Last NameFirst NameTitleSessionsDateTime
AhnSoraA Method of Projection Mapping from a Moving Cart with Reflecting Position Information4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
AkashiTakuyaTemplate Matching via Search History Driven Genetic Algorithm2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
AkashiTakuyaInvestigation of Influence of Loss Function Weights of Cycle-Consistent Adversarial Networks on Generation of Pareidolia Stimuli3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
AkashiTakuyaGeneration of Dynamic Images for Fake-face Detection3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
AkatsukaShunsukeAdaptive Image Projection onto Scattering MediumPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
AkitaJunichiHow Users Feel “Beautifulness” for Images Represented by Pseudorandom Pixel PlacementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
AkizukiShuichiTemplate Matching Using a Small Number of Pixels Selected by Distinctiveness of Quantized Hue ValuesPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
AkizukiShuichiAnalysis of Human’s Skilled Process of Assembly Task using Time sequence based Machine LearningPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
AndohTomohiroAutomatic Extraction of Ridge and Valley Lines based on Overground and Underground Openness 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
AprilPyoneMaungMaungProtection of SVM Model with Secret Key from Unautorized Access6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
AramvithSupavadeeMultiple Non-Local Attentions with Self-Similarity Exemplars Mining Module for Image Super-resolution5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
AramvithSupavadeeDeep Attentive Pixels for Face Super-resolution7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
AriyaritAtthaphonA Hybrid Automatic Defect Detection Method for Thai Woven Fabrics Using CNNs Combined with an ANN3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
AsaiKikuoOn the colored holographic moving pictures employing the blue-violet color light sourcePoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
AscensoJoãoConventional versus Learning-based Video Coding Benchmarking: Where Are We?3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
AscensoJoãoTowards Reliable Point Cloud Quality AssessmentInvited Lecture 3Jan 6 (Thu)1700-1740 hrs
BaeYonghoA study on impact of VVC coding tools for Video Coding for Machine4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
Benitez-GarciaGibranComparison of Real-time CNN-based Methods for Finger-level Hand Segmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
CaoYueDeep Learning Based Post Processing Techniques for Quality Enhancement in Screen Content Coding3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ChanChris Y.H.Coded Diffraction Pattern Phase Retrieval with Green Noise Masks4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ChanYui-LamDeep Learning Based Post Processing Techniques for Quality Enhancement in Screen Content Coding3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ChangChia-MingSketch-based 3D Shape Modeling from Sparse Point Clouds3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ChangChun-TzuMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
CHANGYuanDriver Drowsiness Detection by Multi-task and Transfer Learning3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ChauChun-PongAn indoor visual positioning system using points of interest detection for mobile robot application6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
ChauLap-PuiData Analytics for Intelligent TransportationInvited Lecture 3Jan 5 (Wed)1720-1800 hrs
ChenChanghaoDynamic Photometric Stereo for Flat Bas-relief Surfaces5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
ChenHsin-YangAutomatic color calibration of color electronic papers4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ChenJhih-RongEvaluating video quality between the different number of input views by Test Model for Immersive VideoPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
ChenJiann-JoneUtilizing CU Partition Mode Inheritance to speed up H.266/VVC Intra-Frame CodingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
ChenLi-SyuanA Context-Aware Anchor-free Tiny Object Detector for Aerial Images5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
ChenSovannMultiple Non-Local Attentions with Self-Similarity Exemplars Mining Module for Image Super-resolution5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
ChenSovannDeep Attentive Pixels for Face Super-resolution7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
ChenXiu-ZhiVehicle Re-Identification System for Road Side Unit Application4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ChenYen-LinVehicle Re-Identification System for Road Side Unit Application4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ChenZhangGeometry Reconstruction for Spatial Scalability in Point Cloud Compression Based on Neighbour Occupancies6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
CheongWon-SikDescriptor based video coding for machine for multi-task2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
ChiZihengMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
ChiaHao-WenCritical Points and Ridge, Contour, and Occlusion Information for Two-Stage Facial Landmark Detection2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ChoMinjungA study on impact of VVC coding tools for Video Coding for Machine4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
ChoNam IkKernel Estimation for Super-Resolution with Flow-based Kernel PriorPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
