE RETRIEVAL
16:30 ARS-L4.2—LEARNING IMAGE MANIFOLD USING NEIGHBORING SIMILARITY INTEGRATION
16:30 ARS-L4.3—VISUAL OBJECT TRACKING WITH ONLINE LEARNING ON RIEMANNIAN MANIFOLDS BY ONE-CLASS SUPPORT VECTOR MACHINES
16:30 ARS-L4.4—LEARNING ASSOCIATE APPEARANCE MANIFOLDS FOR CROSS-POSE FACE RECOGNITION
16:30 ARS-L4.5—IMPROVING HEAD AND BODY POSE ESTIMATION THROUGH SEMI-SUPERVISED MANIFOLD ALIGNMENT
ARS-L5: Optical Flow Estimation
Tuesday 16:30–18:10; Oral Session; Room: Dickens 3+4
16:30 ARS-L5.1—ROBUST PROBABILISTIC OPTICAL FLOW FOR VIDEO SEQUENCES
16:50 ARS-L5.2—CROSS BASED ROBUST LOCAL OPTICAL FLOW
17:10 ARS-L5.3—LOCAL TEXTURE BASED OPTICAL FLOW FOR COMPLEX BRIGHTNESS VARIATIONS
17:30 ARS-L5.4—OPTICAL FLOW FOR NON LAMBERTIAN SURFACES BY CANCELLING ILLUMINANT CHROMATICITY
17:50 ARS-L5.5—ARE REFLECTANCE FIELD RENDERINGS APPROPRIATE FOR OPTICAL FLOW EVALUATION?
SMR-L1: Image and Video Quality
Tuesday 16:30–18:10; Oral Session; Room: Leonard de Vinci
16:30 SMR-L1.1—NEURALLY INFORMED ASSESSMENT OF PERCEIVED NATURAL TEXTURE IMAGE QUALITY
16:50 SMR-L1.2—STRUCTURAL TEXTURE SIMILARITY METRIC BASED ON INTRA-CLASS VARIANCES
17:10 SMR-L1.3—FULL REFERENCE VIDEO QUALITY ESTIMATION FOR VIDEOS WITH DIFFERENT SPATIAL RESOLUTIONS
17:30 SMR-L1.4—STEREOSCOPIC IMAGE QUALITY METRIC BASED ON LOCAL ENTROPY AND BINOCULAR JUST NOTICEABLE DIFFERENCE
17:50 SMR-L1.5—DELIVERY QUALITY SCORE MODEL FOR INTERNET VIDEO
TEC-L3: Magnetic Resonance Imaging
Tuesday 16:30–18:10; Oral Session; Room: Ampere 1+3
16:30 TEC-L3.1—ENTROPY RATE ESTIMATION FOR VECTOR PROCESSES: APPLICATION TO COMPLEX FMRI ANALYSIS
16:50 TEC-L3.2—UNSUPERVISED WHITE MATTER FIBER TRACTS CLUSTERING METHODOLOGY WITH APPLICATION ON BRAIN MRI DATA
17:10 TEC-L3.3—MODEL-BASED ESTIMATION OF T2 MAPS WITH DUAL-ECHO STEADY-STATE MR IMAGING
17:30 TEC-L3.4—A REGULARIZED TRUST REGION METHOD FOR JOINT RECONSTRUCTION OF SPIN MAGNITUDE, $T_2^*$ DECAY, AND OFF-RESONANCE FIELD MAP
17:50 TEC-L3.5—BRAIN TUMOR SEGMENTATION FROM MULTIPLE MRI SEQUENCES USING MULTIPLE KERNEL LEARNING
SS13: Advances in Facial Morpho-Functional Sign Recognition and Analysis
Tuesday 16:30–17:50; Oral Session; Room: Dickens 1+2
Session Chairs: A. Enis Cetin,
Bilkent University; Sara Colantonio,
ISTI-CNR
16:30 SS13.1—THE THERMAL DIMENSION OF PSYCHOPHYSIOLOGICAL AND EMOTIONAL RESPONSES REVEALED BY THERMAL INFRARED IMAGING
16:50 SS13.2—AUTOMATIC HEART RATE ESTIMATION FROM PAINFUL FACES
17:10 SS13.3—CLICK AND SHARE: A FACE RECOGNITION TOOL FOR THE MOBILE COMMUNITY
17:30 SS13.4—HEAD POSE TRACKING FOR IMMERSIVE APPLICATIONS
SS3: Plenoptic Imaging (Capture, Representation, Processing and Display)
Tuesday 16:30–18:10; Oral Session; Room: Ampere 7+8
Session Chairs: Atanas Gotchev,
Tampere University of Technology; Mårten Sjöström,
Mid Sweden University
16:30 SS3.1—TILTED LAYER-BASED MODELING FOR ENHANCED LIGHT-FIELD PROCESSING AND IMAGE BASED RENDERING
16:50 SS3.2—THE RADON IMAGE AS PLENOPTIC FUNCTION
17:10 SS3.3—3D KEYPOINT DETECTION BY LIGHT FIELD SCALE-DEPTH SPACE ANALYSIS
17:30 SS3.4—SPATIAL RESOLUTION IN A MULTI-FOCUS PLENOPTIC CAMERA
17:50 SS3.5—DENSE LIGHTFIELD RECONSTRUCTION FROM MULTI APERTURE CAMERAS
ARS-P5: Face Analysis
Tuesday 16:10–18:10; Poster Session; Poster Area A
ARS-P5.1—ADAPTIVE FEATURE SELECTION AND DATA PRUNING FOR 3D FACIAL EXPRESSION RECOGNITION USING THE KINECT
ARS-P5.2—REMOTE PPG BASED VITAL SIGN MEASUREMENT USING ADAPTIVE FACIAL REGIONS
ARS-P5.3—FACIAL GRID TRANSFORMATION: A NOVEL FACE REGISTRATION APPROACH FOR IMPROVING FACIAL ACTION UNIT RECOGNITION
ARS-P5.4—JOINTLY DETECTING INFANTS’ MULTIPLE FACIAL ACTION UNITS EXPRESSED DURING SPONTANEOUS FACE-TO-FACE COMMUNICATION
ARS-P5.5—AN ADAPTIVE GROUP LASSO BASED MULTI-LABEL REGRESSION APPROACH FOR FACIAL EXPRESSION ANALYSIS
ARS-P5.6—FACIAL ACTION UNIT INTENSITY ESTIMATION USING ROTATION INVARIANT FEATURES AND REGRESSION ANALYSIS
ARS-P5.7—LEARNING SYMMETRIC FACE POSE MODELS ONLINE USING LOCALLY WEIGHTED PROJECTRON REGRESSION
ARS-P5.8—ONE SHOT EMOTION SCORES FOR FACIAL EMOTION RECOGNITION
ARS-P5.9—WHAT DOES COMPUTER VISION SAY ABOUT FACE READING?
ARS-P5.10—RESOLUTION LIMITS ON VISUAL SPEECH RECOGNITION
ARS-P5.11—FAST NEWTON ACTIVE APPEARANCE MODELS
ARS-P5.12—3D FACIAL GEOMETRIC FEATURES FOR CONSTRAINED LOCAL MODEL
ARS-P5.13—SLOW FEATURES NONNEGATIVE MATRIX FACTORIZATION FOR TEMPORAL DATA DECOMPOSITION
ARS-P5.14—FIDUCIAL FACIAL POINT EXTRACTION WITH CROSS RATIO
ARS-P5.15—LOCAL AGE GROUP MODELING IN UNCONSTRAINED FACE IMAGES FOR FACIAL AGE CLASSIFICATION
ARS-P5.16—FAST EYE LOCALIZATION WITHOUT A FACE MODEL USING INNER PRODUCT DETECTORS
ARS-P5.17—MARKED POINT PROCESS MODEL FOR FACIAL WRINKLE DETECTION
ARS-P6: Action and Gesture Analysis
Tuesday 16:10–18:10; Poster Session; Poster Area B
ARS-P6.1—RANDOMIZED DECISION BUSH: COMBINING GLOBAL SHAPE PARAMETERS AND LOCAL SCALABLE DESCRIPTORS FOR HUMAN BODY PARTS RECOGNITION
ARS-P6.2—KINECT-BASED MULTIMODAL GESTURE RECOGNITION USING A TWO-PASS FUSION SCHEME
ARS-P6.3—GESTURE DYNAMICS MODELING FOR ATTITUDE ANALYSIS USING GRAPH BASED TRANSFORM
ARS-P6.4—LABEL PROPAGATION ON DATA WITH MULTIPLE REPRESENTATIONS THROUGH MULTI-GRAPH LOCALITY PRESERVING PROJECTIONS
ARS-P6.5—HAND GESTURE RECOGNITION WITH LEAP MOTION AND KINECT DEVICES
ARS-P6.6—AN EFFICIENT METHOD FOR HUMAN POINTING ESTIMATION FOR ROBOT INTERACTION
ARS-P6.7—HAND POSTURE RECOGNITION USING APPROXIMATE VANISHING IDEAL GENERATORS
ARS-P6.8—A CORRESPONDENCE BASED METHOD FOR ACTIVITY RECOGNITION IN HUMAN SKELETON MOTION SEQUENCES
ARS-P6.9—SMILE DETECTION IN UNCONSTRAINED SCENARIOS USING SELF-SIMILARITY OF GRADIENTS FEATURES
ARS-P6.10—ACTION CLASSIFICATION BY EXPLORING DIRECTIONAL CO-OCCURRENCE OF WEIGHTED STIPS
ARS-P6.11—ACTION RECOGNITION BASED ON KINEMATIC REPRESENTATION OF VIDEO DATA
ARS-P6.12—DETECTING SELF-STIMULATORY BEHAVIOURS FOR AUTISM DIAGNOSIS
ARS-P6.13—HUMAN ACTION RECOGNITION BASED ON BAG OF FEATURES AND MULTI-VIEW NEURAL NETWORKS
ARS-P6.14—FREQUENCYGRAMS AND MULTI-FEATURE JOINT SPARSE REPRESENTATION FOR ACTION AND GESTURE RECOGNITION
ARS-P6.15—DENSE BODY PART TRAJECTORIES FOR HUMAN ACTION RECOGNITION
ARS-P6.16—ADVANCES ON ACTION RECOGNITION IN VIDEOS USING AN INTEREST POINT DETECTOR BASED ON MULTIBAND SPATIO-TEMPORAL ENERGIES
ARS-P6.17—AUTOMATIC EXTRACTION OF SEMANTIC FEATURES FOR REAL-TIME ACTION RECOGNITION USING DEPTH ARCHITECTURE NETWORKS
ARS-P6.18—BAGS-OF-DAGLETS FOR ACTION RECOGNITION
ARS-P6.19—TREND-SENSITIVE HOUGH FORESTS FOR ACTION DETECTION
ARS-P6.20—HISTOGRAM OF DMHI AND LBP IMAGES TO REPRESENT HUMAN ACTIONS
ARS-P6.21—2D ARTICULATED HUMAN POSE TRACKING: A HYBRID APPROACH
ARS-P6.22—ACTION RECOGNITION IN VIDEOS USING FREQUENCY ANALYSIS OF CRITICAL POINT TRAJECTORIES
ARS-P6.23—LEARNING DISCRIMINATE FEATURES AND METRICS FOR MEASURING ACTION SIMILARITY
ARS-P6.24—MULTI-CHANNEL CORRELATION FILTERS FOR HUMAN ACTION RECOGNITION
ARS-P6.25—DISCOVERING DISTINCTIVE ACTION PARTS FOR ACTION RECOGNITION
ARS-P6.26—LOW-RANK BASED COMPACT REPRESENTATION OF MOTION CAPTURE DATA
ARS-P7: Object Detection
Tuesday 16:10–18:10; Poster Session; Poster Area C
ARS-P7.1—AN EFFICIENT NAIVE BAYES APPROACH TO CATEGORY-LEVEL OBJECT DETECTION
ARS-P7.2—OPTICAL FLOW BASED DYNAMIC CURVED VIDEO TEXT DETECTION
ARS-P7.3—AUTONOMOUS MULTI-SCALE OBJECT DETECTION WITH HOUGH FORESTS
ARS-P7.4—OBJECT RECONSTRUCTION IN AN IMAGE BASED ON BELIEF FUNCTION REPRESENTATION
ARS-P7.5—HISTOGRAMS OF ORIENTED GRADIENTS FOR FAST ON-BOARD VEHICLE VERIFICATION
ARS-P7.6—SHELF DETECTION VIA VANISHING POINT AND RADIAL PROJECTION
ARS-P7.7—OBJECT CATEGORY DETECTION BY INCORPORATING MID-LEVEL GROUPING CUES
ARS-P7.8—A COMPUTER VISION APPROACH FOR DETECTION AND QUANTIFICATION OF FEED PARTICLES IN MARINE FISH FARMS
ARS-P7.9—CIRCULAR SPOT DETECTION AND SEGMENTATION WITH ROTATING LINE LOCAL BINARY ANALYSIS
ARS-P7.10—WEAKLY SUPERVISED OBJECT LOCALIZATION VIA MAXIMAL ENTROPY RANDOM WALK
ARS-P7.11—USING LARGE COLOR LBP IN GENERALIZED HOUGH TRANSFORM
ARS-P7.12—ROBUST SCENE TEXT DETECTION USING INTEGRATED FEATURE DISCRIMINATION
ARS-P7.13—FACADE REPETITION EXTRACTION USING BLOCK MATRIX BASED MODEL
ARS-P7.14—HOUGH-BASED OBJECT DETECTION WITH GROUPED FEATURES
ARS-P7.15—AUTOMATED CRATER DETECTION AND COUNTING USING THE HOUGH TRANSFORM
ARS-P7.16—MIRROR REFLECTION INVARIANT HOG DESCRIPTORS FOR OBJECT DETECTION
ARS-P7.17—VESSEL EXTRACTION USING ANISOTROPIC MINIMAL PATHS AND PATH SCORE
ARS-P7.18—MULTI-SCALE CAR DETECTION AND LOCALIZATION USING CONTOUR FRAGMENTS
ARS-P7.19—IMAGE PATCH ANALYSIS AND CLUSTERING OF SUNSPOTS: A DIMENSIONALITY REDUCTION APPROACH
ARS-P7.20—K-SVD DICTIONARY LEARNING USING A FAST OMP WITH APPLICATIONS
ARS-P7.21—WIDE-BASELINE IMAGE CHANGE DETECTION
ARS-P7.22—OBSTACLE DETECTION BY MEANS OF STEREO FEATURE MATCHING
ARS-P7.23—PLANETARY ROVER LOCALIZATION WITHIN ORBITAL MAPS
ARS-P7.24—MOVING CAST SHADOW DETECTION USING ONLINE SUB-SCENE SHADOW MODELING AND OBJECT INNER-EDGES ANALYSIS
TEC-P3: Formation and Reconstruction
Tuesday 16:10–18:10; Poster Session; Poster Area D
TEC-P3.1—NUMERICAL STUDY OF AN OPTIMIZATION PROBLEM FOR MOSAIC ACTIVE IMAGING
TEC-P3.2—GLOBAL SCHEME FOR ITERATIVE MOJETTE RECONSTRUCTIONS
TEC-P3.3—TOPOLOGICAL GRADIENT FOR A FOURTH ORDER PDE AND APPLICATION TO THE DETECTION OF FINE STRUCTURES IN 2D AND 3D IMAGES
TEC-P3.4—A GRADIENT-LIKE VARIATIONAL BAYESIAN APPROACH: APPLICATION TO MICROWAVE IMAGING FOR BREAST TUMOR DETECTION
TEC-P3.5—A NONCONVEX REGULARIZED APPROACH FOR PHASE RETRIEVAL
TEC-P3.6—PERFORMANCE COMPARISON OF ITERATIVE REWEIGHTING METHODS FOR TOTAL VARIATION REGULARIZATION
TEC-P3.7—TOMOGRAPHIC RECONSTRUCTION OF FLOWING GASES USING SPARSE TRAINING
TEC-P3.8—MOTION-BASED PROJECTION GENERATION FOR 4D-CT RECONSTRUCTION
TEC-P3.9—ANGULAR DIFFERENCE MEASURE BETWEEN TOMOGRAPHIC PROJECTIONS TAKEN AT UNKNOWN DIRECTIONS IN 2D
TEC-P3.10—BINARY TOMOGRAPHY RECONSTRUCTIONS OF BONE MICROSTRUCTURE FROM FEW PROJECTIONS WITH STOCHASTIC LEVEL-SET METHODS
TEC-P3.11—ULTRASOUND IMAGE RECONSTRUCTION USING THE FINITE-RATE-OF-INNOVATION PRINCIPLE
TEC-P3.12—COMBINING INTERIOR TOMOGRAPHY RECONSTRUCTION AND SPATIAL REGULARIZATION
TEC-P3.13—FAST ITERATIVELY REWEIGHTED LEAST SQUARES FOR LP REGULARIZED IMAGE DECONVOLUTION AND RECONSTRUCTION
TEC-P3.14—HIGH BIT-PRECISION IMAGE ACQUISITION AND RECONSTRUCTION BY PLANNED SENSOR DISTORTION
TEC-P3.15—HIGH-PERFORMANCE 3D DECONVOLUTION OF FLUORESCENCE MICROGRAPHS
TEC-P3.16—A FAST METHOD FOR RECONSTRUCTION OF TOTAL-VARIATION MR IMAGES WITH A PERIODIC BOUNDARY CONDITION
TEC-P3.17—ROBUST PHASE UNWRAPPING BY CONVEX OPTIMIZATION
TEC-P3.18—DICTIONARY LEARNING FOR SPARSITY-DRIVEN SAR IMAGE RECONSTRUCTION
TEC-P3.19—QUANTIFICATION OF COMPUTED TOMOGRAPHY PORK CARCASS IMAGES
TEC-P3.20—SENSOR NOISE MEASUREMENT IN THE PRESENCE OF A FLICKERING ILLUMINATION
TEC-P3.21—THE MAXIMUM SPACING NOISE ESTIMATION IN SINGLE-COIL BACKGROUND MRI DATA
TEC-P4: Interpolation and Mosaicing
Tuesday 16:10–18:10; Poster Session; Poster Area E
TEC-P4.1—ALIGNMENT-FREE EXPOSURE FUSION OF IMAGE PAIRS
TEC-P4.2—COLOR FRINGE CORRECTION BASED ON IMAGE FUSION
TEC-P4.3—PHOTOMETRIC ALIGNMENT FOR SURROUND VIEW CAMERA SYSTEM
TEC-P4.4—A MULTILAYER NEURAL NETWORK FOR IMAGE DEMOSAICKING
TEC-P4.5—EXAMPLE BASED DEMOSAICING
TEC-P4.6—IMAGE DEMOSAICING BY USING ITERATIVE RESIDUAL INTERPOLATION
TEC-P4.7—EXPLOITATION OF INTER-COLOR CORRELATION FOR COLOR IMAGE DEMOSAICKING
TEC-P4.8—GRADIENT GUIDED IMAGE INTERPOLATION
TEC-P4.9—MPCA: EM-BASED PCA FOR MIXED-SIZE IMAGE DATASETS
TEC-P4.10—MODIFIED SOFT-DECISION ADAPTIVE INTERPOLATION BY AN EVOLUTIONARY GAME
TEC-P4.11—2D SEMI-SUPERVISED CCA-BASED INPAINTING INCLUDING NEW PRIORITY ESTIMATION
TEC-P4.12—GENERAL SCALE INTERPOLATION BASED ON FINE-GRAINED ISOPHOTE MODEL WITH CONSISTENCY CONSTRAINT
TEC-P4.13—IMAGE INTERPOLATION FROM MANHATTAN CUTSET SAMPLES VIA ORTHOGONAL GRADIENT METHOD
TEC-P4.14—RECONSTRUCTION OF TEXTURELESS REGIONS USING STRUCTURE FROM MOTION AND IMAGE-BASED INTERPOLATION
TEC-P4.15—DIRECTIONAL INTRA FRAME INTERPOLATION FOR HEVC COMPRESSED VIDEO
TEC-P4.16—LUMINANCE DRIVEN SPARSE REPRESENTATION BASED DEMOSAICKING
TEC-P4.17—DISPARITY-GUIDED DEMOSAICKING OF LIGHT FIELD IMAGES
Wednesday, October 29
ARS-L6: Image Retrieval
Wednesday 10:30–12:30; Oral Session; Room: Leonard de Vinci
10:30 ARS-L6.1—DIMENSIONALITY REDUCTION OF VISUAL FEATURES USING SPARSE PROJECTORS FOR CONTENT-BASED IMAGE RETRIEVAL
10:50 ARS-L6.2—DIVERSITY-DRIVEN LEARNING FOR MULTIMODAL IMAGE RETRIEVAL WITH RELEVANCE FEEDBACK
11:10 ARS-L6.3—SHAPE-BASED OBJECT RETRIEVAL BY CONTOUR SEGMENT MATCHING
11:30 ARS-L6.4—CASCADED SPARSE COLOR-LOCALIZED MATCHING FOR LOGO RETRIEVAL
11:50 ARS-L6.5—EFFICIENT BINARY CODES FOR EXTREMELY HIGH-DIMENSIONAL DATA