ChoSunwooKernel Estimation for Super-Resolution with Flow-based Kernel PriorPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
ChoiJin SooDeep learning-based Feature compression for Video Coding for Machine2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
ChoiKihoA study on impact of VVC coding tools for Video Coding for Machine4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
ChooHyon-GonCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
ChooHyon-GonDescriptor based video coding for machine for multi-task2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
ChooKeng WahAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
ChophukPonlawatCOVID-19 Diagnosis Using a Sliding Window Approach Based on Feature Fusion from Chest X-ray Imaging4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
ChoyYat SzeLDCCRN: Robust Deep Learning-based Speech EnhancementPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
ChungChen-HungAn Ensemble Learning Approach to Chip Defect Detection in Optic Inspection2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
DaileyMatthew N.Robust Real Time Video Face Recognition System for Unconstrained Environments7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
DeguchiDaisukeActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
DingJian-JiunCritical Points and Ridge, Contour, and Occlusion Information for Two-Stage Facial Landmark Detection2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
DoJihoonDeep learning-based Feature compression for Video Coding for Machine2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
DobashiY.Estimation of Parameters for Rendering Fog from a Single Image4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
DongJunyuCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
DongJunyuSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
DongJunyuApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
DongJunyuIVTEN: Integration of Visual-Textual Entities using Graphs for Temporal Activity Localization via Natural Language in Video7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
DongJunyuSwin transformer and fusion for underwater image enhancementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
DongJunyuDynamic Photometric Stereo for Flat Bas-relief Surfaces5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
DuTieHuaAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
DuXushengSketch-based 3D Shape Modeling from Sparse Point Clouds3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
DuangpromKritDeep Attentive Pixels for Face Super-resolution7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
DuongVinh VanEnhancing Angular Resolution using Layers Obtained from Light Field Superpixel Segmentation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
EbaSakuraSingle-scan Multiple Object Detection based on Template Matching using Only Effective Pixels2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
EbaSakuraTemplate Matching Using a Small Number of Pixels Selected by Distinctiveness of Quantized Hue ValuesPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
EndoYoshitakaInvestigation of Influence of Loss Function Weights of Cycle-Consistent Adversarial Networks on Generation of Pareidolia Stimuli3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ErdenebayarShurentsetsegA Study on Protruding pattern Recognition of Jomon Pottery from 3D Point Clouds6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
FanHaoCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
FanHaoDynamic Photometric Stereo for Flat Bas-relief Surfaces5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
FengLinInverse Kinematics in VR Motion Mirroring1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
FengLinContinuous Dynamic Collision Detection in VR Pool4C: VR and ARJan 6 (Thu)1000-1130 hrs
FengLinFrom Visual Perception to Interpretable Visual KnowledgeKeynote 3Jan 5 (Wed)0900-0940 hrs
FuHaoA VR-based Indoor Visualization System from Floorplan Images with Deep Learning4C: VR and ARJan 6 (Thu)1000-1130 hrs
FujimotoReiA Method of Reflection Representation in Mixed Reality Using Light Source EstimationPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
FujitaHiroshiDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
FujitaHiroshiAutomated Segmentation of Oblique Abdominal Muscle Based on Body Cavity Segmentation in Torso CT Images using U-NetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
FujitaHiroshiCurrent Status of AI Support in Medical Imaging and DiagnosisKeynote 2Jan 5 (Wed)1000-1040 hrs
FukatsuAsukaA Study of Calibration Method for Lenticular Glasses-free 3D Display Using Light Transport Matrix5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
FukumiNaotoAn immersive self-training system of receive motion for volleyball beginners7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
FukusatoTsukasaInteractive 3D Character Modeling from 2D Orthogonal Drawings with Annotations5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
FukushimaNorishigeVectorized Computing for Edge-Avoiding Wavelet1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
FukushimaNorishigePolynomial Fitting for Period Prediction in Sliding-DCT-Based Filtering3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
FunahashiKenjiBlending CNNs with Different Signal Lengths for Real-time EEG Classification Sensitive to the Change5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
FuwaHirokiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
GanXiaoboModeling of Aggregates using Aperiodic Space-Filling and Physical Simulation7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
GanboldUuganbayarGeneration of Dynamic Images for Fake-face Detection3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