12:10 ARS-L6.6—COMPONENT HASHING OF VARIABLE-LENGTH BINARY AGGREGATED DESCRIPTORS FOR FAST IMAGE SEARCH
ELI-L2: 3D Modeling and Synthesis
Wednesday 10:30–12:30; Oral Session; Room: Ampere 1+3
10:30 ELI-L2.1—MULTIDIMENSIONAL STEERABLE FILTERS AND 3D FLOW ESTIMATION
10:50 ELI-L2.2—DEPTH EXTRACTION FROM A SINGLE IMAGE BY SAMPLING BASED ON DISTANCE METRIC LEARNING
11:10 ELI-L2.3—LEARNING 3D STRUCTURE FROM 2D IMAGES USING LBP FEATURES
11:30 ELI-L2.4—STREET VIEW CROSS-SOURCED POINT CLOUD MATCHING AND REGISTRATION
11:50 ELI-L2.5—SEAMLESS TEXTURE STITCHING ON A 3D MESH BY POISSON BLENDING IN PATCHES
12:10 ELI-L2.6—3D VISUAL PRONUNCIATION OF MANDARIN CHINESE FOR LANGUAGE LEARNING
GRA-L1: Graph-Based Image Processing
Wednesday 10:30–12:30; Oral Session; Room: Ampere 5+6
10:30 GRA-L1.1—GRAPH SIGNAL DECOMPOSITION FOR MULTI-SCALE DETAIL MANIPULATION
10:50 GRA-L1.2—TRILATERAL FILTER ON GRAPH SPECTRAL DOMAIN
11:10 GRA-L1.3—A COMPLEX NETWORK BASED FEATURE EXTRACTION FOR IMAGE RETRIEVAL
11:30 GRA-L1.4—GRAPH-BASED JOINT DENOISING AND SUPER-RESOLUTION OF GENERALIZED PIECEWISE SMOOTH IMAGES
11:50 GRA-L1.5—GRAPH-BASED APPROACH FOR MOTION CAPTURE DATA REPRESENTATION AND ANALYSIS
12:10 GRA-L1.6—POINT CLOUD ATTRIBUTE COMPRESSION WITH GRAPH TRANSFORM
TEC-L4: Super-Resolution
Wednesday 10:30–12:30; Oral Session; Room: Dickens 3+4
10:30 TEC-L4.1—SINGLE IMAGE SUPER-RESOLUTION VIA SPARSE KPCA AND REGRESSION
10:50 TEC-L4.2—ROBUST SINGLE-IMAGE SUPER-RESOLUTION USING CROSS-SCALE SELF-SIMILARITY
11:10 TEC-L4.3—EXAMPLE-BASED SUPER-RESOLUTION USING SELF-PATCHES AND APPROXIMATED CONSTRAINED LEAST SQUARES FILTER
11:30 TEC-L4.4—SUPER-RESOLUTION FROM A LOW- AND PARTIAL HIGH- RESOLUTION IMAGE PAIR
11:50 TEC-L4.5—JOINT VIDEO FUSION AND SUPER RESOLUTION BASED ON MARKOV RANDOM FIELDS
12:10 TEC-L4.6—SUPER-RESOLUTION HYPERSPECTRAL IMAGING WITH UNKONWN BLURRING BY LOW-RANK AND GROUP-SPARSE MODELING
SS12: Electron-Microscopy Image Processing Problems and Applications in Biology: From Structure to Dynamics
Wednesday 10:30–12:30; Oral Session; Room: Ampere 7+8
Session Chairs: Slavica Jonic,
IMPMC, Sorbonne Universités, CNRS-UPMC-MNHN-IRD; C. Sanchez-Sorzano,
Centro Nacional Biotecnología
10:30 SS12.1—NEW ADVANCES IN IMAGING POLYMERS AT NEAR-ATOMIC RESOLUTION
10:50 SS12.2—ELASTIC IMAGE REGISTRATION TO FULLY EXPLORE MACROMOLECULAR DYNAMICS BY ELECTRON MICROSCOPY
11:10 SS12.3—CONDITIONAL RANDOM FIELDS FOR TUBULIN-MICROTUBULE SEGMENTATION IN CRYO-ELECTRON TOMOGRAPHY
11:30 SS12.4—AUTOMATED DETECTION OF POLYSOMES IN CRYOELECTRON TOMOGRAPHY
11:50 SS12.5—AB INITIO CRYO-EM STRUCTURE DETERMINATION AS A VALIDATION PROBLEM
12:10 SS12.6—AN IMAGE PROCESSING APPROACH TO THE SIMULATION OF ELECTRON MICROSCOPY VOLUMES OF ATOMIC STRUCTURES
SS17: Efficient Design of HEVC Video-Codec Implementations
Wednesday 10:30–12:30; Oral Session; Room: Dickens 1+2
Session Chair: Vivienne Sze,
Massachusetts Institute of Technology
10:30 SS17.1—ENERGY AND AREA-EFFICIENT HARDWARE IMPLEMENTATION OF HEVC INVERSE TRANSFORM AND DEQUANTIZATION
10:50 SS17.2—HIGH-THROUGHPUT AND LOW-COST HARDWARE-ORIENTED INTEGER TRANSFORMS FOR HEVC
11:10 SS17.3—A 2014 MBIN/S DEEPLY PIPELINED CABAC DECODER FOR HEVC
11:30 SS17.4—EXPLORING MPEG HEVC DECODER PARALLELISM FOR THE EFFICIENT PORTING ONTO MANY-CORE PLATFORMS
11:50 SS17.5—REDUCING POWER CONSUMPTION OF HEVC CODEC WITH LOSSLESS REFERENCE FRAME RECOMPRESSION
12:10 SS17.6—REAL TIME SHVC DECODER: IMPLEMENTATION AND COMPLEXITY ANALYSIS
ARS-P8: Video Surveillance
Wednesday 10:30–12:30; Poster Session; Poster Area B
ARS-P8.1—A SIMILARITY MEASURE FOR ANALYZING HUMAN ACTIVITIES USING HUMAN-OBJECT INTERACTION CONTEXT
ARS-P8.2—A CLUSTER SPECIFIC LATENT DIRICHLET ALLOCATION MODEL FOR TRAJECTORY CLUSTERING IN CROWDED VIDEOS
ARS-P8.3—WEAKLY SUPERVISED CROSS-VIEW ACTION RECOGNITION VIA SEQUENTIAL MOTION ACCUMULATION
ARS-P8.4—GAUSSIAN RINGLET INTENSITY DISTRIBUTION (GRID) FEATURES FOR ROTATION-INVARIANT OBJECT DETECTION IN WIDE AREA MOTION IMAGERY
ARS-P8.5—MULTI-FEATURE STATIONARY FOREGROUND DETECTION FOR CROWDED VIDEO-SURVEILLANCE
ARS-P8.6—SIMULTANEOUS SPARSITY MODEL FOR MULTI-PERSPECTIVE VIDEO ANOMALY DETECTION
ARS-P8.7—AN ONLINE LEARNED HOUGH FOREST MODEL FOR MULTI-TARGET TRACKING
ARS-P8.8—PEDESTRIAN DETECTION IN HIGHLY CROWDED SCENES USING “ONLINE” DICTIONARY LEARNING FOR OCCLUSION HANDLING
ARS-P8.9—A SCENE-SPECIFIC DEFORMABLE PART-BASED MODEL FOR OBJECT DETECTION
ARS-P8.10—METRIC LEARNING WITH TRACE-NORM REGULARIZATION FOR PERSON RE-IDENTIFICATION
ARS-P8.11—WEAKLY SUPERVISED PEDESTRIAN DETECTOR TRAINING BY UNSUPERVISED PRIOR LEARNING AND CUE FUSION IN VIDEOS
ARS-P8.12—A FRAMEWORK FOR UNIQUE PEOPLE COUNT FROM MONOCULAR VIDEOS
ARS-P8.13—A NOVEL SOLUTION FOR MULTI-CAMERA OBJECT TRACKING
ARS-P8.14—SWARM-BASED MOTION FEATURES FOR ANOMALY DETECTION IN CROWDS
ARS-P8.15—SUPER-PIXEL BASED CROWD FLOW SEGMENTATION IN H.264 COMPRESSED VIDEOS
ARS-P8.16—MULTI-SCALE ANALYSIS OF CONTEXTUAL INFORMATION WITHIN SPATIO-TEMPORAL VIDEO VOLUMES FOR ANOMALY DETECTION
ARS-P8.17—BACKGROUND EXTRACTION FROM VIDEO SEQUENCES VIA MOTION-ASSISTED MATRIX COMPLETION
ARS-P8.18—COMPLEX EVENT RECOGNITION BY LATENT TEMPORAL MODELS OF CONCEPTS
ARS-P8.19—PEDESTRIAN COUNTING BASED ON SPATIAL AND TEMPORAL ANALYSIS
ARS-P8.20—STATIC REGION CLASSIFICATION USING HIERARCHICAL FINITE STATE MACHINE
ARS-P8.21—PERIMETER-INTRUSION EVENT CLASSIFICATION FOR ON-LINE DETECTION USING MULTIPLE INSTANCE LEARNING SOLVING TEMPORAL AMBIGUITIES
ARS-P8.22—“CLUSTERING BY SALIENCY”—UNSUPERVISED DISCOVERY OF CROWD ACTIVITIES
ARS-P8.23—EXPLOITING LOW-RANK STRUCTURES FROM CROSS-CAMERA IMAGES FOR ROBUST PERSON RE-IDENTIFICATION
ARS-P8.24—FIRST-PERSON MULTIPLE OBJECT TRACKING IN COMPLEX TRAFFIC SCENES
ARS-P8.25—PERSON RE-IDENTIFICATION BY FREE ENERGY SCORE SPACE ENCODING
ARS-P8.26—A PERSON RE-IDENTIFICATION ALGORITHM BASED ON COLOR TOPOLOGY
ARS-P8.27—FOUNDATIONAL METADATA FOR IMAGE BASED COGNITION
ARS-P8.28—PEDESTRIAN DETECTION FROM SALIENT REGIONS
ARS-P8.29—PEDESTRIAN DETECTION USING MIXED PARTIAL DERIVATIVE BASED HISTOGRAM OF ORIENTED GRADIENTS
ARS-P8.30—MOVING TARGETS DETECTION FROM UAV BASED ON A ROBUST REAL-TIME IMAGE REGISTRATION ALGORITHM
COM-P1: Multimedia Communication
Wednesday 10:30–12:30; Poster Session; Poster Area C
COM-P1.1—PERCEPTUAL PRE-PROCESSING FILTER FOR ADAPTIVE VIDEO ON DEMAND CONTENT DELIVERY
COM-P1.2—AN ERROR-BASED RECURSIVE FILLING ORDERING FOR IMAGE ERROR CONCEALMENT
COM-P1.3—ROBUST AND EFFICIENT SAR IMAGE CODING TRANSMISSION
COM-P1.4—JOINT SOURCE AND CHANNEL CODING OF VIEW AND RATE SCALABLE MULTI-VIEW VIDEO
COM-P1.5—ADAPTIVE 3D MULTI-VIEW VIDEO STREAMING OVER P2P NETWORKS
COM-P1.6—ADAPTIVE VIDEO TRANSMISSION WITH SUBJECTIVE QUALITY CONSTRAINTS
COM-P1.7—PROXIMATE CONTROL STREAM ASSISTED VIDEO TRANSCODING FOR HETEROGENEOUS CONTENT DELIVERY NETWORK
COM-P1.8—CAMERA VIEWPOINT CHANGE DETECTION FOR INTERACTION ANALYSIS IN TV SHOWS
COM-P1.9—ENHANCED SPATIO-TEMPORAL VIDEO COPY DETECTION BY COMBINING TRAJECTORY AND SPATIAL CONSISTENCY
COM-P1.10—SHOULD WE DISCARD SPARSE OR INCOMPLETE VIDEOS?
COM-P1.11—FAST QUADTREE LEVEL DECISION ALGORITHM FOR H.264/HEVC TRANSCODER
COM-P1.12—HIGH QUALITY IMAGE RECONSTRUCTION VIA NON-LOCAL COLLABORATIVE ESTIMATION FOR WIRELESS IMAGE/VIDEO SOFTCAST
COM-P1.13—EFFICIENT TRANSCODING FOR SPATIALLY MISALIGNED COMPOSITIONS FOR HEVC
COM-P1.14—A FAST HEVC TRANSCODER BASED ON CONTENT MODELING AND EARLY TERMINATION
COM-P1.15—FAST MOTION ESTIMATION FOR CLOSED-LOOP HEVC TRANSRATING
COM-P1.16—COMBINING COMPUTER VISION AND VIDEO PROCESSING TO ACHIEVE IMMERSIVE MOBILE VIDEOCONFERENCING
COM-P1.17—JUMPING PHOTOS
COM-P1.18—A STEREO CLIENT USING OPEN SVC DECODER EXTENSIONS: QOE PERFORMANCE EVALUATION
COM-P1.19—A 3D MAP AUGMENTED PHOTO GALLERY APPLICATION ON MOBILE DEVICE
COM-P1.20—SELECTIVE MOTION VECTOR REDUNDANCIES FOR IMPROVED ERROR RESILIENCE IN HEVC
ELI-P3: Image Scanning and Printing
Wednesday 10:30–12:30; Poster Session; Poster Area D
ELI-P3.1—SHARPNESS-AWARE DOCUMENT IMAGE MOSAICING USING GRAPHCUTS
ELI-P3.2—COLOR FEATURES FOR DATING HISTORICAL COLOR IMAGES
ELI-P3.3—USING PYRAMID OF HISTOGRAM OF ORIENTED GRADIENTS ON NATURAL SCENE TEXT RECOGNITION
ELI-P3.4—A NOVEL APPROACH FOR COLOR BARCODE DECODING USING SMART PHONES
ELI-P3.5—HANDWRITTEN WORD SPOTTING BASED ON A HYBRID OPTIMAL DISTANCE
ELI-P3.6—CONTEXT-DEPENDENT BLSTM MODELS. APPLICATION TO OFFLINE HANDWRITING RECOGNITION
ELI-P3.7—BAG OF FEATURES APPROACH FOR OFFLINE TEXT-INDEPENDENT CHINESE WRITER IDENTIFICATION
ELI-P3.8—3D RECTIFICATION OF DISTORTED DOCUMENT IMAGE BASED ON TILED RECTANGLE FRAGMENTS
ELI-P3.9—IMAGE CHARACTER RECOGNITION USING DEEP CONVOLUTIONAL NEURAL NETWORK LEARNED FROM DIFFERENT LANGUAGES
ELI-P3.10—THE ZONEMAP METRIC FOR PAGE SEGMENTATION AND AREA CLASSIFICATION IN SCANNED DOCUMENTS
ELI-P3.11—A MORPHOLOGICAL METHOD FOR MUSIC SCORE STAFF REMOVAL
ELI-P3.12—LEARNING TO REMOVE STAFF LINES FROM MUSIC SCORE IMAGES
ELI-P3.13—BINARY TEXT IMAGE FILE PREPROCESSING TO ACCOUNT FOR PRINTER DOT GAIN
ELI-P3.14—A DEEP LEARNING APPROACH TO DOCUMENT IMAGE QUALITY ASSESSMENT
ELI-P3.15—SEMANTICALLY-BASED 2.5D TEXTURE PRINTING
ELI-P3.16—ESTIMATING EMBEDDED DATA FROM CLUSTERED HALFTONE DOTS VIA LEARNED DICTIONARY
ELI-P3.17—AN IMPROVED ERROR DIFFUSION ALGORITHM BASED ON VISUAL DIFFERENCE
ELI-P3.18—A PRECISE SKEW ESTIMATION ALGORITHM FOR DOCUMENT IMAGES USING KNN CLUSTERING AND FOURIER TRANSFORM
TEC-P5: Classification of Medical Images
Wednesday 10:30–12:30; Poster Session; Poster Area A
TEC-P5.1—A COLOR TEXTURE ANALYSIS METHOD BASED ON A GRAVITATIONAL APPROACH FOR CLASSIFICATION OF THE PAP-SMEAR DATABASE
TEC-P5.2—THE MS KINECT IMAGE AND DEPTH SENSORS USE FOR GAIT FEATURES DETECTION
TEC-P5.3—A SEMANTIC FRAMEWORK FOR THE RETRIEVAL OF SIMILAR RADIOLOGICAL IMAGES BASED ON MEDICAL ANNOTATIONS
TEC-P5.4—UPPER LIMB MOVEMENT ANALYSIS VIA MARKER TRACKING WITH A SINGLE-CAMERA SYSTEM
TEC-P5.5—RETRIEVAL OF PATHOLOGY IMAGE FOR BREAST CANCER USING PLSA MODEL BASED ON TEXTURE AND PATHOLOGICAL FEATURES
TEC-P5.6—PERFORMANCE ANALYSIS OF UNCONVENTIONAL DICTIONARY ON RETINAL IMAGES
TEC-P5.7—SHAPE AND SIZE ADAPTED LOCAL FRACTAL DIMENSION FOR THE CLASSIFICATION OF POLYPS IN HD COLONOSCOPY
TEC-P5.8—A TEXTURE-BASED PROBABILITY MAPPING FOR LOCALISATION OF CLINICALLY IMPORTANT CARDIAC SEGMENTS IN THE MYOCARDIUM IN CARDIAC MAGNETIC RESONANCE IMAGES FROM MYOCARDIAL INFARCTION PATIENTS
TEC-P5.9—CLASSIFICATION OF CARDIAC MAGNETIC RESONANCE IMAGE TYPE AND ORIENTATION
TEC-P5.10—A STATISTICAL FRAMEWORK FOR THE CLASSIFICATION OF INFANT DT IMAGES
TEC-P5.11—ULTRASOUND TISSUE CHARACTERIZATION BY GENERALIZED GAMMA MRF MODEL
TEC-P5.12—AUTOMATIC LESION DETECTION IN WIRELESS CAPSULE ENDOSCOPY – A SIMPLE SOLUTION FOR A COMPLEX PROBLEM
TEC-P5.13—COMPUTER-AIDED DIAGNOSTIC FOR PROSTATE CANCER DETECTION AND CHARACTERIZATION COMBINING LEARNED DICTIONARIES AND SUPERVISED CLASSIFICATION
TEC-P5.14—OPTIMAL SET OF FEATURES FOR ACCURATE SKIN CANCER DIAGNOSIS
TEC-P5.15—ADABOOST WITH DUMMY-VARIABLE MODELING FOR REDUCTION OF FALSE POSITIVES IN DETECTION OF CLUSTERED MICROCALCIFICATIONS
TEC-P5.16—SVM WITH FEATURE SELECTION AND SMOOTH PREDICTION IN IMAGES: APPLICATION TO CAD OF PROSTATE CANCER
TEC-P5.17—A DEPTH-MAP APPROACH FOR AUTOMATIC MICE BEHAVIOR RECOGNITION
TEC-P5.18—WAVELET-BASED STATISTICAL FEATURES FOR DISTINGUISHING MITOTIC AND NON-MITOTIC CELLS IN BREAST CANCER HISTOPATHOLOGY
TEC-P6: Denoising
Wednesday 10:30–12:30; Poster Session; Poster Area E
TEC-P6.1—BLIND FULL REFERENCE QUALITY ASSESSMENT OF POISSON IMAGE DENOISING
TEC-P6.2—ADAPTIVE REGULARIZATION OF THE NL-MEANS FOR VIDEO DENOISING
TEC-P6.3—MOTION BLUR RESISTANT METHOD FOR TEMPORAL VIDEO DENOISING
TEC-P6.4—IMAGE DENOISING USING CONTEXTUAL MODELING OF CURVELET COEFFICIENTS
TEC-P6.5—STRATEGIC IMAGE DENOISING USING A SUPPORT VECTOR MACHINE WITH SEAM ENERGY AND SALIENCY FEATURES
TEC-P6.6—ANISOTROPIC COLOR IMAGE DENOISING AND SHARPENING
TEC-P6.7—NOISE BIAS COMPENSATION OF TONE MAPPED NOISY IMAGE
TEC-P6.8—NONLOCAL IMAGE DENOISING VIA COLLABORATIVE SPATIAL-DOMAIN LMMSE ESTIMATION
TEC-P6.9—SIGNAL DEPENDENT NOISE REMOVAL FROM A SINGLE IMAGE
TEC-P6.10—DENOISING BASED ON NON LOCAL MEANS FOR ULTRASOUND IMAGES WITH SIMULTANEOUS MULTIPLE NOISE DISTRIBUTIONS
TEC-P6.11—IMAGE NOISE LEVEL ESTIMATION BASED ON A NEW ADAPTIVE SUPERPIXEL CLASSIFICATION
TEC-P6.12—HANDLING NOISE IN IMAGE DECONVOLUTION WITH LOCAL/NON-LOCAL PRIORS
TEC-P6.13—FAST LOG-GABOR-BASED NONLOCAL MEANS IMAGE DENOISING METHODS
TEC-P6.14—THE NOISE CLINIC: A UNIVERSAL BLIND DENOISING ALGORITHM
TEC-P6.15—DENOISING USING PROJECTIONS ONTO THE EPIGRAPH SET OF A CONVEX COST FUNCTION
TEC-P6.16—CAN A SINGLE IMAGE DENOISING NEURAL NETWORK HANDLE ALL LEVELS OF GAUSSIAN NOISE?
TEC-P6.17—A NONLOCAL POISSON DENOISING ALGORITHM BASED ON STOCHASTIC DISTANCES
TEC-P6.18—REGULARISED, SEMI-LOCAL HURST ESTIMATION VIA GENERALISED LASSO AND DUAL-TREE COMPLEX WAVELETS
TEC-P6.19—FRACTIONAL CYCLE SPINNING VIA MODULATED LAPPED TRANSFORM FOR OVERCOMPLETE IMAGE REPRESENTATION
ST1.1—A SMARTPHONE APPLICATION FOR REMOVING HANDSHAKE BLUR AND COMPENSATING ROLLING SHUTTER
ST1.2—A PORTABLE REAL-TIME HIGH-DYNAMIC RANGE VIDEO SYSTEM
ST1.3—REVERIE: NATURAL HUMAN INTERACTION IN VIRTUAL IMMERSIVE ENVIRONMENTS
ST1.4—DUAL-VIEW MEDICAL IMAGE VISUALIZATION BASED ON SPATIAL-TEMPORAL PSYCHOVISUAL MODULATION
ST1.5—HARMONY-GUIDED IMAGE EDITING
ST1.6—SNOW PHENOMENA MODELING THROUGH ONLINE PUBLIC MEDIA
ST1.7—INFORMATION OPTIMAL SCALABLE COMPRESSIVE IMAGER DEMONSTRATOR
ST1.8—INTERACTIVE DEMONSTRATIONS OF THE LOCALLY ADAPTIVE FUSION FOR COMBINING QUALITY MEASURES
ST1.9—QUASAR – A NEW HETEROGENEOUS PROGRAMMING FRAMEWORK FOR IMAGE AND VIDEO PROCESSING ALGORITHMS ON CPU AND GPU
ST1.10—UNIFIED REAL TIME SOFTWARE DECODER FOR HEVC EXTENSIONS
ST1.11—OPEN SOURCE HEVC ANALYZER FOR RAPID PROTOTYPING (HARP)
ST2.1—LIGHTWEIGHT FORENSIC VIDEO WATERMARKING TO ENABLE PREMIUM CONTENT CONSUMPTION ON MOBILE DEVICES
ST2.2—SCALABLE, SELF-ORGANIZING 3D CAMERA NETWORK FOR NON-INTRUSIVE PEOPLE TRACKING AND COUNTING
ST2.3—ENABLING VISUAL ANALYSIS IN WIRELESS SENSOR NETWORKS
ST2.4—DEMONSTRATING THE NEW COMPACT DESCRIPTORS FOR VISUAL SEARCH (CDVS) STANDARD FOR IMAGE RETRIEVAL ON MOBILE DEVICES
ST2.5—A MATLAB IMPLEMENTATION OF A FAST INCREMENTAL PRINCIPAL COMPONENT PURSUIT ALGORITHM FOR VIDEO BACKGROUND MODELING
ST2.6—HUMAN TRACKING & VISUAL SPATIO-TEMPORAL STATISTICAL ANALYSIS
ST2.7—RELIABLE AND CONVENIENT MULTIMODAL BIOMETRIC SYSTEM BASED ON IRIS, FACE & PALM FOR HIGH-THROUGHPUT RECOGNITION
ST2.8—SCRAMBLING-BASED TOOL FOR SECURE PROTECTION OF JPEG IMAGES
ST2.9—LIGHTWEIGHT MOBILE OBJECT RECOGNITION
ST2.10—SENSAREA, A GENERAL PUBLIC VIDEO EDITING APPLICATION
ST2.11—A REAL-TIME CIPHERING TRANSCODER FOR H.264 AND HEVC STREAMS
ARS-L7: Object Recognition
Wednesday 14:00–16:00; Oral Session; Room: Ampere 1+3
14:00 ARS-L7.1—INCREMENTAL TRANSFER LEARNING FOR OBJECT RECOGNITION IN STREAMING VIDEO
14:20 ARS-L7.2—WEIGHTED BAG OF VISUAL WORDS FOR OBJECT RECOGNITION
14:40 ARS-L7.3—UNSUPERVISED DOMAIN ADAPTATION USING MANIFOLD ALIGNMENT FOR OBJECT AND EVENT CATEGORIZATION
15:00 ARS-L7.4—ANALYSIS OF FOOD IMAGES: FEATURES AND CLASSIFICATION
15:20 ARS-L7.5—3D OBJECT RETRIEVAL BY 3D CURVE MATCHING
15:40 ARS-L7.6—SCALABLE LEARNING FOR RESTRICTED BOLTZMANN MACHINES
ELI-L3: Multiview Image Processing
Wednesday 14:00–16:00; Oral Session; Room: Leonard de Vinci
14:00 ELI-L3.1—RECONSTRUCTION OF IMAGES TAKEN BY A PAIR OF NON-REGULAR SAMPLING SENSORS USING CORRELATION BASED MATCHING
14:20 ELI-L3.2—INTER-VIEW CONSISTENT HOLE FILLING IN VIEW EXTRAPOLATION FOR MULTI-VIEW IMAGE GENERATION
14:40 ELI-L3.3—CORRECTING 3D SCENES ESTIMATED FROM SETS OF MULTI-VIEW IMAGES USING SHAPE-FROM-CONTOURS
15:00 ELI-L3.4—TEMPORAL DEPTH VIDEO ENHANCEMENT BASED ON INTRINSIC STATIC STRUCTURE
15:20 ELI-L3.5—WARPING-BASED VIDEO RETARGETING FOR STEREOSCOPIC VIDEO
15:40 ELI-L3.6—REGION-BASED DEPTH-PRESERVING STEREOSCOPIC IMAGE RETARGETING
SMR-L2: Subspace Representations
Wednesday 14:00–16:00; Oral Session; Room: Dickens 3+4
14:00 SMR-L2.1—KERNEL SPARSE SUBSPACE CLUSTERING
14:20 SMR-L2.2—SEMI-SUPERVISED SUBSPACE SEGMENTATION
14:40 SMR-L2.3—ENDOGENOUS CONVOLUTIONAL SPARSE REPRESENTATIONS FOR TRANSLATION INVARIANT IMAGE SUBSPACE MODELS
15:00 SMR-L2.4—MULTIDATASET INDEPENDENT SUBSPACE ANALYSIS EXTENDS INDEPENDENT VECTOR ANALYSIS
15:20 SMR-L2.5—MINIMIZING DATASET BIAS: DISCRIMINATIVE MULTI-TASK SPARSE CODING THROUGH SHARED SUBSPACE LEARNING FOR IMAGE CLASSIFICATION
15:40 SMR-L2.6—ITERATIVE KEYFRAME SELECTION BY ORTHOGONAL SUBSPACE PROJECTION
TEC-L5: Classification of Medical Images
Wednesday 14:00–16:00; Oral Session; Room: Ampere 5+6
14:00 TEC-L5.1—DEGRADATION ADAPTIVE TEXTURE CLASSIFICATION
14:20 TEC-L5.2—IMAGE CLASSIFICATION OF BOWEL ABNORMALITIES AND ISCHEMIA
14:40 TEC-L5.3—HELICOBACTER PYLORI INFECTION DETECTION FROM MULTIPLE X-RAY IMAGES BASED ON DECISION LEVEL FUSION
15:00 TEC-L5.4—BRAIN TUMOR CLASSIFICATION USING SPARSE CODING AND DICTIONARY LEARNING
15:20 TEC-L5.5—A BAYESIAN MODEL FOR BRAIN TUMOR CLASSIFICATION USING CLINICAL-BASED FEATURES
15:40 TEC-L5.6—DEEP LEARNING FOR BRAIN DECODING
SS4: Photon-Limited Image Reconstruction
Wednesday 14:00–16:00; Oral Session; Room: Dickens 1+2
Session Chairs: Charles-Alban Deledalle,
Université de Bordeaux; Joseph Salmon,
CNRS-Télécom ParisTech
14:00 SS4.1—ITERATIVE POISSON-GAUSSIAN NOISE PARAMETRIC ESTIMATION FOR BLIND IMAGE DENOISING
14:20 SS4.2—GENERALIZED SUBSPACE PURSUIT AND AN APPLICATION TO SPARSE POISSON DENOISING
14:40 SS4.3—TO E OR NOT TO E IN POISSON IMAGE RECONSTRUCTION
15:00 SS4.4—APPROXIMATE BAYESIAN COMPUTATION, STOCHASTIC ALGORITHMS AND NON-LOCAL MEANS FOR COMPLEX NOISE MODELS
15:20 SS4.5—SPARSITY BASED POISSON INPAINTING
15:40 SS4.6—SPARSE RECONSTRUCTION FROM MULTIPLE-ANGLE TOTAL INTERNAL REFLECTION FLUORESCENCE MICROSCOPY
SS6: Compact Feature-Based Representation of Visual Content
Wednesday 14:00–16:00; Oral Session; Room: Ampere 7+8
Session Chair: Giuseppe Valenzise,
Institut Mines-Télécom, Télécom ParisTech, CNRS LTCI
14:00 SS6.1—VIDEO QUERYING VIA COMPACT DESCRIPTORS OF VISUALLY SALIENT OBJECTS
14:20 SS6.2—CODING BINARY LOCAL FEATURES EXTRACTED FROM VIDEO SEQUENCES
14:40 SS6.3—ROBUST AND SCALABLE AGGREGATION OF LOCAL FEATURES FOR ULTRA LARGE-SCALE RETRIEVAL
15:00 SS6.4—CAMERA-BASED INDOOR POSITIONING USING SCALABLE STREAMING OF COMPRESSED BINARY IMAGE SIGNATURES
15:20 SS6.5—LOCAL VISUAL FEATURES EXTRACTION FROM TEXTURE+DEPTH CONTENT BASED ON DEPTH IMAGE ANALYSIS
15:40 SS6.6—LOCAL DESCRIPTIONS FOR HUMAN ACTION RECOGNITION FROM 3D RECONSTRUCTION DATA
ARS-P10: Foreground/Background Segregation
Wednesday 14:00–16:00; Poster Session; Poster Area D
ARS-P10.1—OBJECTNESS TO IMPROVE THE BAG OF VISUAL WORDS MODEL
ARS-P10.2—CONFIDENCE-AWARE GUIDED IMAGE FILTER
ARS-P10.3—ROBOT USERS FOR THE EVALUATION OF BOUNDARY-TRACKING APPROACHES IN INTERACTIVE IMAGE SEGMENTATION
ARS-P10.4—ONLINE FEATURE SUBSET SELECTION FOR OBJECT TRACKING
ARS-P10.5—DETECTING DEFECTS IN REPEATEDLY PATTERNED IMAGE WITH SPATIALLY DIFFERENT LEVEL OF NOISE
ARS-P10.6—SALIENCY DETECTION VIA FOREGROUND RENDERING AND BACKGROUND EXCLUSION
ARS-P10.7—A MULTISCALE SPATIO-TEMPORAL BACKGROUND MODEL FOR MOTION DETECTION
ARS-P10.8—IMAGE SEGMENTATION USING CONSENSUS FROM HIERARCHICAL SEGMENTATION ENSEMBLES
ARS-P10.9—AUTOMATIC IMAGE CO-SEGMENTATION USING GEOMETRIC MEAN SALIENCY
ARS-P10.10—PID-BASED REGULATION OF BACKGROUND DYNAMICS FOR FOREGROUND SEGMENTATION
ARS-P10.11—FIGURE/GROUND VIDEO SEGMENTATION USING GREEDY TRANSDUCTIVE COSEGMENTATION
ARS-P10.12—SALIENT OBJECT DETECTION USING OCTONION WITH BAYESIAN INFERENCE
ARS-P10.13—SALIENT-REGION DETECTION IN A MULTI-LEVEL FRAMEWORK OF IMAGE SMOOTHING WITH OVER-SEGMENTATION
ARS-P10.14—SALIENCY DETECTION USING REGRESSION TREES ON HIERARCHICAL IMAGE SEGMENTS
ARS-P10.15—ROBUST 3D SFS RECONSTRUCTION BASED ON RELIABILITY MAPS
ARS-P10.16—FOREGROUND OBJECT SEGMENTATION FOR MOVING CAMERA SEQUENCES BASED ON FOREGROUND-BACKGROUND PROBABILISTIC MODELS AND PRIOR PROBABILITY MAPS
ARS-P10.17—NATURAL IMAGE MATTING VIA ADAPTIVE LOCAL AND NONLOCAL SAMPLE CLUSTERING
ARS-P10.18—MULTIVIEW FOREGROUND SEGMENTATION USING 3D PROBABILISTIC MODEL
ARS-P10.19—AN ADAPTIVE TRANSFER SCHEME BASED ON SPARSE REPRESENTATION FOR FIGURE-GROUND SEGMENTATION
ARS-P11: Pose Estimation
Wednesday 14:00–16:00; Poster Session; Poster Area E
ARS-P11.1—JOINT ESTIMATION OF HEAD POSE AND VISUAL FOCUS OF ATTENTION
ARS-P11.2—3D-FERNS+: VIEWPOINT-BASED KEYPOINT CLASSIFIER FOR ROBUST 3D OBJECT POSE DETECTION
ARS-P11.3—ROBUST FACE POSE CLASSIFICATION METHOD BASED ON GEOMETRY-PRESERVING VISUAL PHRASE
ARS-P11.4—HIERARCHICAL GAZE ESTIMATION BASED ON ADAPTIVE FEATURE LEARNING
ARS-P11.5—MAPPING AND RE-LOCALIZATION FOR MOBILE AUGMENTED REALITY
ARS-P11.6—AUTOMATIC AND ROBUST HEAD POSE ESTIMATION BY BLOCK ENERGY MAP
ARS-P11.7—GLOBAL MOTION ESTIMATION FROM RELATIVE MEASUREMENTS USING ITERATED EXTENDED KALMAN FILTER ON MATRIX LIE GROUPS
ARS-P11.8—SHADOW ANALYSIS FOR CAMERA HEADING IN IMAGE GEO-LOCALIZATION
ARS-P11.9—DIRECTIONAL CHAMFER MATCHING IN 2.5 DIMENSIONS
ARS-P11.10—ORIENTATION ESTIMATION FOR PLANAR TEXTURED SURFACES BASED ON COMPLEX WAVELETS
ARS-P11.11—LYING-POSE DETECTION WITH TRAINING DATASET EXPANSION
ARS-P11.12—SEMI-SUPERVISED LEARNING OF SPARSE REPRESENTATIONS TO RECOGNIZE PEOPLE SPATIAL ORIENTATION
ARS-P11.13—EFFICIENT 2D HUMAN POSE ESTIMATION USING MEAN-SHIFT
ARS-P11.14—MULTI-LAYER TEMPORAL GRAPHICAL MODEL FOR HEAD POSE ESTIMATION IN REAL-WORLD VIDEOS
ARS-P11.15—UNCERTAINTY MODELING FOR EFFICIENT VISUAL ODOMETRY VIA INERTIAL SENSORS ON MOBILE DEVICES
ARS-P9: Indexing and Retrieval
Wednesday 14:00–16:00; Poster Session; Poster Area B
ARS-P9.1—ROTATION-INVARIANT TEXTURE RETRIEVAL USING A STEERABLE GAUSSIAN COPULA MODEL
ARS-P9.2—LOCALITY PRESERVING HASHING
ARS-P9.3—EXPLOITING DISPARITY INFORMATION FOR STEREO IMAGE RETRIEVAL
ARS-P9.4—SKETCH BASED IMAGE RETRIEVAL USING A SOFT COMPUTATION OF THE HISTOGRAM OF EDGE LOCAL ORIENTATIONS (S-HELO)
ARS-P9.5—PLSA DRIVEN IMAGE ANNOTATION, CLASSIFICATION, AND TOURISM RECOMMENDATION
ARS-P9.6—A PRACTICAL SPATIAL RE-RANKING METHOD FOR INSTANCE SEARCH FROM VIDEOS
ARS-P9.7—WEIGHTED SVM FROM CLICKTHROUGH DATA FOR IMAGE RETRIEVAL
ARS-P9.8—IMPROVING VLAD: HIERARCHICAL CODING AND A REFINED LOCAL COORDINATE SYSTEM
ARS-P9.9—FARNESS PRESERVING NON-NEGATIVE MATRIX FACTORIZATION
ARS-P9.10—ARABIC TEXT DETECTION IN VIDEOS USING NEURAL AND BOOSTING-BASED APPROACHES: APPLICATION TO VIDEO INDEXING