GotoKazuyaCar Number Recognition for Formula One Driver Identification5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
GuChunzhiDiversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
GuChunzhiMeasuring Speaking Time from Privacy-Preserving Videos3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
GuoJ.Immersive 3D Flow Visualization Based on Enhanced Texture Convolution and Volume Rendering 7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
GuoJing-MingCrack Detection Using Hybrid Convolutional Neural Networks and Transformer5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
HamamotoTakayukiA study on 5-D light field compression using multi-focus images3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
HamamotoTakayukiImaging Method using Multi-Threshold Pattern for Photon Detection of Quanta Image Sensor1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
HanHyeon-DeokBilateral Mesh Normal Filtering for Feature Enhancement1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
HanJong-KiCU Partitioning Mode Decision based on CNN for Intra Prediction of VVCPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HanJong-KiBilateral Mesh Normal Filtering for Feature Enhancement1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
HANAZAWAAkitoshiValidation of Random Forest Algorithm to Monitor Land Cover Classification and Change Detection using Remote Sensing Data in Google Earth Engine6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
HaoClifford Eng PingInverse Kinematics in VR Motion Mirroring1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
HaraTakeshiDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HaraTakeshiClassification of Pancreatic Tumors using Colored Two-dimensiona lHistograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
HaraTakeshiAutomated Segmentation of Oblique Abdominal Muscle Based on Body Cavity Segmentation in Torso CT Images using U-NetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HaradaYoshihiroA Study of Lightweighting Method Using Reinforcement Learning6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
HasebeKahoHow Users Feel “Beautifulness” for Images Represented by Pseudorandom Pixel PlacementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
HasegawaMakotoQuantification of Skin Using Smartphone and skip-GANomaly Deep Learning Model in Beauty IndustryPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HasegawaMakotoDataset Generation with GAN for Reflection Image Removal on Eyeglasses7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
HaseyamaMikiExplainable Artist Recommendation Based on Reinforcement Knowledge Graph Exploration2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
HashimotoKotaReal-time volume rendering running on an AR device in medical applicationsPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
HashimotoManabuSingle-scan Multiple Object Detection based on Template Matching using Only Effective Pixels2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
HashimotoManabuTemplate Matching Using a Small Number of Pixels Selected by Distinctiveness of Quantized Hue ValuesPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
HashimotoManabuAnalysis of Human’s Skilled Process of Assembly Task using Time sequence based Machine LearningPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
HashimotoNaokiPose Estimation Using Object Contour and Projection Distortion for Dynamic Projection Mapping6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
HayashiTatsuroDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HeXiangjianMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
HeYiSketch-based 3D Shape Modeling from Sparse Point Clouds3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
HeoChangyoungImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
HigakiToruReal-time volume rendering running on an AR device in medical applicationsPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
HiguchiDaikiA Study of Multimodal Head and Gaze Orientation Prediction Techniques in Virtual Space4C: VR and ARJan 6 (Thu)1000-1130 hrs
HolkarAkshayMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
HongKai-DunAutomatic color calibration of color electronic papers4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
HoriTakayukiHuman Retrieval from Large-Scale Video Data Based on Types and Colors of ClothingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
HorngMong-FongAn Ensemble Learning Approach to Chip Defect Detection in Optic Inspection2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
HottaYumaImprovement of Cell Image Analysis System based on CNNPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HouJunhuiDeep Learning-based Light Field Reconstruction and ProcessingTutorial 1Jan 4 (Tue)1400-1700 hrs
HsiaChih-HsienImproved Multi-Reference Makeup Transfer with Localized Attention MechanismPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
HuangZhengyuInteractive 3D Character Modeling from 2D Orthogonal Drawings with Annotations5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
HuangZiyinDeep Learning Based Post Processing Techniques for Quality Enhancement in Screen Content Coding3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
HuuThuc NguyenEnhancing Angular Resolution using Layers Obtained from Light Field Superpixel Segmentation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
IdeIchiroActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
IijimaRyotaProtection of SVM Model with Secret Key from Unautorized Access6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
IkedaYusukeMixed Reality Visualization of Room Impulse Responses on Two Planes by Moving Microphone7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
InoshitaTetsuoActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
IshidaYukiA study of colored point cloud completion for a human head6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
IshikawaKazuyaVectorized Computing for Edge-Avoiding Wavelet1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
IshikawaKazuyaPolynomial Fitting for Period Prediction in Sliding-DCT-Based Filtering3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
ISHIKAWAMayukoSwimmer Position Estimation and Stroke Analysis Based on Head Recognition5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
IslamMdMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
IsonoDaikiScale Adaptive Structure Tensor Based Rolling Trilateral Filter4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ItoKairiDepth image restoration algorithm using graph signal processing based image colorization6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
ItoTomoyaModeling of Aggregates using Aperiodic Space-Filling and Physical Simulation7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
ItohSusumuImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
ItohSusumuDesign of a SSIM-Optimal 2D Post Filter with Symmetric Coefficients for Coding Artifacts ReductionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
IwanagaShinzaburoOn the colored holographic moving pictures employing the blue-violet color light sourcePoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
IwasaYuheiClassification of Pancreatic Tumors using Colored Two-dimensional Histograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
IwashitaTakujiClassification of Pancreatic Tumors using Colored Two-dimensional Histograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
JeonByeungwooOptimizing Coded Patterns with Various Length3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
JeonByeungwooCombined CCLM and Intra PredictionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
JeonByeungwooStudy of Sub-pel Block Vector for Intra Block CopyPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
JeonByeungwooNeural Network Based Fast Transform Skip Decision for VVC Screen Content Coding7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
JeonByeungwooEnhancing Angular Resolution using Layers Obtained from Light Field Superpixel Segmentation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
JeonGwanggilDesign of Non-Separable Oversampled Lapped Transform via Stochastic Optimization for Image Restoration4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
JeongSe YoonDeep learning-based Feature compression for Video Coding for Machine2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
JiaZhenlinDynamic Photometric Stereo for Flat Bas-relief Surfaces5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
JianMuweiCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
JianMuweiSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
JianMuweiApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
JinJingDeep Learning-based Light Field Reconstruction and ProcessingTutorial 1Jan 4 (Tue)1400-1700 hrs
JuYakunSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
JungWoo-KyungCU Partitioning Mode Decision based on CNN for Intra Prediction of VVCPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KajitaniTakuyaImprovement of Cell Image Analysis System based on CNNPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KamedaYoshinariPosture Estimation for the Visually Impaired People Using Human Skeleton with White Cane2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KAMEDAYoshinariThree-Stage Navigation to Hand Size Object for Visually Impaired6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
KAMEDAYoshinariSwimmer Position Estimation and Stroke Analysis Based on Head Recognition5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
KAMEDAYoshinariA Frame-by-Frame Integrated Environment Map Building Method in Cooperative SLAM2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
KamedaYusukeImaging Method using Multi-Threshold Pattern for Photon Detection of Quanta Image Sensor1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KamedaYusukeImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KamedaYusukeDesign of a SSIM-Optimal 2D Post Filter with Symmetric Coefficients for Coding Artifacts ReductionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KamedaYusukeDepth Scene Flow Estimation based on Variational Method using Thin-Plate Spline Regularization2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
KameiHirokazuVectorized Computing for Edge-Avoiding Wavelet1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KAMEYAMAWataruDriver Drowsiness Detection by Multi-task and Transfer Learning3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
KAMEYAMAWataruPerformance Analysis of Generated Predictive Frames Using PredNet Bi-directionally7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KamiyaNaokiAutomated Segmentation of Oblique Abdominal Muscle Based on Body Cavity Segmentation in Torso CT Images using U-NetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KanariKeiFood Image Generation and Appetite Evaluation Based on Appetite Factor Analysis by Image Features6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
KanariKeiA Study of the Effects on Psychological Time Range Changed by FearPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KanedaKazufumiReal-time volume rendering running on an AR device in medical applicationsPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
KanedaMizukiCNN-based realization of Depth from Defocus technique7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