ARS-P9.11—L1-NORM GLOBAL GEOMETRIC CONSISTENCY FOR PARTIAL-DUPLICATE IMAGE RETRIEVAL
ARS-P9.12—ON VISUAL SIMILARITY BASED INTERACTIVE PRODUCT RECOMMENDATION FOR ONLINE SHOPPING
ARS-P9.13—CONTENT-BASED IMAGE RETRIEVAL USING COLOR FEATURES OF SALIENT REGIONS
ARS-P9.14—SCENE-BASED AUTOMATIC IMAGE ANNOTATION
ARS-P9.15—IMAGE AUTO-ANNOTATION BY EXPLOITING WEB INFORMATION
ARS-P9.16—DENSE SAMPLING OF FEATURES FOR IMAGE RETRIEVAL
ARS-P9.17—IMAGE TAG COMPLETION BY LOW-RANK FACTORIZATION WITH DUAL RECONSTRUCTION STRUCTURE PRESERVED
ARS-P9.18—IMAGE RETRIEVAL WITH HIERARCHICAL MATCHING PURSUIT
ARS-P9.19—BENCHMARKING RESULT DIVERSIFICATION IN SOCIAL IMAGE RETRIEVAL
ARS-P9.20—LINKING TEXT AND VISUAL CONCEPTS SEMANTICALLY FOR CROSS MODAL MULTIMEDIA SEARCH
ARS-P9.21—EFFICIENT VIDEO SEARCH USING IMAGE QUERIES
ARS-P9.22—RETRIEVING IMAGES USING SALIENCY DETECTION AND GRAPH MATCHING
ARS-P9.23—CROSS MODAL METRIC LEARNING WITH MULTI-LEVEL SEMANTIC RELEVANCE
ARS-P9.24—SKETCH2MANGA: SKETCH-BASED MANGA RETRIEVAL
ARS-P9.25—IMAGE ANNOTATION VIA LEARNING THE IMAGE-LABEL INTERRELATIONS
ARS-P9.26—AUTOMATIC IMAGE ANNOTATION USING INVERSE MAPS FROM SEMANTIC EMBEDDINGS
ARS-P9.27—SCENE AND VIEWPOINT BASED VISUAL SUMMARIZATION FOR LANDMARKS
ARS-P9.28—IMAGE MATCHING USING ADAPTED IMAGE MODELS AND ITS APPLICATION TO CONTENT-BASED IMAGE RETRIEVAL
ARS-P9.29—FAST AND ACCURATE VIDEO ANNOTATION USING DENSE MOTION HYPOTHESES
ARS-P9.30—OPTIMAL NO-INTERSECTION MULTI-LABEL BINARY LOCALIZATION FOR TIME SERIES USING TOTALLY UNIMODULAR LINEAR PROGRAMMING
ARS-P9.31—3D NON-RIGID PATTERN RECOGNITION BASED ON STRUCTURAL ANALYSIS
COM-P2: Video Compression
Wednesday 14:00–16:00; Poster Session; Poster Area C
COM-P2.1—HIERARCHICAL DEPENDENCY CONTEXT MODEL BASED ARITHMETIC CODING FOR DCT VIDEO COMPRESSION
COM-P2.2—ADAPTIVE WEIGHTED DISTORTION OPTIMIZATION FOR VIDEO CODING IN RGB COLOR SPACE
COM-P2.3—RATE-DISTORTION OPTIMIZATION AND ADAPTATION OF INTRA PREDICTION FILTER PARAMETERS
COM-P2.4—NEAREST-NEIGHBOR INTRA PREDICTION FOR SCREEN CONTENT VIDEO CODING
COM-P2.5—FIR/IIR CASCADE APPROXIMATING H.264/AVC INTERPOLATION FILTER
COM-P2.6—MASKING OF TRANSFORMED INTRA-PREDICTED BLOCKS FOR HIGH QUALITY IMAGE AND VIDEO CODING
COM-P2.7—MODE-DEPENDENT DISTORTION MODELING FOR H.264/SVC COARSE GRAIN SNR SCALABILITY
COM-P2.8—JOINT DESIGN OF BI-PREDICTIVE INTERPOLATION FILTERS
COM-P2.9—RATE DISTORTION-BASED MOTION ESTIMATION SEARCH ORDERING FOR RATE-CONSTRAINED SUCCESSIVE ELIMINATION ALGORITHMS
COM-P2.10—HIERARCHICAL ANCHORING OF MOTION FIELDS FOR FULLY SCALABLE VIDEO CODING
COM-P2.11—AN EFFICIENT ADAPTIVE ENERGY MODEL BASED PREDICTIVE MOTION ESTIMATION ALGORITHM FOR VIDEO CODING
COM-P2.12—RECURSIVE PREDICTION FOR JOINT SPATIAL AND TEMPORAL PREDICTION IN VIDEO CODING
COM-P2.13—ADAPTIVE LAGRANGE MULTIPLIER SELECTION MODEL IN RATE DISTORTION OPTIMIZATION FOR 3D WAVELET-BASED SCALABLE VIDEO CODING
COM-P2.14—BIT RATE ESTIMATION FOR H.264/AVC VIDEO ENCODING BASED ON TEMPORAL AND SPATIAL ACTIVITIES
COM-P2.15—LOW-COMPLEXITY DICTIONARY BASED LOSSLESS SCREEN CONTENT CODING
COM-P2.16—CORRELATION NOISE MODELING FOR MULTIVIEW TRANSFORM DOMAIN WYNER-ZIV VIDEO CODING
COM-P2.17—COMPLEXITY REDUCTION FOR 3D-HEVC DEPTH MAPS INTRA-FRAME PREDICTION USING SIMPLIFIED EDGE DETECTOR ALGORITHM
COM-P2.18—FAST CODING TREE UNIT DEPTH DECISION FOR HIGH EFFICIENCY VIDEO CODING
COM-P2.19—GENERIC SEGMENT-WISE DC FOR 3D-HEVC DEPTH INTRA CODING
COM-P2.20—QUANTIZATION OPTIMIZATION IN MULTIVIEW PLUS DEPTH VIDEO CODING
COM-P2.21—A NOVEL DISTORTION MODEL FOR DEPTH CODING IN 3D-HEVC
COM-P2.22—A PANORAMIC 3D VIDEO CODING WITH DIRECTIONAL DEPTH AIDED INPAINTING
TEC-P7: Wavelets and Filtering
Wednesday 14:00–16:00; Poster Session; Poster Area A
TEC-P7.1—FAST L1 GAUSSIAN CONVOLUTION VIA DOMAIN SPLITTING
TEC-P7.2—LEARNING FILTERS IN GAUSSIAN PROCESS CLASSIFICATION PROBLEMS
TEC-P7.3—SCALE-SPACE FILTERING USING A PIECEWISE POLYNOMIAL REPRESENTATION
TEC-P7.4—IMPULSE-MOWING ANISOTROPIC DIFFUSION FILTER FOR IMAGE DENOISING
TEC-P7.5—FAST AND MEMORY-EFFICIENT QUANTILE FILTER FOR DATA IN THREE AND HIGHER DIMENSIONS
TEC-P7.6—A FIRST PARALLEL ALGORITHM TO COMPUTE THE MORPHOLOGICAL TREE OF SHAPES OF ND IMAGES
TEC-P7.7—IMAGE ADAPTED TOTAL ORDERING FOR MATHEMATICAL MORPHOLOGY ON MULTIVARIATE IMAGES
TEC-P7.8—A NOVEL HYPERSPECTRAL IMAGES DESTRIPING METHOD BASED ON EDGE RECONSTRUCTION AND ADAPTIVE MORPHOLOGICAL OPERATORS
TEC-P7.9—MEANINGFUL DISJOINT LEVEL LINES SELECTION
TEC-P7.10—ULTIMATE GRAIN FILTER
TEC-P7.11—OCEAN SURFACE CURRENT RETRIEVAL USING A NON HOMOGENEOUS MARKOV-SWITCHING MULTI-REGIME MODEL
TEC-P7.12—MULTIDIMENSIONAL LINEAR-PHASE PERFECT RECONSTRUCTION FILTER BANKS WITH HIGHER ORDER FEASIBLE BUILDING BLOCKS
TEC-P7.13—VOW: VARIANCE OPTIMAL WAVELETS FOR THE STEERABLE PYRAMID
TEC-P7.14—DIAGONAL VECTORISATION OF 2-D WAVELET LIFTING
TEC-P7.15—EDGE-AWARE IMAGE GRAPH EXPANSION METHODS FOR OVERSAMPLED GRAPH LAPLACIAN MATRIX
ARS-L8: Object Detection
Wednesday 16:30–18:10; Oral Session; Room: Leonard de Vinci
16:30 ARS-L8.1—OBJECT DETECTION USING EDGE HISTOGRAM OF ORIENTED GRADIENT
16:50 ARS-L8.2—LAPLACIAN OBJECT: ONE-SHOT OBJECT DETECTION BY LOCALITY PRESERVING PROJECTION
17:10 ARS-L8.3—WINDOW MINING BY CLUSTERING MID-LEVEL REPRESENTATION FOR WEAKLY SUPERVISED OBJECT DETECTION
17:30 ARS-L8.4—FUSING GENERIC OBJECTNESS AND DEFORMABLE PART-BASED MODELS FOR WEAKLY SUPERVISED OBJECT DETECTION
17:50 ARS-L8.5—HETEROGENEOUS DOMAIN ADAPTATION USING PREVIOUSLY LEARNED CLASSIFIER FOR OBJECT DETECTION PROBLEM
COI-L1: Microscopic Imaging
Wednesday 16:30–18:10; Oral Session; Room: Ampere 1+3
16:30 COI-L1.1—EXACT RECONSTRUCTION IN QUANTITATIVE PHASE MICROSCOPY
16:50 COI-L1.2—PHASE RETRIEVAL BY USING TRANSPORT-OF-INTENSITY EQUATION AND DIFFERENTIAL INTERFERENCE CONTRAST MICROSCOPY
17:10 COI-L1.3—ON PROPER SIMULATION OF PHENOMENA INFLUENCING IMAGE FORMATION IN FLUORESCENCE MICROSCOPY
17:30 COI-L1.4—BINARIZATION OF NOISY MICROSCOPY IMAGES THROUGH SIGNAL RECONSTRUCTION USING ITERATIVE DETECTION NETWORK
17:50 COI-L1.5—ALGORITHM AND BENCHMARK DATASET FOR STAIN SEPARATION IN HISTOLOGY IMAGES
DIS-L1: Mobile Visual Search
Wednesday 16:30–18:10; Oral Session; Room: Ampere 5+6
16:30 DIS-L1.1—ELEMENTARY BLOCK EXTRACTION FOR MOBILE IMAGE SEARCH
16:50 DIS-L1.2—CONTEXT-AWARE CODEBOOK LEARNING FOR MOBILE LANDMARK RECOGNITION
17:10 DIS-L1.3—WORD-HOGS: WORD HISTOGRAM OF ORIENTED GRADIENTS FOR MOBILE VISUAL SEARCH
17:30 DIS-L1.4—A HOG-BASED HAND GESTURE RECOGNITION SYSTEM ON A MOBILE DEVICE
17:50 DIS-L1.5—JOINT OPTIMIZATION OF JPEG QUANTIZATION TABLE AND COEFFICIENT THRESHOLDING FOR LOW BITRATE MOBILE VISUAL SEARCH
TEC-L6: Image Enhancement
Wednesday 16:30–18:10; Oral Session; Room: Dickens 3+4
16:30 TEC-L6.1—COMPRESSED FACE HALLUCINATION
16:50 TEC-L6.2—SINGLE IMAGE DEHAZING WITH IMAGE ENTROPY AND INFORMATION FIDELITY
17:10 TEC-L6.3—BLIND IMAGE DEBLURRING USING NON-NEGATIVE SPARSE APPROXIMATION
17:30 TEC-L6.4—IMAGE ENHANCEMENT BY ENTROPY MAXIMIZATION AND QUANTIZATION RESOLUTION UPCONVERSION
17:50 TEC-L6.5—IMAGE BIT-DEPTH ENHANCEMENT VIA MAXIMUM-A-POSTERIORI ESTIMATION OF GRAPH AC COMPONENT
SS11: Realistic 3D in Interactive Virtual Worlds
Wednesday 16:30–18:10; Oral Session; Room: Ampere 7+8
Session Chair: Julie Wall,
University of London
16:30 SS11.1—ARCHITECTURE OF A SOCIO-CONVERSATIONAL AGENT IN VIRTUAL WORLDS
16:50 SS11.2—MONITORING AND TAILORING THE USAGE OF NETWORK RESOURCES FOR SMOOTHING THE PROVISION OF INTERACTIVE 3D SERVICES
17:10 SS11.3—OPTIMIZED SCALABLE VIDEO TRANSMISSION OVER P2P NETWORK WITH HIERARCHICAL NETWORK CODING
17:30 SS11.4—ARTICULATED 3D MODEL TRACKING WITH ON-THE-FLY TEXTURING
17:50 SS11.5—SHELLCAM: INTERACTIVE GEOMETRY-AWARE VIRTUAL CAMERA CONTROL
SS2: Learning Image Features to Encode Visual Information
Wednesday 16:30–18:10; Oral Session; Room: Dickens 1+2
Session Chairs: Javier Portilla,
Consejo Superior de Investigaciones Científicas (CSIC); Joan Serra-Sagrista,
Universitat Autonoma de Barcelona
16:30 SS2.1—LEARNING TRANSFORMATIONS
16:50 SS2.2—LEARNING SPARSE FILTERBANK TRANSFORMS WITH CONVOLUTIONAL ICA
17:10 SS2.3—IMAGE RESTORATION VIA BAYESIAN STRUCTURED SPARSE CODING
17:30 SS2.4—LOSSLESS CODING OF HYPERSPECTRAL IMAGES WITH PRINCIPAL POLYNOMIAL ANALYSIS
17:50 SS2.5—LOCAL FEATURE SELECTION FOR EFFICIENT BINARY DESCRIPTOR CODING
COM-P3: HEVC
Wednesday 16:10–18:10; Poster Session; Poster Area C
COM-P3.1—SAMPLE-BASED WEIGHTED PREDICTION FOR LOSSLESS ENHANCEMENT LAYER CODING IN SHVC
COM-P3.2—LINEAR ADAPTIVE SEARCH RANGE MODEL FOR UNI-PREDICTION AND MOTION ANALYSIS FOR BI-PREDICTION IN HEVC
COM-P3.3—HEVC-BASED DEBLOCKING FILTER WITH RAMP PRESERVATION PROPERTIES
COM-P3.4—FAST HIERARCHICAL INTRA ANGULAR MODE SELECTION FOR HIGH EFFICIENCY VIDEO CODING
COM-P3.5—BACKWARD COMPATIBLE ENHANCEMENT OF CHROMA FORMAT IN HEVC
COM-P3.6—EFFECTIVE CODING UNIT SIZE DECISION BASED ON MOTION HOMOGENEITY CLASSIFICATION FOR HEVC INTER PREDICTION
COM-P3.7—ENHANCED AMVP MECHANISM BASED ADAPTIVE MOTION SEARCH RANGE DECISION ALGORITHM FOR FAST HEVC CODING
COM-P3.8—CROSS COMPONENT DECORRELATION FOR HEVC RANGE EXTENSION STANDARD
COM-P3.9—FAST INTRA MODE DECISION FOR HEVC BASED ON TRANSPARENT COMPOSITE MODEL
COM-P3.10—MODIFIED SAMPLE ADAPTIVE OFFSET FILTERING AS AN INTER-LAYER PROCESSING FOR SCALABLE HEVC
COM-P3.11—FAST AND EFFICIENT INTER CU DECISION FOR HIGH EFFICIENCY VIDEO CODING
COM-P3.12—INTRA PREDICTION WITH ADAPTIVE CU PROCESSING ORDER IN HEVC
COM-P3.13—DECODER COMPLEXITY REDUCTION FOR THE SCALABLE EXTENSION OF HEVC
COM-P3.14—SCALABLE EXTENSION OF HEVC USING ENHANCED INTER-LAYER PREDICTION
COM-P3.15—ADAPTIVE CROSS-COMPONENT PREDICTION FOR 4:4:4 HIGH EFFICIENCY VIDEO CODING
COM-P3.16—MODELING THE ENERGY CONSUMPTION OF HEVC P- AND B-FRAME DECODING