KanekoKoutaA Computer Simulation Method for the Motion Sharpening Phenomenon in Human Vision System7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KaoWen-ChungAutomatic color calibration of color electronic papers4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
KassaiKazumaSimultaneous Scanning of Both Feet Shapes using Multiple Depth SensorsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KatoHirokiAutomated Segmentation of Oblique Abdominal Muscle Based on Body Cavity Segmentation in Torso CT Images using U-NetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KatoShomaEstimating the number of Table Tennis Rallies in a Match Video2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KatsumataAkitoshiDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KawabataNorifumiColor Laparoscopic High-Definition Video Quality Assessment for Super-Resolution7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KawamoriKeitaroA Method of Automatic Photos Selection for Photo AlbumsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KawamuraKeiImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KawamuraKeiSimplified Vertex Projection and Sorting on TrisoupPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KawamuraKeiFast Decision Method for Adaptive Motion Vector Resolution in Versatile Video Coding3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
KawamuraKeiFast Decision Method for Merge with Motion Vector Difference in
Versatile Video Coding
3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
KawanishiYasutomoActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
KhooChia HongCNN-based Driver's Action Alert System2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KidaniYoshitakaFast Decision Method for Adaptive Motion Vector Resolution in Versatile Video Coding3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
KidaniYoshitakaFast Decision Method for Merge with Motion Vector Difference in
Versatile Video Coding
3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
KikuchiAoA Study on Protruding pattern Recognition of Jomon Pottery from 3D Point Clouds6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KikuchiTsukasaModeling of Aggregates using Aperiodic Space-Filling and Physical Simulation7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
KimBumyoonCombined CCLM and Intra PredictionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KimBumyoonStudy of Sub-pel Block Vector for Intra Block CopyPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KimDo YeonRegion-aware Point Cloud Sampling for Hand Gesture RecognitionPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
KimDong-HaA method of feature map reordering for machine vision based on channel correlation2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
KimHae-KwangBilateral Mesh Normal Filtering for Feature Enhancement1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
KimHaekwangCU Partitioning Mode Decision based on CNN for Intra Prediction of VVCPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
KimHanyoungImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
KimJae-GonAn Atlas Generation Method with Patch Trimming for Efficient Immersive Video Coding7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
KimJae-GonA method of feature map reordering for machine vision based on channel correlation2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
KimJihangImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
KimJongHyoImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
KimMinsuImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
KimShinCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
KimYongbeomHuman Retrieval from Large-Scale Video Data Based on Types and Colors of ClothingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KimYounheeDeep learning-based Feature compression for Video Coding for Machine2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
KimuraAkioStudy on Facial Part Extraction for Face Similarity Evaluation of Japanese Terracotta Figurines (Haniwa) from 3D Point Cloud6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KimuraKosukeAnalysis of Human’s Skilled Process of Assembly Task using Time sequence based Machine LearningPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KinoshitaTsutomuStudy on Facial Part Extraction for Face Similarity Evaluation of Japanese Terracotta Figurines (Haniwa) from 3D Point Cloud6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KinoshitaTsutomuA Study on Protruding pattern Recognition of Jomon Pottery from 3D Point Clouds6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KitaYasuyoImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KitaYasuyoDesign of a SSIM-Optimal 2D Post Filter with Symmetric Coefficients for Coding Artifacts ReductionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KitajimaMasakiA Study of the Effects on Psychological Time Range Changed by FearPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KitoAkiraEstimating the number of Table Tennis Rallies in a Match Video2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KitsudaAkiraFingerprint Minutiae Detection using Improved Tamura’s ThinningPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KiyaHitoshiProtection of SVM Model with Secret Key from Unautorized Access6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
KiyaHitoshiProxy System with JPEG Bitsretem-Based File-Size Preserving Encryption for Cloud Photo Streams2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KobayashiDaichiDevelopment of a Video Support System for Teaching Basketball Shoot Forms in Physical Education ClassesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KobayashiHiroyukiProxy System with JPEG Bitsretem-Based File-Size Preserving Encryption for Cloud Photo Streams2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