COM-P3.17—SCREEN CONTENT CODING FOR HEVC BY IMPROVED LINE-BASED INTRA BLOCK COPY
COM-P3.18—DOMINANT EDGE DIRECTION BASED FAST PARAMETER ESTIMATION ALGORITHM FOR SAMPLE ADAPTIVE OFFSET IN HEVC
COM-P3.19—AN ADAPTIVE RESIDUAL DECORRELATION METHOD FOR HEVC
COM-P3.20—REGION BASED INTER-LAYER CROSS-COLOR FILTERING FOR SCALABLE EXTENSION OF HEVC
COM-P3.21—TEMPORAL LAYER ADAPTIVE LOOP FILTER FOR HEVC
COM-P3.22—BINARY CLASSIFICATION BASED LINEAR RATE ESTIMATION MODEL FOR HEVC RDO
ELI-P4: Multiview Systems
Wednesday 16:10–18:10; Poster Session; Poster Area A
ELI-P4.1—SCREEN-CAMERA CALIBRATION USING A THREAD
ELI-P4.2—RADIAL DISTORTION CORRECTION FROM A SINGLE IMAGE OF A PLANAR CALIBRATION PATTERN USING CONVEX OPTIMIZATION
ELI-P4.3—CALIBRATION OF AN INDUSTRIAL VISION SYSTEM USING AN ELLIPSOID
ELI-P4.4—A PRACTICAL ALGORITHM FOR AUTOMATIC CHESSBOARD CORNER DETECTION
ELI-P4.5—OMNIDIRECTIONAL CAMERA CALIBRATION FROM A LOW-RANK TEXTURED IMAGE
ELI-P4.6—CALIBRATION OF DEPTH CAMERAS USING DENOISED DEPTH IMAGES
ELI-P4.7—CROSSTALK MODELING IN CIRCULARLY POLARIZED STEREOSCOPIC LCDS
ELI-P4.8—EFFECT OF EYE DOMINANCE ON THE PERCEPTION OF STEREOSCOPIC 3D VIDEO
ELI-P4.9—MASTERCAM FVV: ROBUST REGISTRATION OF MULTIVIEW SPORTS VIDEO TO A STATIC HIGH-RESOLUTION MASTER CAMERA FOR FREE VIEWPOINT VIDEO
ELI-P4.10—AUTO-RECTIFICATION OF USER PHOTOS
ELI-P4.11—QUALITY ASSESSMENT OF PERCEPTUAL CROSSTALK IN AUTOSTEREOSCOPIC DISPLAY
ELI-P4.12—IMAGE REGISTRATION FOR QUALITY ASSESSMENT OF PROJECTION DISPLAYS
ELI-P4.13—HYBRID 3D FEATURE DESCRIPTION AND MATCHING FOR MULTI-MODAL DATA REGISTRATION
ELI-P4.14—TOWARDS DYNAMIC RESOURCE OPTIMIZATION FOR CLOUD-BASED FREE VIEWPOINT VIDEO SERVICE
ELI-P5: Depth and Disparity Estimation
Wednesday 16:10–18:10; Poster Session; Poster Area D
ELI-P5.1—MONOCULAR 3D STRUCTURE ESTIMATION FOR URBAN SCENES
ELI-P5.2—EDGE GUIDED SINGLE DEPTH IMAGE SUPER RESOLUTION
ELI-P5.3—DEPTH IMAGES SUPER-RESOLUTION: AN ITERATIVE APPROACH
ELI-P5.4—POST-AGGREGATION STEREO MATCHING METHOD USING DEMPSTER-SHAFER THEORY
ELI-P5.5—ADAPTIVE STEREO MATCHING VIA LOOP-ERASED RANDOM WALK
ELI-P5.6—COARSE-TO-FINE STRATEGY FOR EFFICIENT COST-VOLUME FILTERING
ELI-P5.7—TEMPORAL AND COLOR CONSISTENT DISPARITY ESTIMATION IN STEREO VIDEOS
ELI-P5.8—DATA-DRIVEN SINGLE IMAGE DEPTH ESTIMATION USING WEIGHTED MEDIAN STATISTICS
ELI-P5.9—DEPTH MAP PROPAGATION WITH THE TEXTURE IMAGE GUIDANCE
ELI-P5.10—3D CURVATURE ANALYSIS WITH A NOVEL ONE-SHOT TECHNIQUE
ELI-P5.11—REVISITING GUIDED IMAGE FILTER BASED STEREO MATCHING AND SCANLINE OPTIMIZATION FOR IMPROVED DISPARITY ESTIMATION
ELI-P5.12—A FAST NON-LOCAL DISPARITY REFINEMENT METHOD FOR STEREO MATCHING
ELI-P5.13—GROUP SEARCHING AND PROPORTION COMBINATION BASED DISPARITY VECTOR DERIVATION FOR 3D-HEVC
ELI-P5.14—DEPTH ENHANCEMENT USING RGB-D GUIDED FILTERING
ELI-P5.15—SUBSPACE BASED DISPARITY ESTIMATION FOR PLENOPTIC CAMERAS
ELI-P5.16—PIXEL RESOLUTION PLENOPTIC DISPARITY USING COST AGGREGATION
ELI-P5.17—DEPTH MOTION DETECTION—A NOVEL RS-TRIGGER TEMPORAL LOGIC BASED METHOD
ELI-P5.18—DENSE DEPTH MAP GENERATION USING SPARSE DEPTH DATA FROM NORMAL FLOW
ELI-P5.19—DEPTH ESTIMATION FOR AUTOMOTIVE WITH TILTED OPTICS IMAGING
ELI-P5.20—MODEL BASED CLUSTERING FOR 3D DDIRECTIONAL FEATURES: APPLICATION TO DEPTH IMAGE ANALYSIS
TEC-P8: Biomedical Image Processing
Wednesday 16:10–18:10; Poster Session; Poster Area B
TEC-P8.1—A NEW METHOD FOR DATA-DRIVEN MULTI-BRAIN ATLAS GENERATION
TEC-P8.2—DIRECTED INTERACTIVITY OF LARGE-SCALE BRAIN NETWORKS: INTRODUCING A NEW METHOD FOR ESTIMATING RESTING-STATE EFFECTIVE CONNECTIVITY MRI
TEC-P8.3—ONE-SIDED TRANSPARENCY: A NOVEL VISUALIZATION FOR TUBULAR OBJECTS
TEC-P8.4—HIDDEN CONDITIONAL RANDOM FIELD FOR LUNG NODULE DETECTION
TEC-P8.5—MULTIPLE-MODEL BAYESIAN APPROACH TO VOLUMETRIC IMAGING OF CARDIAC CURRENT SOURCES
TEC-P8.6—IMPROVING DERMOSCOPY IMAGE ANALYSIS USING COLOR CONSTANCY
TEC-P8.7—FINDING THE OPTIMAL PARAMETER SETTING FOR AN ENSEMBLE-BASED LESION DETECTOR
TEC-P8.8—A NOVEL 4D PDE-BASED APPROACH FOR ACCURATE ASSESSMENT OF MYOCARDIUM FUNCTION USING CINE CARDIAC MAGNETIC RESONANCE IMAGES
TEC-P8.9—REGISTERING SEQUENCES OF IN VIVO MICROSCOPY IMAGES FOR CELL TRACKING USING DYNAMIC PROGRAMMING AND MINIMUM SPANNING TREES
TEC-P8.10—A JOINT SEGMENTATION-REGISTRATION FRAMEWORK BASED ON WEIGHTED TOTAL VARIATION AND NONLINEAR ELASTICITY PRINCIPLES
TEC-P8.11—MAMMOGRAM ITERATIVE POMPEIU-HAUSDORFF REGISTRATION ALGORITHM
TEC-P8.12—HIERARCHICAL NONRIGID MODEL FOR 3D MEDICAL IMAGE REGISTRATION
TEC-P8.13—FEATURE-BASED REGISTRATION FOR CORRELATIVE LIGHT AND ELECTRON MICROSCOPY IMAGES
TEC-P8.14—POSITIONING OF ANATOMICAL LANDMARKS IN ORTHOPEDICS BY MESH REGISTRATION
TEC-P8.15—NON RIGID IMAGE REGISTRATION BY MODELING DEFORMATIONS AS ELASTIC WAVES
TEC-P8.16—HIDDEN MARKOV MODEL-BASED MULTI-MODAL IMAGE FUSION WITH EFFICIENT TRAINING
TEC-P8.17—DEMON REGISTRATION FOR 3D IMAGES OBTAINED BY SERIAL BLOCK FACE SCANNING ELECTRON MICROSCOPY
TEC-P8.18—INTESTINAL EVENT SEGMENTATION FOR ENDOLUMINAL VIDEO ANALYSIS
TEC-P8.19—RECONSTRUCTING NEURONAL MORPHOLOGY FROM MICROSCOPY STACKS USING FAST MARCHING
TEC-P8.20—GABOR-BASED NEEDLE DETECTION AND TRACKING IN THREE-DIMENSIONAL ULTRASOUND DATA VOLUMES
TEC-P8.21—AUTOMATED COLORIMETRIC ANALYSIS IN PAPER BASED SENSORS
TEC-P8.22—PERFORMANCE OF COMPLEX-VALUED ICA ALGORITHMS FOR FMRI ANALYSIS: IMPORTANCE OF TAKING FULL DIVERSITY INTO ACCOUNT
TEC-P8.23—APPLICATIONS OF GAUSSIAN MIXTURE MODELS AND MEAN SQUARE ERROR WITHIN DATSCAN SPECT IMAGING
TEC-P8.24—SHAPE STATISTICS FOR CELL DIVISION DETECTION IN TIME-LAPSE VIDEOS OF EARLY MOUSE EMBRYO
TEC-P8.25—AN INTEGRATED GEOMETRICAL AND STOCHASTIC APPROACH FOR ACCURATE INFANT BRAIN EXTRACTION
TEC-P8.26—3-D MESH COMPENSATED WAVELET LIFTING FOR 3-D+T MEDICAL CT DATA
TEC-P8.27—RECONSTRUCTION WITH ANGULAR COMPENSATION IN RESPIRATORY-GATED CARDIAC SPECT
TEC-P8.28—PERFORMANCE ANALYSIS OF THE GAIN CORRECTION IN RADIOGRAPHY IMAGING
TEC-P8.29—ELLIPSES FROM TRIANGLES
TEC-P8.30—REGULARIZED ESTIMATION OF BLOCH-SIEGERT B1+ MAPS IN MRI
TEC-P8.31—FAST MR IMAGE RECONSTRUCTION WITH ORTHOGONAL WAVELET REGULARIZATION VIA SHIFT-VARIANT SHRINKAGE
TEC-P9: Super-Resolution
Wednesday 16:10–18:10; Poster Session; Poster Area E
TEC-P9.1—DCT COEFFICIENTS GENERATION MODEL FOR FILM GRAIN NOISE AND ITS APPLICATION IN SUPER-RESOLUTION
TEC-P9.2—SINGLE IMAGE SUPER-RESOLUTION USING SPARSE REPRESENTATIONS WITH STRUCTURE CONSTRAINTS
TEC-P9.3—HIERARCHICAL EXAMPLE-BASED RANGE-IMAGE SUPER-RESOLUTION WITH EDGE-PRESERVATION
TEC-P9.4—FRAME RATE UP-CONVERSION USING NONPARAMETRIC ESTIMATOR
TEC-P9.5—EXPLOITING IN-PLANE STRUCTURAL COMPLEXITY FOR SPARSITY BASED IMAGE SUPER-RESOLUTION
TEC-P9.6—NON-ADDITIVE IMPRECISE IMAGE SUPER-RESOLUTION
TEC-P9.7—ITERATED NEIGHBOR-EMBEDDINGS FOR IMAGE SUPER-RESOLUTION
TEC-P9.8—A NOVEL TOTAL VARIATION OPTIMIZATION METHOD AND ITS APPLICATION ON BLIND SUPER-RESOLUTION
TEC-P9.9—SHEARLET-BASED SPARSE REPRESENTATION FOR SUPER-RESOLUTION IN DIFFUSION WEIGHTED IMAGING (DWI)
TEC-P9.10—CONTENT ADAPTIVE SCREEN IMAGE SCALING
TEC-P9.11—MODIFIED NEIGHBOR EMBEDDING-BASED FACE HALLUCINATION USING COUPLED MAPPINGS OF PARTIAL LEAST SQUARES
TEC-P9.12—NEW IMAGE SUPER RESOLUTION BY TEXTURE TRANSFER
TEC-P9.13—COUPLED K-SVD DICTIONARY TRAINING FOR SUPER-RESOLUTION
TEC-P9.14—IMAGE AMPLIFICATION BASED ON PIXEL-SPLITTING
TEC-P9.15—CONTEXT-ADAPTIVE PANSHARPENING BASED ON BINARY PARTITION TREE SEGMENTATION
TEC-P9.16—A CONFIDENCE GROWING MODEL FOR SUPER-RESOLUTION
Thursday, October 30
ARS-L9: Image Classification
Thursday 10:30–12:30; Oral Session; Room: Leonard de Vinci
10:30 ARS-L9.1—ENSEMBLE MARGIN FRAMEWORK FOR IMAGE CLASSIFICATION
10:50 ARS-L9.2—MULTI-TASK IMAGE CLASSIFICATION VIA COLLABORATIVE, HIERARCHICAL SPIKE-AND-SLAB PRIORS
11:10 ARS-L9.3—A NOVEL KERNEL COLLABORATIVE REPRESENTATION APPROACH FOR IMAGE CLASSIFICATION
11:30 ARS-L9.4—INCREMENTAL LEARNING OF LATENT STRUCTURAL SVM FOR WEAKLY SUPERVISED IMAGE CLASSIFICATION
11:50 ARS-L9.5—TISVM: LARGE MARGIN CLASSIFIER FOR MISALIGNED IMAGE CLASSIFICATION
12:10 ARS-L9.6—HOW MANY MORE IMAGES DO WE NEED? PERFORMANCE PREDICTION OF BOOTSTRAPPING FOR IMAGE CLASSIFICATION
BIO-L1: Bio-Inspired Image Processing
Thursday 10:30–12:30; Oral Session; Room: Ampere 1+3
10:30 BIO-L1.1—EXAMINING VISUAL SALIENCY PREDICTION IN NATURALISTIC SCENES
10:50 BIO-L1.2—SPARSE CODING WITH A GLOBAL CONNECTIVITY CONSTRAINT
11:10 BIO-L1.3—A HOPFIELD RECURRENT NEURAL NETWORK TRAINED ON NATURAL IMAGES PERFORMS STATE-OF-THE-ART IMAGE COMPRESSION
11:30 BIO-L1.4—IMAGE/VIDEO CODING BASED ON EVOLUTIVE UNIDIRECTIONAL TRANSFORMS
11:50 BIO-L1.5—COMPARISON OF TEXTURE FEATURES FOR HUMAN EMBRYONIC STEM CELLS WITH BIO-INSPIRED MULTI-CLASS SUPPORT VECTOR MACHINE
12:10 BIO-L1.6—UNIFORMLY MINIMUM VARIANCE UNBIASED ESTIMATION FOR ASYNCHRONOUS EVENT-BASED CAMERAS
COM-L1: Video Coding
Thursday 10:30–12:30; Oral Session; Room: Ampere 5+6
10:30 COM-L1.1—FAST PARTITIONING ALGORITHM FOR HEVC INTRA FRAME CODING USING MACHINE LEARNING
10:50 COM-L1.2—A FAST INTRA CODING ALGORITHM FOR HEVC
11:10 COM-L1.3—HEVC INTRA CODING OF ULTRA HD VIDEO WITH REDUCED COMPLEXITY
11:30 COM-L1.4—SINGULAR VECTOR DECOMPOSITION BASED ADAPTIVE TRANSFORM FOR MOTION COMPENSATION RESIDUALS
11:50 COM-L1.5—CODING OF DISTORTION-CORRECTED FISHEYE VIDEO SEQUENCES USING H.265/HEVC
12:10 COM-L1.6—A PRE-FILTERING APPROACH TO EXPLOIT DECOUPLED PREDICTION AND TRANSFORM BLOCK STRUCTURES IN VIDEO CODING
IFS-L1: Data Hiding
Thursday 10:30–12:30; Oral Session; Room: Dickens 3+4
10:30 IFS-L1.1—HYBRID WEIGHTED-STEGO DETECTION USING MACHINE LEARNING
10:50 IFS-L1.2—A NEW COST FUNCTION FOR SPATIAL IMAGE STEGANOGRAPHY
11:10 IFS-L1.3—A NEW LOOK AT ML STEP-SIZE ESTIMATION FOR SCALAR COSTA SCHEME DATA HIDING