KoboriKenichiCenter of Gravity Correction Method for Self-Support of Output Model in 3D PrinterPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
KoboriKenichiA Method of Reflection Representation in Mixed Reality Using Light Source EstimationPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
KoboriKenichiA Method of Composition Evaluation for PhotographsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KoboriKenichiA Method of Automatic Photos Selection for Photo AlbumsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KoboriKenichiSimultaneous Scanning of Both Feet Shapes using Multiple Depth SensorsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KoboriKenichiAutomatic Generation of Impossible Shapes from Line-drawing CharactersPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KodamaKazuyaA study on 5-D light field compression using multi-focus images3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
KoikeYukiViewpoint Extension Method for Light Field Display using Stacked Imaginary Image Display5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
KojimaChiakiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
KojimaHirokiImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
KokaphanOpardA High Accuracy Circle Detection Method Using Multi-Angle Rotating Equilateral TrianglePoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KomatsuTakanoriHow Users Feel “Beautifulness” for Images Represented by Pseudorandom Pixel PlacementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
KongWai MingAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
KonnoKouichiA Study on Algorithm to Extract Stone Tool Surfaces from Measured Point Clouds of Joining Materials Based on Images6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KonnoKouichiStudy on Facial Part Extraction for Face Similarity Evaluation of Japanese Terracotta Figurines (Haniwa) from 3D Point Cloud6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KonnoKouichiA Study on Protruding pattern Recognition of Jomon Pottery from 3D Point Clouds6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
KubotaTsukasaDepth image restoration algorithm using graph signal processing based image colorization6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
KurosakiToshiyaTraction force presentation in Redirected Walking3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
LamKin-ManMulti-scale Feature Fusion Network for High Dynamic Range Imaging1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
LamKin-ManSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
LamKin-ManMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
LamKin-manApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
LauPhooi YeePetCare: A Real-time Pet Monitoring System with Food Dispensing using Raspberry Pi4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
LauPhooi YeeSiren Tracking System with Emergency Support using Self-Organizing MapPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
LauPhooi YeeCNN-based Driver's Action Alert System2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
LawNgai-FongPRNU-based Source Camera Identification on Smart Video Surveillance: A Practical Approach5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
LawSai-ChungPRNU-based Source Camera Identification on Smart Video Surveillance: A Practical Approach5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
LeeChulLow-light Image Enhancement via Channel-wise Intensity Transformation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
LeeHeeKyungDescriptor based video coding for machine for multi-task2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
LeeJaelinOptimizing Coded Patterns with Various Length3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
LeeJeehwanNeural Network Based Fast Transform Skip Decision for VVC Screen Content Coding7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
LeeJeehwanCombined CCLM and Intra PredictionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
LeeJemyoungImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
LeeJin YoungDescriptor based video coding for machine for multi-task2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
LeeJooyoungDeep learning-based Feature compression for Video Coding for Machine2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
LeeKyongJoonImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
LeePin-HuaImproved Multi-Reference Makeup Transfer with Localized Attention MechanismPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
LeeSanghoonDoes Modern Facial Feature Extraction Network Needs Face Normalization?: A Study on K-Face DatasetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
LeeTsair-FwuAn Ensemble Learning Approach to Chip Defect Detection in Optic Inspection2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
LeeWei QiPetCare: A Real-time Pet Monitoring System with Food Dispensing using Raspberry Pi4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
LeeYegiCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
LeeYujinStudy of Sub-pel Block Vector for Intra Block CopyPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
LiDuRobust Lane Detection through Automatic Trajectory Analysis with Deep Learning and Big Data Environment7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
LiJiafengAnomaly Object Detection in X-ray Images with Gabor Convolution and Bigger Discriminative RoI Pooling2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
LiSichengInteractive Drawing Interface with 3D Animal Model Retrieval3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
LiTianshanMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
LiWenyunA Single-Target License Plate Detection with Attention7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
LiXinyueMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
LIANGZilongThree-Stage Navigation to Hand Size Object for Visually Impaired6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
LimHanshinCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
LimSung-GyunAn Atlas Generation Method with Patch Trimming for Efficient Immersive Video Coding7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
LinTing-LanEvaluating video quality between the different number of input views by Test Model for Immersive VideoPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
LiuAllen Yan LunAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
LuXiangweiSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
LuXinStudy on Facial Part Extraction for Face Similarity Evaluation of Japanese Terracotta Figurines (Haniwa) from 3D Point Cloud6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
LunDaniel P.K.Coded Diffraction Pattern Phase Retrieval with Green Noise Masks4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
LunDaniel P.K.LDCCRN: Robust Deep Learning-based Speech EnhancementPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
LunDaniel Pak-KongRobust Lane Detection through Automatic Trajectory Analysis with Deep Learning and Big Data Environment7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
LvQingxuanSwin transformer and fusion for underwater image enhancementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MaChunjieAnomaly Object Detection in X-ray Images with Gabor Convolution and Bigger Discriminative RoI Pooling2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
MaChunjieAbnormal object detection in X-ray images with self-normalizing channel attention and efficient data augmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
MaedaShunMeasuring Speaking Time from Privacy-Preserving Videos3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
MaekawaMisatoA VR-based Repetitive Learning System of Accurate Tuna Dismantling for Fisheries High School Students4C: VR and ARJan 6 (Thu)1000-1130 hrs
MakinoMitsunoriA VR-based Repetitive Learning System of Accurate Tuna Dismantling for Fisheries High School Students4C: VR and ARJan 6 (Thu)1000-1130 hrs
MakinoMitsunoriAn immersive self-training system of receive motion for volleyball beginners7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
MakinoMitsunoriA VR-based Indoor Visualization System from Floorplan Images with Deep Learning4C: VR and ARJan 6 (Thu)1000-1130 hrs
ManabeYoshitsuguA Study of Lightweighting Method Using Reinforcement Learning6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
ManabeYoshitsuguA study of Automatic generation of motif tag in Nishiki-ePoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
ManabeYoshitsuguImproving the Accuracy of the Color Constancy Network by Object Detection5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
ManabeYoshitsuguA Study of Multimodal Head and Gaze Orientation Prediction Techniques in Virtual Space4C: VR and ARJan 6 (Thu)1000-1130 hrs
ManabeYoshitsuguA study of colored point cloud completion for a human head6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
MANGKHASEUMSackdavongValidation of Random Forest Algorithm to Monitor Land Cover Classification and Change Detection using Remote Sensing Data in Google Earth Engine6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
MarkoniHerleeyandiCrack Detection Using Hybrid Convolutional Neural Networks and Transformer5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
MatsudaIchiroImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
MatsudaIchiroDesign of a SSIM-Optimal 2D Post Filter with Symmetric Coefficients for Coding Artifacts ReductionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
MatsumotoKotaA feasibility study of watermark embedding in RNN models3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
MatsuoRuiQuantification of Skin Using Smartphone and skip-GANomaly Deep Learning Model in Beauty IndustryPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
MigitaMasahiroStudy on Bottom Sediment Classification by Complementary Use of Seafloor Images and Environmental Sounds4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
MinagiHoshitoA study of Automatic generation of motif tag in Nishiki-ePoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
MiyataKazunoriInteractive Drawing Interface with 3D Animal Model Retrieval3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
MiyataKazunoriInteractive Shadow Generation System for Spatial Augmented Reality4C: VR and ARJan 6 (Thu)1000-1130 hrs
MiyoshiRyoAnalysis of Human’s Skilled Process of Assembly Task using Time sequence based Machine LearningPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
MizunoShinjiA Method of Projection Mapping from a Moving Cart with Reflecting Position Information4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
MoriMitsuhiroAutomatic Generation of Impossible Shapes from Line-drawing CharactersPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MoriTaroActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
MorishitaTakumiDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
MugungaIsraelIVTEN: Integration of Visual-Textual Entities using Graphs for Temporal Activity Localization via Natural Language in Video7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MungSteve W.Y.LDCCRN: Robust Deep Learning-based Speech EnhancementPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