11:30 IFS-L1.4—REVERSIBLE DATA HIDING BASED ON TWO-DIMENSIONAL HISTOGRAM AND GENERALIZED HISTOGRAM SHIFTING
11:50 IFS-L1.5—GENERALIZATIONS OF THE KUZNETSOV-TSYBAKOV PROBLEM FOR GENERATING IMAGE-LIKE 2D BARCODES
12:10 IFS-L1.6—RECOVERING PLANAR PROJECTIONS OF PRINTED CLUSTERED-DOT HALFTONES
SS18: Behavior Imaging
Thursday 10:30–12:30; Oral Session; Room: Dickens 1+2
Session Chair: Severine Dubuisson,
Institut des Système Intelligents et de Robotique
10:30 SS18.1—AN AUGMENTED REPRESENTATION OF ACTIVITY IN VIDEO USING SEMANTIC-CONTEXT INFORMATION
10:50 SS18.2—3D TRAJECTORIES FOR ACTION RECOGNITION
11:10 SS18.3—CONTACTLESS MEASUREMENT OF MUSCLES FATIGUE BY TRACKING FACIAL FEATURE POINTS IN A VIDEO
11:30 SS18.4—AUTOMATED BOBBING AND PHASE ANALYSIS TO MEASURE WALKING ENTRAINMENT TO MUSIC
11:50 SS18.5—AUTOMATIC ANALYSIS OF FACIAL ATTRACTIVENESS FROM VIDEO
12:10 SS18.6—CONTINUOUS PREDICTION OF PERCEIVED TRAITS AND SOCIAL DIMENSIONS IN SPACE AND TIME
SS7: Advances in Optimization for Inverse Imaging Problems
Thursday 10:30–12:30; Oral Session; Room: Ampere 7+8
Session Chair: Jalal Fadili,
CNRS and Greyc, ENSICAEN
10:30 SS7.1—A FORWARD-BACKWARD VIEW OF SOME PRIMAL-DUAL OPTIMIZATION METHODS IN IMAGE RECOVERY
10:50 SS7.2—ON THE CONVERGENCE RATES OF PROXIMAL SPLITTING ALGORITHMS
11:10 SS7.3—THRESHOLDING RULES AND ITERATIVE SHRINKAGE/THRESHOLDING ALGORITHM: A CONVERGENCE STUDY
11:30 SS7.4—PRIMAL-DUAL FIRST ORDER METHODS FOR TOTAL VARIATION IMAGE RESTORATION IN PRESENCE OF POISSON NOISE
11:50 SS7.5—PRIMAL-DUAL INTERIOR-POINT OPTIMIZATION BASED ON MAJORIZATION-MINIMIZATION FOR EDGE-PRESERVING SPECTRAL UNMIXING
12:10 SS7.6—HYPERSPECTRAL IMAGE SUPERRESOLUTION: AN EDGE-PRESERVING CONVEX FORMULATION
ARS-P12: Segmentation
Thursday 10:30–12:30; Poster Session; Poster Area B
ARS-P12.1—INCORPORATING TEXTURE INFORMATION INTO REGION-BASED UNSUPERVISED IMAGE SEGMENTATION USING TEXTURAL SUPERPIXELS
ARS-P12.2—AUTOMATIC DEFOCUS SPECTRAL MATTING
ARS-P12.3—IMAGE SEGMENTATION BY IMAGE FORESTING TRANSFORM WITH GEODESIC BAND CONSTRAINTS
ARS-P12.4—ON THE IMPLEMENTATION OF THE MULTI-PHASE REGION SEGMENTATION, SOLVING THE HIDDEN PHASE PROBLEM
ARS-P12.5—WATERPIXELS: SUPERPIXELS BASED ON THE WATERSHED TRANSFORMATION
ARS-P12.6—UNSUPERVISED TEXTURE SEGMENTATION USING MONOGENIC CURVELETS AND THE POTTS MODEL
ARS-P12.7—RESIDUAL APPROACH ON A HIERARCHICAL SEGMENTATION
ARS-P12.8—A MODEL FOR SIMULATING USER INTERACTION IN HIERARCHICAL SEGMENTATION
ARS-P12.9—STREAMING HIERARCHICAL VIDEO SEGMENTATION BASED ON AN OBSERVATION SCALE
ARS-P12.10—EIKONAL-BASED VERTICES GROWING AND ITERATIVE SEEDING FOR EFFICIENT GRAPH-BASED SEGMENTATION
ARS-P12.11—SUPERVISED TEXTURE SEGMENTATION USING 2D LSTM NETWORKS
ARS-P12.12—ELASTIC BODY SPLINE BASED IMAGE SEGMENTATION
ARS-P12.13—ROBUST INTERACTIVE IMAGE SEGMENTATION VIA ITERATIVE REFINEMENT
ARS-P12.14—STREAMING SPATIO-TEMPORAL VIDEO SEGMENTATION USING GAUSSIAN MIXTURE MODEL
ARS-P12.15—OPTIMAL SPATIAL SCALE FOR LOCAL REGION-BASED ACTIVE CONTOURS
ARS-P12.16—FAST, ROBUST AND OCCLUSION RESILIENT MOTION BASED VIDEO SEGMENTATION
ARS-P12.17—IMPROVING SUPERPIXEL-BASED IMAGE SEGMENTATION BY INCORPORATING COLOR COVARIANCE MATRIX MANIFOLDS
ARS-P12.18—SCENE SEGMENTATION FROM DEPTH AND COLOR DATA DRIVEN BY SURFACE FITTING
ARS-P12.19—UNSUPERVISED CO-SEGMENTATION BASED ON A NEW GLOBAL GMM CONSTRAINT IN MRF
ARS-P12.20—A NEW APPROACH FOR MULTIPHASE PIECEWISE SMOOTH IMAGE SEGMENTATION
ARS-P12.21—MERGING DOMINANT SETS AND DBSCAN FOR ROBUST CLUSTERING AND IMAGE SEGMENTATION
ARS-P12.22—BLURRED IMAGE REGION DETECTION AND SEGMENTATION
ARS-P12.23—FLOODING BASED SUPERPIXELS GENERATION WITH COLOR, COMPACTNESS AND SMOOTHNESS CONSTRAINTS
ARS-P12.24—LEARNING SUPERPIXEL RELATIONS FOR SUPERVISED IMAGE SEGMENTATION
ARS-P12.25—IMAGE EDITING USING LEVEL SET TREES
ARS-P12.26—A SCANNING ELECTRON MICROSCOPE IMAGE SEGMENTATION METHOD FOR STEAM GENERATOR FOULING RATE ESTIMATION
ARS-P12.27—AGGLOMERATIVE CLUSTERING FOR FEATURE POINT GROUPING
ARS-P12.28—JACCARD INDEX COMPENSATION FOR OBJECT SEGMENTATION EVALUATION
ARS-P12.29—MORPHOLOGICAL FLOODINGS AND OPTIMAL CUTS IN HIERARCHIES
ARS-P12.30—COLOR-BASED SKIN SEGMENTATION: AN EVALUATION OF THE STATE OF THE ART
ARS-P13: Synthesis and Rendering
Thursday 10:30–12:30; Poster Session; Poster Area D
ARS-P13.1—EXPRESSIVE FACIAL ANIMATION FROM VIDEOS
ARS-P13.2—A SMARTER EXEMPLAR-BASED INPAINTING ALGORITHM USING LOCAL AND GLOBAL HEURISTICS FOR MORE GEOMETRIC COHERENCE
ARS-P13.3—RELIGHTING FROM MULTIPLE COLOR AND DEPTH IMAGES USING MATRIX FACTORIZATION
ARS-P13.4—LONG SCENE PANORAMA GENERATION FOR INDOOR ENVIRONMENT
ARS-P13.5—GABOR-BASED COVARIANCE MATRICES FOR FACE SKETCH SYNTHESIS
ARS-P13.6—A FRAMEWORK OF CHANGING IMAGE EMOTION USING EMOTION PREDICTION
ARS-P13.7—EXAMPLE-BASED MOTION MANIPULATION
ARS-P13.8—COLORBRUSH: ANIMATED DIFFUSION FOR INTUITIVE COLORIZATION SIMULATING WATER PAINTING
ARS-P13.9—2D+T AUTOREGRESSIVE FRAMEWORK FOR VIDEO TEXTURE COMPLETION
ARS-P13.10—RANDOMIZED TEXTURE FLOW ESTIMATION USING VISUAL SIMILARITY
ARS-P13.11—LOCALLY GAUSSIAN EXEMPLAR BASED TEXTURE SYNTHESIS
ARS-P13.12—OPTIMAL UV SPACES FOR FACIAL MORPHABLE MODEL CONSTRUCTION
ARS-P13.13—ALIASING-FREE SIMPLIFICATION OF SURFACE MESHES
ARS-P13.14—MESH-FREE SPARSE REPRESENTATION OF MULTIDIMENSIONAL LIDAR DATA
ARS-P13.15—SELF-SIMILARITY-BASED IMAGE COLORIZATION
ARS-P13.16—AUTOMATIC INPAINTING OF LINEARLY RELATED VIDEO FRAMES
ARS-P13.17—JOINT GAZE-CORRECTION AND BEAUTIFICATION OF DIBR-SYNTHESIZED HUMAN FACE VIA DUAL SPARSE CODING
ARS-P13.18—ROBUST VIRTUAL FRONTAL FACE SYNTHESIS FROM A GIVEN POSE USING REGULARIZED LINEAR REGRESSION
ARS-P14: Boundary and Shape Analysis
Thursday 10:30–12:30; Poster Session; Poster Area E
ARS-P14.1—OCCLUSION BOUNDARY DETECTION BASED ON MID-LEVEL FIGURE/GROUND ASSIGNMENT FEATURES
ARS-P14.2—GLOBAL SAMPLING OF IMAGE EDGES
ARS-P14.3—TOPOLOGICAL STACKING GRAYSCALE THINNING FOR EDGE DETECTION AND REAL-TIME APPLICATIONS
ARS-P14.4—DIRECTION SELECTIVE VECTOR FIELD CONVOLUTION FOR CONTOUR DETECTION
ARS-P14.5—A SIMPLE AND EFFICIENT ALGORITHM FOR DOT PATTERNS RECONSTRUCTION
ARS-P14.6—SYMMETRIC POLYNOMIALS FOR 2D SHAPE REPRESENTATION
ARS-P14.7—BIHARMONIC DENSITY ESTIMATE – A SCALE SPACE SIGNATURE FOR DEFORMABLE SURFACES
ARS-P14.8—AN OPTIMAL ELASTIC PARTIAL SHAPE MATCHING VIA SHAPE GEODESICS
ARS-P14.9—GEODESICS-BASED STATISTICAL SHAPE ANALYSIS
ARS-P14.10—NON-RIGID POINT SET REGISTRATION FOR CHINESE CHARACTERS USING STRUCTURE-GUIDED COHERENT POINT DRIFT
ARS-P14.11—A CONTRARIO DETECTION OF GOOD CONTINUATION OF POINTS
ARS-P14.12—PROBABILITY DENSITY FUNCTION OF OBJECT CONTOURS USING REGIONAL REGULARIZED STOCHASTIC WATERSHED
ARS-P14.13—SELECTIVE AND ROBUST D-DIMENSIONAL PATH OPERATORS
SMR-P3: Statistical Models
Thursday 10:30–12:30; Poster Session; Poster Area A
SMR-P3.1—A NON-PARAMETRIC APPROACH FOR THE ESTIMATION OF INTENSITY-FREQUENCY DEPENDENT NOISE
SMR-P3.2—NON-STATIONARY TEXTURE SYNTHESIS FROM RANDOM FIELD MODELING
SMR-P3.3—BAYESIAN TEXTURE AND INSTRUMENT PARAMETER ESTIMATION FROM BLURRED AND NOISY IMAGES USING MCMC
SMR-P3.4—HOMOGENEITY CLASSIFICATION FOR SIGNAL-DEPENDENT NOISE ESTIMATION IN IMAGES
SMR-P3.5—MAXIMUM LIKELIHOOD EXTENSION FOR NON-CIRCULANT DECONVOLUTION
SMR-P3.6—STATISTICAL MODELLING FOR ENHANCED OUTLIER DETECTION
SMR-P3.7—STATISTICAL MORPHABLE MODEL FOR THE HUMAN TEETH RESTORATION
SMR-P3.8—EFFICIENT BAYESIAN INFERENCE USING FULLY CONNECTED CONDITIONAL RANDOM FIELDS WITH STOCHASTIC CLIQUES
SMR-P3.9—DIGITAL CRADLE REMOVAL IN X-RAY IMAGES OF ART PAINTINGS
SMR-P3.10—MODELING CORRELATION BETWEEN MULTI-MODAL CONTINUOUS WORDS FOR PLSA-BASED VIDEO CLASSIFICATION
SMR-P3.11—OPTICAL CHARACTER RECOGNITION USING TRANSFER LEARNING DECISION FORESTS
SMR-P3.12—STABILITY EVALUATION OF NEURAL AND BAYESIAN CLASSIFIERS: A NEW INSIGHT
SMR-P3.13—ON THE AMPLITUDE AND PHASE COMPUTATION OF THE AM-FM IMAGE MODEL
SMR-P3.14—IMAGE SALIENCY DETECTION VIA MULTI-SCALE STATISTICAL NON-REDUNDANCY MODELING
TEC-P10: Restoration and Enhancement
Thursday 10:30–12:30; Poster Session; Poster Area C
TEC-P10.1—BLIND ESTIMATION OF PIXEL BRIGHTNESS TRANSFORM
TEC-P10.2—EXPLOITING IMAGE STRUCTURAL SIMILARITY FOR SINGLE IMAGE RAIN REMOVAL
TEC-P10.3—COMBINING LONG-RANGE DEPENDENCIES WITH PHASE INFORMATION IN NATURAL STOCHASTIC TEXTURE ENHANCEMENT
TEC-P10.4—UNDERSTANDING IMAGE PRIORS IN BLIND DECONVOLUTION
TEC-P10.5—AN INTEGER TONE MAPPING OPERATION FOR HDR IMAGES IN OPENEXR WITH DENORMALIZED NUMBERS
TEC-P10.6—SINGLE IMAGE HAZE REMOVAL USING NOVEL ESTIMATION OF ATMOSPHERIC LIGHT AND TRANSMISSION
TEC-P10.7—NON-BLIND IMAGE RESTORATION WITH SYMMETRIC GENERALIZED PARETO PRIORS
TEC-P10.8—CONTRAST ENHANCEMENT WITH CHROMATICITY ERROR BOUND
TEC-P10.9—A REGIONAL MULTIMODULUS ALGORITHM FOR BLIND IMAGE DECONVOLUTION
TEC-P10.10—GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS
TEC-P10.11—AN EFFECTIVE IMAGE RESTORATION USING KULLBACK-LEIBLER DIVERGENCE MINIMIZATION
TEC-P10.12—DEPTH-GUIDED ADAPTIVE CONTRAST ENHANCEMENT USING 2D HISTOGRAMS
TEC-P10.13—IMAGE ENHANCEMENT AND DYNAMIC RANGE COMPRESSION USING NOVEL INTENSITY-SPECIFIC STOCHASTIC RESONANCE-BASED PARAMETRIC IMAGE ENHANCEMENT MODEL
TEC-P10.14—IMAGE DECONVOLUTION USING TREE-STRUCTURED BAYESIAN GROUP SPARSE MODELING
TEC-P10.15—SINGLE IMAGE DEHAZING BASED ON FAST WAVELET TRANSFORM WITH WEIGHTED IMAGE FUSION
TEC-P10.16—AN ALGORITHM FOR NONCONVEX FUNCTIONAL MINIMIZATION AND APPLICATIONS TO IMAGE RESTORATION
TEC-P10.17—NIGHTTIME HAZE REMOVAL BASED ON A NEW IMAGING MODEL
TEC-P10.18—SIMULTANEOUS DEBLUR AND SUPER-RESOLUTION TECHNIQUE FOR VIDEO SEQUENCE CAPTURED BY HAND-HELD VIDEO CAMERA
TEC-P10.19—ARTIFACT REDUCTION OF COMPRESSED VIDEO VIA THREE-DIMENSIONAL ADAPTIVE ESTIMATION OF TRANSFORM COEFFICIENTS
TEC-P10.20—WHAT IS THE RIGHT CENTER/SURROUND FOR RETINEX?
TEC-P10.21—A RETINEX-BASED ENHANCING APPROACH FOR SINGLE UNDERWATER IMAGE
TEC-P10.22—RESTORATION OF ULTRASOUND IMAGES USING A HIERARCHICAL BAYESIAN MODEL WITH A GENERALIZED GAUSSIAN PRIOR
TEC-P10.23—INCOHERENT DICTIONARY LEARNING FOR SPARSE REPRESENTATION BASED IMAGE RESTORATION
TEC-P10.24—PHASE IMAGING VIA SPARSE CODING IN THE COMPLEX DOMAIN BASED ON HIGH-ORDER SVD AND NONLOCAL BM3D TECHNIQUES
TEC-P10.25—4DGVF-BASED FILTERING OF VECTOR-VALUED IMAGES
TEC-P10.26—ADAPTIVE SCALE SELECTION FOR MULTIRESOLUTION DEFOCUS BLUR ESTIMATION
TEC-P10.27—MOTION BLUR KERNEL ESTIMATION USING NOISY INERTIAL DATA
TEC-P10.28—ROBUST PAN-SHARPENING VIA COLOR SAMPLES RELOCATION AND EDGE AWARE INTERPOLATION
TEC-P10.29—SPARSITY-DRIVEN RECONSTRUCTION OF $\ELL_\INFTY$-DECODED IMAGES
ARS-L10: Tracking
Thursday 14:00–16:00; Oral Session; Room: Leonard de Vinci
14:00 ARS-L10.1—OCCLUSION-AWARE HMM-BASED TRACKING BY LEARNING
14:20 ARS-L10.2—JOINT SPARSITY-BASED ROBUST VISUAL TRACKING
14:40 ARS-L10.3—OBJECT TRACKING WITH PART-BASED DISCRIMINATIVE CONTEXT MODELS
15:00 ARS-L10.4—ROBUST PATCH-BASED TRACKING USING VALID PATCH SELECTION AND FEATURE FUSION UPDATE
15:20 ARS-L10.5—TRACKING DEFORMABLE PARTS VIA DYNAMIC CONDITIONAL RANDOM FIELDS
15:40 ARS-L10.6—DENSE NON-RIGID VISUAL TRACKING WITH A ROBUST SIMILARITY FUNCTION
COM-L2: Image Coding
Thursday 14:00–16:00; Oral Session; Room: Ampere 5+6
14:00 COM-L2.1—CLOUD-BASED DISTRIBUTED IMAGE CODING
14:20 COM-L2.2—LOSSY IMAGE CODING IN THE PIXEL DOMAIN USING A SPARSE STEERING KERNEL SYNTHESIS APPROACH
14:40 COM-L2.3—NON-CAUSAL ENCODING OF PREDICTIVELY CODED SAMPLES
15:00 COM-L2.4—IMAGE COMPRESSION BASED ON TASK-SPECIFIC INFORMATION
15:20 COM-L2.5—COLOUR IMAGE COMPRESSION WITH ANISOTROPIC DIFFUSION
15:40 COM-L2.6—EVALUATION OF CONTEXT MODELS TO CODE WAVELET-TRANSFORMED HYPERSPECTRAL IMAGES
SMR-L3: Sparse Representations
Thursday 14:00–16:00; Oral Session; Room: Dickens 3+4
14:00 SMR-L3.1—LEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING
14:20 SMR-L3.2—LEARNING MULTI-SCALE SPARSE REPRESENTATION FOR VISUAL TRACKING
14:40 SMR-L3.3—HIERARCHICAL IMAGE REPRESENTATION VIA MULTI-LEVEL SPARSE CODING
15:00 SMR-L3.4—DALM-SVD: ACCELERATED SPARSE CODING THROUGH SINGULAR VALUE DECOMPOSITION OF THE DICTIONARY
15:20 SMR-L3.5—LDA BASED COMPACT AND DISCRIMINATIVE DICTIONARY LEARNING FOR SPARSE CODING
15:40 SMR-L3.6—KERNEL TAPERING: A SIMPLE AND EFFECTIVE APPROACH TO SPARSE KERNELS FOR IMAGE PROCESSING
SS1: Variational and Morphological Optimizations: A Tribute to Vicent Caselles
Thursday 14:00–16:00; Oral Session; Room: Ampere 7+8
Session Chairs: Philippe Salembier,
Universitat Politecnica de Catalunya; Guillermo Sapiro,
Duke University; Jean Serra,
Université Paris-Est
14:00 SS1.1—PROPERTIES OF MINIMIZERS OF THE TOTAL VARIATION AND OF THE SOLUTIONS OF THE TOTAL VARIATION FLOW
14:20 SS1.2—SHAPE FROM SILHOUETTE CONSENSUS AND PHOTO-CONSISTENCY
14:40 SS1.3—HOMOGRAPHY ESTIMATION USING ONE ELLIPSE CORRESPONDENCE AND MINIMAL ADDITIONAL INFORMATION
15:00 SS1.4—AN ANALYSIS OF SCALE-SPACE SAMPLING IN SIFT
15:20 SS1.5—ADAPTIVE COLOR TRANSFER WITH RELAXED OPTIMAL TRANSPORT
15:40 SS1.6—ENERGETIC LATTICE FOR OPTIMIZING OVER HIERARCHIES OF PARTITIONS
SS10: Image Processing for Materials Characterization
Thursday 14:00–16:00; Oral Session; Room: Dickens 1+2
Session Chair: Laurent Duval,
IFP Energies Nouvelles
14:00 SS10.1—IMAGE PROCESSING FOR MATERIALS CHARACTERIZATION: ISSUES, CHALLENGES AND OPPORTUNITIES
14:20 SS10.2—STRUCTURE TENSOR BASED SYNTHESIS OF DIRECTIONAL TEXTURES FOR VIRTUAL MATERIAL DESIGN
14:40 SS10.3—MORSE THEORY AND PERSISTENT HOMOLOGY FOR TOPOLOGICAL ANALYSIS OF 3D IMAGES OF COMPLEX MATERIALS
15:00 SS10.4—IMAGE PROCESSING IN EXPERIMENTS ON, AND SIMULATIONS OF PLASTIC DEFORMATION OF POLYCRYSTALS
15:20 SS10.5—PHYSICS OF MRF REGULARIZATION FOR SEGMENTATION OF MATERIALS MICROSTRUCTURE IMAGES
15:40 SS10.6—VOLUME-BASED SHAPE ANALYSIS FOR INTERNAL MICROSTRUCTURE OF STEELS
SS15: 3D Data Security
Thursday 14:00–16:00; Oral Session; Room: Ampere 1+3
Session Chairs: Adrian Bors,
University of York; William Puech,
LIRMM
14:00 SS15.1—CRYPTANALYSIS ASPECTS IN 3-D WATERMARKING
14:20 SS15.2—SPREAD TRANSFORM AND ROUGHNESS-BASED SHAPING TO IMPROVE 3D WATERMARKING BASED ON QUADRATIC PROGRAMMING
14:40 SS15.3—A STEGANALYTIC ALGORITHM FOR 3D POLYGONAL MESHES
15:00 SS15.4—IMPACT OF GEOMETRY-PRESERVING ENCRYPTION ON RENDERING TIME
15:20 SS15.5—E3D-D2D: EMBEDDING IN 3D, DETECTION IN 2D THROUGH PROJECTIVE INVARIANTS
15:40 SS15.6—3D CONTENT FINGERPRINTING
ARS-P15: Biometric Analysis
Thursday 14:00–16:00; Poster Session; Poster Area A
ARS-P15.1—LATENT FINGERPRINT PERSISTENCE: A NEW TEMPORAL FEATURE SPACE FOR FORENSIC TRACE EVIDENCE ANALYSIS
ARS-P15.2—GENERAL PURPOSE BIVARIATE QUALITY-METRICS FOR FINGERPRINT-IMAGE ASSESSMENT REVISITED
ARS-P15.3—IMPROVING PORE EXTRACTION IN HIGH RESOLUTION FINGERPRINT IMAGES USING SPATIAL ANALYSIS
ARS-P15.4—MATCHING HETEROGENEOUS PERIOCULAR REGIONS: SHORT AND LONG STANDOFF DISTANCES
ARS-P15.5—AUTOMATIC CLOTHES SEGMENTATION FOR SOFT BIOMETRICS
ARS-P15.6—PERIOCULAR RECOGNITION BASED ON GABOR AND PARZEN PNN
ARS-P15.7—BIOMETRICS ON VISUAL PREFERENCES: A “PUMP AND DISTILL” REGRESSION APPROACH
ARS-P15.8—BEST REGIONS FOR PERIOCULAR RECOGNITION WITH NIR AND VISIBLE IMAGES
ARS-P15.9—MINIMIZING THE IMPACT OF SPOOF FABRICATION MATERIAL ON FINGERPRINT LIVENESS DETECTOR
ARS-P15.10—MATCHING FACE AGAINST IRIS IMAGES USING PERIOCULAR INFORMATION
ARS-P15.11—FINGER-DRAWN PIN AUTHENTICATION ON TOUCH DEVICES
ARS-P15.12—ON CROSS SPECTRAL PERIOCULAR RECOGNITION
ARS-P15.13—LEAP SIGNATURE RECOGNITION USING HOOF AND HOT FEATURES
ARS-P15.14—LEVERAGING APPEARANCE AND GEOMETRY FOR KINSHIP VERIFICATION
ARS-P15.15—FINGERPRINT-PKI AUTHENTICATION USING ZERNIKE MOMENTS
ARS-P16: Classification
Thursday 14:00–16:00; Poster Session; Poster Area C
ARS-P16.1—MULTI-STAGE OBJECT CLASSIFICATION FEATURING CONFIDENCE ANALYSIS OF CLASSIFIER AND INCLINED LOCAL NAIVE BAYES NEAREST NEIGHBOR
ARS-P16.2—A META ALGORITHM FOR CLASSIFICATION BY FEATURE NOMINATION
ARS-P16.3—MULTIMODAL SPARSE REPRESENTATION CLASSIFICATION WITH FISHER DISCRIMINATIVE SAMPLE REDUCTION
ARS-P16.4—FUSING WELL-CRAFTED FEATURE DESCRIPTORS FOR EFFICIENT FINE-GRAINED CLASSIFICATION
ARS-P16.5—3D OBJECT CLASSIFICATION IN BAGGAGE COMPUTED TOMOGRAPHY IMAGERY USING RANDOMISED CLUSTERING FORESTS
ARS-P16.6—ANALYSIS SPARSE CODING MODELS FOR IMAGE-BASED CLASSIFICATION
ARS-P16.7—CLASSIFYING FOOD IMAGES REPRESENTED AS BAG OF TEXTONS
ARS-P16.8—ATTRIBUTE PREDICTION WITH LONG-RANGE INTERACTIONS VIA PATH CODING
ARS-P16.9—STRUCTURE-CONSTRAINED LOW-RANK AND PARTIAL SPARSE REPRESENTATION FOR IMAGE CLASSIFICATION
ARS-P16.10—MULTI-LABEL ACTIVE LEARNING FOR IMAGE CLASSIFICATION
ARS-P16.11—RECOGNIZING LIVE FISH SPECIES BY HIERARCHICAL PARTIAL CLASSIFICATION BASED ON THE EXPONENTIAL BENEFIT
ARS-P16.12—DOG BREED CLASSIFICATION VIA LANDMARKS
ARS-P16.13—JEFFREYS CENTROIDS: A CLOSED-FORM EXPRESSION FOR POSITIVE HISTOGRAMS AND A GUARANTEED TIGHT APPROXIMATION FOR FREQUENCY HISTOGRAMS
ARS-P16.14—LOCALITY PRESERVING DISCRIMINATIVE DICTIONARY LEARNING
ARS-P16.15—NEW CASCADE MODEL FOR HIERARCHICAL JOINT CLASSIFICATION OF MULTITEMPORAL, MULTIRESOLUTION AND MULTISENSOR REMOTE SENSING DATA
ARS-P16.16—AGGREGATING CONTOUR FRAGMENTS FOR SHAPE CLASSIFICATION
ARS-P16.17—A ROTATION-INVARIANT BAG OF VISUAL WORDS MODEL FOR SYMBOLS BASED ANCIENT COIN CLASSIFICATION
ARS-P16.18—TASK-DRIVEN DICTIONARY LEARNING FOR HYPERSPECTRAL IMAGE CLASSIFICATION WITH STRUCTURED SPARSITY PRIORS
ARS-P16.19—SCALING UP DISCRETE DISTRIBUTION CLUSTERING USING ADMM
ARS-P16.20—DEGREE OF LOOP ASSESSMENT IN MICROVIDEO
ARS-P16.21—SEQUENTIAL LABELING WITH STRUCTURAL SVM UNDER THE F1 LOSS
ARS-P16.22—FACE, GENDER AND RACE CLASSIFICATION USING MULTI-REGULARIZED FEATURES LEARNING
ARS-P16.23—ROBUST NONNEGATIVE MATRIX FACTORIZATION VIA $L_1$ NORM REGULARIZATION BY MULTIPLICATIVE UPDATING RULES
COI-P1: Infrared, Multispectral, and Hyperspectral Imaging
Thursday 14:00–16:00; Poster Session; Poster Area B
COI-P1.1—MRF AND DEMPSTER-SHAFER THEORY FOR SIMULTANEOUS SHADOW/VEGETATION DETECTION ON HIGH RESOLUTION AERIAL COLOR IMAGES
COI-P1.2—A COMPRESSED SENSING-BASED PAN-SHARPENING USING JOINT DATA FIDELITY AND BLIND BLURRING KERNEL ESTIMATION
COI-P1.3—HYPERSPECTRAL IMAGE CLASSIFICATION WITH MULTIPLE KERNEL BOOSTING ALGORITHM
COI-P1.4—LINEAR DISCRIMINANT MULTIPLE KERNEL LEARNING FOR MULTISPECTRAL IMAGE CLASSIFICATION
COI-P1.5—A UNIFIED FRAMEWORK FOR LAND-COVER DATABASE UPDATE AND ENRICHMENT USING SATELLITE IMAGERY
COI-P1.6—CONTEXT DEPENDENT HYPERSPECTRAL SUBPIXEL TARGET DETECTION
COI-P1.7—USING ENSEMBLE MARGIN TO EXPLORE ISSUES OF TRAINING DATA IMBALANCE AND MISLABELING ON LARGE AREA LAND COVER CLASSIFICATION
COI-P1.8—URBAN ROAD EXTRACTION VIA GRAPH CUTS BASED PROBABILITY PROPAGATION
COI-P1.9—BINARY PARTITION TREES-BASED ROBUST ADAPTIVE HYPERSPECTRAL RX ANOMALY DETECTION
COI-P1.10—AN END-MEMBER BASED ORDERING RELATION FOR THE MORPHOLOGICAL DESCRIPTION OF HYPERSPECTRAL IMAGES
COI-P1.11—SYSTEMATIC STUDY OF COLOR SPACES AND COMPONENTS FOR THE SEGMENTATION OF SKY/CLOUD IMAGES
COI-P1.12—CLUSTER CONSTRAINT BASED SPARSE NMF FOR HYPERSPECTRAL IMAGERY UNMIXING
COI-P1.13—IMAGE FUSION USING MULTIVARIATE AND MULTIDIMENSIONAL EMD
COI-P1.14—DETECTING NEW CLASSES VIA INFINITE WARPED MIXTURE MODELS FOR HYPERSPECTRAL IMAGE ANALYSIS
COI-P1.15—ENHANCING HYPERSPECTRAL IMAGE QUALITY USING NONLINEAR PCA
COI-P1.16—SPECTRAL COMPRESSION OF HYPERSPECTRAL IMAGES BY MEANS OF NONLINEAR PRINCIPAL COMPONENTS ANALYSIS
COI-P1.17—A REAL-TIME, SEMI-AUTOMATIC METHOD FOR DISCRIMINANT TARGET INITIALIZATION IN THERMAL IMAGERY
COI-P1.18—A PHYSICS-BASED UNMIXING METHOD FOR THERMAL HYPERSPECTRAL IMAGES
COI-P1.19—HIGH-RESOLUTION COMPUTATIONAL SPECTRAL IMAGING WITH PHOTON SIEVES
COI-P1.20—SPATIAL INFORMATION BASED FCM FOR INFRARED SHIP TARGET SEGMENTATION
COI-P1.21—COMPRESSIVE DATA FUSION FOR MULTI-SENSOR IMAGE ANALYSIS
COI-P1.22—CLASSIFICATION OF HYPERSPECTRAL IMAGE BASED ON DEEP BELIEF NETWORKS
COI-P1.23—INFRARED HYPERSPECTRAL IMAGING FOR ENHANCED TISSUE VISUALIZATION AND DISCRIMINATION DURING SURGICAL OPERATION
COI-P1.24—A HARDWARE-FRIENDLY ARCHITECTURE FOR ONBOARD RATE-CONTROLLED PREDICTIVE CODING OF HYPERSPECTRAL AND MULTISPECTRAL IMAGES
COI-P1.25—BLIND SOURCE SEPARATION BASED ANOMALY DETECTION IN MULTI-SPECTRAL IMAGES
COI-P1.26—SEQUENTIAL DECONVOLUTION – UNMIXING OF BLURRED HYPERSPECTRAL DATA
COI-P1.27—LOCAL HISTOGRAM BASED CLASSIFICATION OF SAR IMAGES USING SPATIALLY DEPENDENT MIXTURES
COI-P1.28—SCENE RECOGNITION BASED ON PHASE GRADIENT INSAR IMAGES
COI-P1.29—TAILORING NON-HOMOGENEOUS MARKOV CHAIN WAVELET MODELS FOR HYPERSPECTRAL SIGNATURE CLASSIFICATION
COI-P1.30—MULTI-SPECTRAL DOCUMENT IMAGE BINARIZATION USING IMAGE FUSION AND BACKGROUND SUBTRACTION TECHNIQUES
ELI-P6: Stereo and Multiview Image Processing
Thursday 14:00–16:00; Poster Session; Poster Area E
ELI-P6.1—MULTIVIEW IMAGE AND VIDEO INTERPOLATION USING WEIGHTED VECTOR MEDIAN FILTERS
ELI-P6.2—A RAO-BLACKWELLIZED MCMC ALGORITHM FOR RECOVERING PIECEWISE PLANAR 3D MODEL FROM MULTIPLE VIEW RGBD IMAGES
ELI-P6.3—SPATIO-TEMPORAL MODELING OF VISUAL ATTENTION FOR STEREOSCOPIC 3D VIDEO
ELI-P6.4—SPRITE GENERATION FOR HOLE FILLING IN DEPTH IMAGE-BASED RENDERING
ELI-P6.5—VIEWPOINT INTERPOLATION: DIRECT AND VARIATIONAL METHODS
ELI-P6.6—A HOMOGRAPHY-BASED INPAINTING ALGORITHM FOR EFFECTIVE DEPTH-IMAGE-BASED RENDERING
ELI-P6.7—STEREO RECONSTRUCTION OF SEMIREGULAR MESHES, AND MULTIRESOLUTION ANALYSIS FOR AUTOMATIC DETECTION OF DENTS ON SURFACES
ELI-P6.8—UNDERWATER STEREO IMAGE ENHANCEMENT USING A NEW PHYSICAL MODEL
ELI-P6.9—STEREO IMAGE DEFOGGING
ELI-P6.10—STEREO VIDEO DERAINING AND DESNOWING BASED ON SPATIOTEMPORAL FRAME WARPING
ELI-P6.11—MULTI-VIEW VIDEO SUPER-RESOLUTION FOR HYBRID CAMERAS USING MODIFIED NLM AND ADAPTIVE THRESHOLDING
ELI-P6.12—ANALYTICAL MODEL FOR CAMERA DISTANCE RELATED 3D VIRTUAL VIEW DISTORTION ESTIMATION
ELI-P6.13—ON STEREO-RECTIFICATION OF PUSHBROOM IMAGES
ELI-P6.14—EDGE ENHANCEMENT OF DEPTH BASED RENDERED IMAGES
ELI-P6.15—TRANSLATION INVARIANCE-BASED SUPER RESOLUTION METHOD FOR MIXED RESOLUTION MULTIVIEW VIDEO
ELI-P6.16—LINEAR VIEW/IMAGE RESTORATION FOR DENSE LIGHT FIELDS
ELI-P6.17—MATERIALITY MAPS: A NOVEL SCENE-BASED FRAMEWORK FOR DIRECT MULTI-VIEW STEREOVISION RECONSTRUCTION
ELI-P6.18—STEREOSCOPIC VIDEO SHOT CLUSTERING INTO SEMANTIC CONCEPTS BASED ON VISUAL AND DISPARITY INFORMATION
ELI-P6.19—BALANCED OPTICAL FLOW REFINEMENT BY BIDIRECTIONAL CONSTRAINT
IFS-P1: Image Forensics
Thursday 14:00–16:00; Poster Session; Poster Area D
IFS-P1.1—HUE MODIFICATION ESTIMATION USING SENSOR PATTERN NOISE
IFS-P1.2—CONTENT BASED IMAGE AUTHENTICATION USING HOG FEATURE DESCRIPTOR
IFS-P1.3—IMAGE FORGERY DETECTION THROUGH RESIDUAL-BASED LOCAL DESCRIPTORS AND BLOCK-MATCHING
IFS-P1.4—COPY-MOVE FORGERY DETECTION BASED ON PATCHMATCH
IFS-P1.5—IMAGE FORGERY LOCALIZATION THROUGH THE FUSION OF CAMERA-BASED, FEATURE-BASED AND PIXEL-BASED TECHNIQUES
IFS-P1.6—MULTIPLE PARENTING IDENTIFICATION IN IMAGE PHYLOGENY
IFS-P1.7—ROBUST IMAGE RECAPTURE DETECTION USING A K-SVD LEARNING APPROACH TO TRAIN DICTIONARIES OF EDGE PROFILES
IFS-P1.8—A BENFORD-FOURIER JPEG COMPRESSION DETECTOR
IFS-P1.9—REVEALING SYNTHETIC FACIAL ANIMATIONS OF REALISTIC CHARACTERS
IFS-P1.10—TOWARDS AUTOMATIC DETECTION OF CHILD PORNOGRAPHY
IFS-P1.11—DETECTABILITY-QUALITY TRADE-OFF IN JPEG COUNTER-FORENSICS
IFS-P1.12—COMPRESSION NOISE BASED VIDEO FORGERY DETECTION
IFS-P1.13—WEIGHTED AVERAGING-BASED SENSOR PATTERN NOISE ESTIMATION FOR SOURCE CAMERA IDENTIFICATION
IFS-P1.14—TWOFOLD VIDEO HASHING WITH AUTOMATIC SYNCHRONIZATION
IFS-P1.15—WHO IS MY PARENT? RECONSTRUCTING VIDEO SEQUENCES FROM PARTIALLY MATCHING SHOTS
IFS-P1.16—ATTACKING THE TRIANGLE TEST IN SENSOR-BASED CAMERA IDENTIFICATION
IFS-P1.17—EXPLOITING ROLLING SHUTTER FOR ENF SIGNAL EXTRACTION FROM VIDEO
IFS-P1.18—IDENTIFICATION OF DIGITAL RADIOGRAPHY IMAGE SOURCE BASED ON DIGITAL RADIOGRAPHY PATTERN NOISE RECOGNITION
IFS-P1.19—IMAGE MODEL AND PRINTED DOCUMENT AUTHENTICATION: A THEORETICAL ANALYSIS
IFS-P1.20—COUNTERING ANTI-FORENSICS TO WAVELET-BASED COMPRESSION
ARS-L11: Facial-Expression Analysis
Thursday 16:30–18:10; Oral Session; Room: Ampere 1+3
16:30 ARS-L11.1—DETECTING EMOTIONAL STRESS FROM FACIAL EXPRESSIONS FOR DRIVING SAFETY
16:50 ARS-L11.2—REGION-BASED FEATURE FUSION FOR FACIAL-EXPRESSION RECOGNITION
17:10 ARS-L11.3—ADAPTIVE FEATURE EXTRACTION FOR BLURRED FACE IMAGES IN FACIAL EXPRESSION RECOGNITION
17:30 ARS-L11.4—ONLINE FACIAL EXPRESSION RECOGNITION BASED ON COMBINING TEXTURE AND GEOMETRIC INFORMATION
17:50 ARS-L11.5—FACIAL EXPRESSION RECOGNITION USING STATISTICAL SUBSPACE
ARS-L12: Active Contour Methods
Thursday 16:30–18:10; Oral Session; Room: Dickens 3+4
16:30 ARS-L12.1—GLOBAL-TO-LOCAL SHAPE PRIORS FOR VARIATIONAL IMAGE SEGMENTATION
16:50 ARS-L12.2—SEGMENTATION OF SPARSE NOISY POINT CLOUDS USING ACTIVE CONTOUR MODELS
17:10 ARS-L12.3—STATISTICAL REGION-BASED ACTIVE CONTOUR USING OPTIMIZATION OF ALPHA-DIVERGENCE FAMILY FOR IMAGE SEGMENTATION
17:30 ARS-L12.4—NONPARAMETRIC MDL SEGMENTATION OF INHOMOGENEOUS IMAGES BASED ON QUADRATIC LOCAL BINARY FITTING
17:50 ARS-L12.5—A ROBUST ACTIVE SHAPE MODEL USING AN EXPECTATION-MAXIMIZATION FRAMEWORK
COM-L3: Image Communications
Thursday 16:30–18:10; Oral Session; Room: Ampere 5+6
16:30 COM-L3.1—OVERLAPPING MOTION HINTS WITH POLYNOMIAL MOTION FOR VIDEO COMMUNICATION
16:50 COM-L3.2—FAST CHANNEL SWITCHING FOR SINGLE-LOOP SCALABLE HEVC
17:10 COM-L3.3—DELAY-RATE-DISTORTION OPTIMIZED RATE CONTROL FOR WIRELESS VIDEO COMMUNICATION
17:30 COM-L3.4—HYBRIDCAST: A WIRELESS IMAGE/VIDEO SOFTCAST SCHEME USING LAYERED REPRESENTATION AND HYBRID DIGITAL-ANALOG MODULATION
17:50 COM-L3.5—BANDWIDTH EFFICIENT MOBILE CLOUD GAMING WITH LAYERED CODING AND SCALABLE PHONG LIGHTING
SMR-L4: Statistical Models
Thursday 16:30–18:10; Oral Session; Room: Leonard de Vinci
16:30 SMR-L4.1—INVERSE PROBLEM FORMULATION FOR REGULARITY ESTIMATION IN IMAGES
16:50 SMR-L4.2—SIMULATION OF IMAGE TIME SERIES FROM DYNAMICAL FRACTIONAL BROWNIAN FIELDS
17:10 SMR-L4.3—TEXTURE MODELING BY GAUSSIAN FIELDS WITH PRESCRIBED LOCAL ORIENTATION
17:30 SMR-L4.4—STATISTICS OF WAVELET COEFFICIENTS FOR SPARSE SELF-SIMILAR IMAGES
17:50 SMR-L4.5—A UNIFIED MARKOV RANDOM FIELD/MARKED POINT PROCESS IMAGE MODEL AND ITS APPLICATION TO COMPUTATIONAL MATERIALS
SS20: Privacy-Preserving Multimedia Content Analysis: Privacy by Design and Social-Impact Analysis
Thursday 16:30–17:50; Oral Session; Room: Dickens 1+2
Session Chair: Atta Badii,
University of Reading
16:30 SS20.1—TEMPORAL FACE EMBEDDING AND PROPAGATION IN PHOTO COLLECTIONS
16:50 SS20.2—CROWD ANALYSIS IN NON-STATIC CAMERAS USING FEATURE TRACKING AND MULTI-PERSON DENSITY
17:10 SS20.3—SCRAMBLING FACES FOR PRIVACY PROTECTION USING BACKGROUND SELF-SIMILARITIES
17:30 SS20.4—TOWARDS OPTIMAL DISTORTION-BASED VISUAL PRIVACY FILTERS
SS9: Advances in Astronomical Signal and Image Processing
Thursday 16:30–18:10; Oral Session; Room: Ampere 7+8
Session Chair: Jerome Bobin,
CEA
16:30 SS9.1—STATISTICAL PROPERTIES OF SPHERICAL WAVELETS SYSTEMS
16:50 SS9.2—STATISTICAL ANALYSES OF GALAXY-SURVEYS TO PROBE THE STANDARD COSMOLOGICAL MODEL
17:10 SS9.3—SPARSE BLIND SOURCE SEPARATION FOR PARTIALLY CORRELATED SOURCES
17:30 SS9.4—SPARSITY IN TENSOR OPTIMIZATION FOR OPTICAL-INTERFEROMETRIC IMAGING
17:50 SS9.5—DETECTION OF ASTROPHYSICAL SOURCES IN HYPERSPECTRAL DATA. APPLICATIONS TO THE MUSE INSTRUMENT
ARS-P17: Feature Selection
Thursday 16:10–18:10; Poster Session; Poster Area C
ARS-P17.1—DTRF: A PHYSIOLOGICALLY MOTIVATED METHOD FOR IMAGE DESCRIPTION
ARS-P17.2—HDO: A NOVEL LOCAL IMAGE DESCRIPTOR
ARS-P17.3—KEYPOINT DETECTION BY CASCADED FAST
ARS-P17.4—AFFINE REGION DETECTORS ON THE FISHEYE DOMAIN
ARS-P17.5—BAMBOO: A FAST DESCRIPTOR BASED ON ASYMMETRIC PAIRWISE BOOSTING
ARS-P17.6—ROBUST TEXTURE FEATURES FOR BLURRED IMAGES USING UNDECIMATED DUAL-TREE COMPLEX WAVELETS
ARS-P17.7—PHOTOGRAPHIC PAPER TEXTURE CLASSIFICATION USING MODEL DEVIATION OF LOCAL VISUAL DESCRIPTORS
ARS-P17.8—TEMPORAL AND LONGITUDINAL VARIANCES IN WOOD LOG CROSS-SECTION IMAGE ANALYSIS
ARS-P17.9—ROTATION-INVARIANT LOCAL RADIUS INDEX: A COMPACT TEXTURE SIMILARITY FEATURE FOR CLASSIFICATION
ARS-P17.10—MAX-SIFT: FLIPPING INVARIANT DESCRIPTORS FOR WEB LOGO SEARCH
ARS-P17.11—TWO-DIMENSIONAL LOCAL TERNARY PATTERNS USING SYNCHRONIZED IMAGES FOR OUTDOOR PLACE CATEGORIZATION
ARS-P17.12—LOW-RANK SIFT: AN AFFINE INVARIANT FEATURE FOR PLACE RECOGNITION
ARS-P17.13—3D INTEREST POINT DETECTION USING LOCAL SURFACE CHARACTERISTICS WITH APPLICATION IN ACTION RECOGNITION
ARS-P17.14—SCALE-INVARIANT CORNER KEYPOINTS
ARS-P17.15—LOCAL SELF-SIMILARITY FREQUENCY DESCRIPTOR FOR MULTISPECTRAL FEATURE MATCHING
ARS-P17.16—BRISKOLA: BRISK OPTIMIZED FOR LOW-POWER ARM ARCHITECTURES
ARS-P17.17—EVALUATING THE PERFORMANCE AND CORRELATION OF COLOUR INVARIANT LOCAL IMAGE FEATURE DETECTORS
ARS-P17.18—IMPROVING THE MATCHING PRECISION OF SIFT
ARS-P17.19—LEARNING COMPRESSED IMAGE CLASSIFICATION FEATURES
ARS-P17.20—EFFICIENT FUSION OF MULTIDIMENSIONAL DESCRIPTORS FOR IMAGE RETRIEVAL
ARS-P17.21—HAMMING EMBEDDING WITH FRAGILE BITS FOR IMAGE SEARCH
ARS-P17.22—DENSE INTEREST FEATURES FOR VIDEO PROCESSING
ARS-P18: Recognition
Thursday 16:10–18:10; Poster Session; Poster Area E
ARS-P18.1—A NEW ROBUST CONTEXT-BASED DENSE CRF MODEL FOR IMAGE LABELING
ARS-P18.2—A DATASET FOR HAND-HELD OBJECT RECOGNITION
ARS-P18.3—MODELING LABEL DEPENDENCIES IN KERNEL LEARNING FOR IMAGE ANNOTATION
ARS-P18.4—AGE AND GENDER RECOGNITION USING INFORMATIVE FEATURES OF VARIOUS TYPES
ARS-P18.5—COMPLEMENTARY FEATURE EXTRACTION FOR BRANDED HANDBAG RECOGNITION
ARS-P18.6—HIERARCHY OF VISUAL FEATURES FOR OBJECT RECOGNITION
ARS-P18.7—QUALITY OF DIRTY: A DECISION MAKING ASSESSMENT METHODOLOGY FOR AUTOMATIC LICENSE PLATE RECOGNITION UNDER DIRTIED CONDITIONS
ARS-P18.8—GENDER IDENTIFICATION IN UNCONSTRAINED SCENARIOS USING SELF-SIMILARITY OF GRADIENTS FEATURES
ARS-P18.9—HIERARCHICAL MULTI-FEATURE FUSION FOR MULTIMODAL DATA ANALYSIS
ARS-P18.10—HIGH SPEED DEEP NETWORKS BASED ON DISCRETE COSINE TRANSFORMATION
ARS-P18.11—LEARNING A COMPACT LATENT REPRESENTATION OF THE BAG-OF-PARTS MODEL
ARS-P18.12—SHARING MODEL WITH MULTI-LEVEL FEATURE REPRESENTATIONS
ARS-P18.13—TEXTURE CLASSIFICATION USING ASYMMETRIC POWER DISTRIBUTION AND WAVELET TRANSFORMS
ARS-P18.14—A SHAPE-BASED OBJECT CLASS DETECTION MODEL USING LOCAL SCALE-INVARIANT FRAGMENT FEATURE
ARS-P18.15—REFINED CLOTHING TEXTURE PARSING BY EXPLOITING THE DISCRIMINATIVE MEANINGS OF SPARSE CODES
ARS-P18.16—IMPROVING NON-NEGATIVE MATRIX FACTORIZATION VIA RANKING ITS BASES
ARS-P18.17—LEARNING CO-OCCURRENCE STROKES FOR SCENE CHARACTER RECOGNITION BASED ON SPATIALITY EMBEDDED DICTIONARY
COM-P4: Image Compression
Thursday 16:10–18:10; Poster Session; Poster Area B
COM-P4.1—OPERATIONAL RATE-DISTORTION SHAPE CODING WITH DUAL ERROR REGULARIZATION
COM-P4.2—COLORIZATION MATRIX CONSTRUCTION WITH HIGH COMPRESSION EFFICIENCY FOR COLORIZATION-BASED CODING USING OPTIMIZATION
COM-P4.3—COLOR PALETTE FOR SCREEN CONTENT CODING
COM-P4.4—ADAPTIVE GUIDED IMAGE FILTERING FOR SCREEN CONTENT CODING
COM-P4.5—ON PREDICTION TECHNIQUES FOR PALETTE CODING
COM-P4.6—SELF-ADAPTIVE STRETCH IN ANAMORPHIC IMAGE COMPRESSION
COM-P4.7—UNSUPERVISED AND SUPERVISED APPROACHES TO COLOR SPACE TRANSFORMATION FOR IMAGE CODING
COM-P4.8—EPITOME INPAINTING WITH IN-LOOP RESIDUE CODING FOR IMAGE COMPRESSION
COM-P4.9—SIMPLIFIED DCT-LIFTING-BASED REVERSIBLE LAPPED TRANSFORMS USING PARALLEL PROCESSING OF TWO SAME TYPE LAPPED TRANSFORMS
COM-P4.10—LOW DELAY WYNER-ZIV CODING USING OPTICAL FLOW
COM-P4.11—A BACKWARD WAVELET REMESHER FOR LEVEL OF DETAIL CONTROL AND SCALABLE CODING
COM-P4.12—HIGHLY EFFICIENT, LOW COMPLEXITY ARITHMETIC CODER FOR JPEG2000
COM-P4.13—RATE DISTORTION OPTIMIZED QUANTIZATION BASED ON WEIGHTED MEAN SQUARED ERROR FOR LOSSY IMAGE CODING
COM-P4.14—AN EFFICIENT DCT-BASED IMAGE COMPRESSION SYSTEM BASED ON TRANSPARENT COMPOSITE MODEL
COM-P4.15—OPTIMIZED QUANTIZATION OF WAVELET SUBBANDS FOR HIGH QUALITY REAL-TIME TEXTURE COMPRESSION
COM-P4.16—IMPROVING HYBRID CODING VIA CONTROL OF QUANTIZATION ERRORS IN THE SPATIAL AND FREQUENCY DOMAINS
COM-P4.17—LOSSY DEPTH IMAGE COMPRESSION USING GREEDY RATE-DISTORTION SLOPE OPTIMIZATION
COM-P4.18—ADAPTIVE CONTEXT FORMATION FOR LINEAR PREDICTION OF IMAGE DATA
COM-P4.19—LOSSLESS IMAGE COMPRESSION USING CAUSAL BLOCK MATCHING AND 3D COLLABORATIVE FILTERING
COM-P4.20—A NEW DIFFERENTIAL AND LOSSLESS REFERENCE FRAME VARIABLE-LENGTH CODER: AN APPROACH FOR HIGH DEFINITION VIDEO CODERS
COM-P4.21—AN EFFICIENT ADAPTIVE ARITHMETIC CODING FOR BLOCK-BASED LOSSLESS IMAGE COMPRESSION USING MIXTURE MODELS
COM-P4.22—IMPROVED HEVC LOSSLESS COMPRESSION USING TWO-STAGE CODING WITH SUB-FRAME LEVEL OPTIMAL QUANTIZATION VALUES
COM-P4.23—ANCHOR POINTS CODING FOR DEPTH MAP COMPRESSION
COM-P4.24—VISUALLY LOSSLESS STRATEGIES TO DECODE AND TRANSMIT JPEG2000 IMAGERY
COM-P4.25—HIERARCHIZED BLOCK WISE IMAGE APPROXIMATION BY GREEDY PURSUIT STRATEGIES
COM-P4.26—ASYMMETRIC CODING OF STEREOSCOPIC 3D BASED ON PERCEPTUAL SIGNIFICANCE
COM-P4.27—RATE DISTORTION OPTIMAL BIT ALLOCATION FOR STEREO IMAGE CODING
IFS-P2: Image Security
Thursday 16:10–18:10; Poster Session; Poster Area A
IFS-P2.1—AN EFFECTIVE WATERMARKING METHOD AGAINST VALUMETRIC DISTORTIONS
IFS-P2.2—DISPARITY BASED STEREO IMAGE REVERSIBLE DATA HIDING
IFS-P2.3—A BLIND WATERMARKING SCHEME FOR DEPTH-IMAGE-BASED RENDERED 3D VIDEO USING THE DUAL-TREE COMPLEX WAVELET TRANSFORM
IFS-P2.4—INFORMATION HIDING IN HEVC STANDARD USING ADAPTIVE CODING BLOCK SIZE DECISION
IFS-P2.5—SIFT BASED ROBUST IMAGE WATERMARKING RESISTANT TO RESOLUTION SCALING
IFS-P2.6—IMPROVED STEGANALYSIS ALGORITHM AGAINST MOTION VECTOR BASED VIDEO STEGANOGRAPHY
IFS-P2.7—STATISTICAL DETECTION OF JSTEG STEGANOGRAPHY USING HYPOTHESIS TESTING THEORY
IFS-P2.8—SCALABLE CODING OF STREAM CIPHER ENCRYPTED IMAGES VIA ADAPTIVE SAMPLING
IFS-P2.9—A CHEAT PREVENTING METHOD WITH EFFICIENT PIXEL EXPANSION FOR NAOR-SHAMIR’S VISUAL CRYPTOGRAPHY
IFS-P2.10—SPARSE REPRESENTATION BASED ANOMALY DETECTION WITH ENHANCED LOCAL DICTIONARIES
IFS-P2.11—A SEMI-AUTOMATIC DESHREDDING METHOD BASED ON CURVE MATCHING
IFS-P2.12—EFFICIENT ALIGNMENT FOR VEHICLE MAKE AND MODEL RECOGNITION
SMR-P4: Sensing and Acquisition
Thursday 16:10–18:10; Poster Session; Poster Area D
SMR-P4.1—A PRACTICAL METHOD FOR MEASURING THE SPATIAL FREQUENCY RESPONSE OF LIGHT FIELD CAMERAS
SMR-P4.2—ROBUST VIDEO STABILIZATION BASED ON MESH GRID WARPING OF ROLLING-FREE FEATURES
SMR-P4.3—SEMI-ONLINE VIDEO STABILIZATION USING PROBABILISTIC KEYFRAME UPDATE AND INTER-KEYFRAME MOTION SMOOTHING
SMR-P4.4—KINECT UNBIASED
SMR-P4.5—A COMPARATIVE ANALYSIS OF CAPACITIVE TOUCH PANEL GRID DESIGNS AND INTERPOLATION METHODS
SMR-P4.6—MOTION ESTIMATION OF MULTIPLE DEPTH CAMERAS USING SPHERES
SMR-P4.7—A NOVEL GEOMETRIC APPROACH FOR CAMERA CALIBRATION
SMR-P4.8—FAST OMNI-IMAGE UNWARPING USING PANO-MAPPING POINTERS ARRAY
SMR-P4.9—SPECKLE IN ULTRASOUND IMAGES: FRIEND OR FOE?
SMR-P4.10—IMAGING ACTIVITY IN INTEGRATED CIRCUITS
SMR-P4.11—CONTROLLED BLURRING FOR IMPROVING IMAGE RECONSTRUCTION QUALITY IN FLUTTER-SHUTTER ACQUISITION
SMR-P4.12—3-D BATHYMETRIC RECONSTRUCTION IN MULTI-PATH AND REVERBERANT UNDERWATER ENVIRONMENTS
SMR-P4.13—EFFECTS OF STAR EXTRACTION ARTIFACTS ON BLIND ATTITUDE DETERMINATION
SMR-P4.14—BI-STATIC SYNTHETIC APERTURE INVERSION FOR NON-STATIONARY TARGET AND CLUTTER
SMR-P4.15—STRUCTURE PRESERVING BILATERAL FILTERING FOR POLSAR DATA
SMR-P4.16—AUTOMATIC FAULT TRACKING ACROSS SEISMIC VOLUMES VIA TRACKING VECTORS
SMR-P4.17—DISCONTINUOUS SEISMIC HORIZON RECONSTRUCTION BASED ON LOCAL DIP TRANSFORMATION
SMR-P4.18—TIME OF FLIGHT MOTION COMPENSATION REVISITED
SMR-P4.19—AUTOMATED REGISTRATION OF LOW AND HIGH RESOLUTION ATOMIC FORCE MICROSCOPY IMAGES USING SCALE INVARIANT FEATURES
SMR-P4.20—FLASH/NO-FLASH FUSION FOR MOBILE DOCUMENT IMAGE BINARIZATION