MurakiYutaCenter of Gravity Correction Method for Self-Support of Output Model in 3D PrinterPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
MurakiYutaA Method of Reflection Representation in Mixed Reality Using Light Source EstimationPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
MurakiYutaA Method of Composition Evaluation for PhotographsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MurakiYutaA Method of Automatic Photos Selection for Photo AlbumsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MurakiYutaSimultaneous Scanning of Both Feet Shapes using Multiple Depth SensorsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MurakiYutaAutomatic Generation of Impossible Shapes from Line-drawing CharactersPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
MuramatsuShogoDesign of Non-Separable Oversampled Lapped Transform via Stochastic Optimization for Image Restoration4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
MuramatsuChisakoDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
MuraseHiroshiActive Learning for Human Pose Estimation based on Temporal Pose Continuity6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
MutouRyouHuman Retrieval from Large-Scale Video Data Based on Types and Colors of ClothingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
NakabayashiNaoyaSingle-scan Multiple Object Detection based on Template Matching using Only Effective Pixels2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
NakaguchiToshiyaColor Laparoscopic High-Definition Video Quality Assessment for Super-Resolution7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
NakaizumiYasutakaPosture Estimation for the Visually Impaired People Using Human Skeleton with White Cane2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
NakajimaKatsutoEmpty Mug Detection in Pubs and Restaurants Using a Ceiling Camera6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
NakajimaKatsutoCar Number Recognition for Formula One Driver Identification5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
NakaneTakumiTemplate Matching via Search History Driven Genetic Algorithm2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
NakataTakayuki.Method of Hiding Phase-shift Pattern for Depth Estimation in Interactive Art5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
NakataTakayukiViewpoint Extension Method for Light Field Display using Stacked Imaginary Image Display5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
NakataTakayukiRaden Code: A study of Matching Algorithm for Raden Based on Phase Information6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
NakataTakayukiA Study of Calibration Method for Lenticular Glasses-free 3D Display Using Light Transport Matrix5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
NakataTakayukiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
NakataTakayukiTraction force presentation in Redirected WalkingPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
NakatsukaJumpeiCenter of Gravity Correction Method for Self-Support of Output Model in 3D PrinterPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
NamikiShuichiImaging Method using Multi-Threshold Pattern for Photon Detection of Quanta Image Sensor1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
NamiokaRyosukeStudy on Facial Part Extraction for Face Similarity Evaluation of Japanese Terracotta Figurines (Haniwa) from 3D Point Cloud6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
NaoyaNakabayashiTemplate Matching Using a Small Number of Pixels Selected by Distinctiveness of Quantized Hue ValuesPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
NawazHafiza SadiaIVTEN: Integration of Visual-Textual Entities using Graphs for Temporal Activity Localization via Natural Language in Video7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
NishiharaIsao.Method of Hiding Phase-shift Pattern for Depth Estimation in Interactive Art5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
NishiharaIsaoViewpoint Extension Method for Light Field Display using Stacked Imaginary Image Display5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
NishiharaIsaoA Study of Calibration Method for Lenticular Glasses-free 3D Display Using Light Transport Matrix5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
NishiyamaWataruDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
OgawaKodaiDesign of a SSIM-Optimal 2D Post Filter with Symmetric Coefficients for Coding Artifacts ReductionPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
OgawaTakahiroExplainable Artist Recommendation Based on Reinforcement Knowledge Graph Exploration2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
OhtsukaTomohikoFingerprint Minutiae Detection using Improved Tamura’s ThinningPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
OikawaYasuhiroMixed Reality Visualization of Room Impulse Responses on Two Planes by Moving Microphone7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
OkiMasayaImprovement of Cell Image Analysis System based on CNNPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
OkuraYukiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
Olivares-MercadoJesusComparison of Real-time CNN-based Methods for Finger-level Hand Segmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
OliveiraHelenaConventional versus Learning-based Video Coding Benchmarking: Where Are We?3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
OmiKazukiOn the Instability of Unsupervised Domain Adaptation with ADDAPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
OsaAtsushiA Computer Simulation Method for the Motion Sharpening Phenomenon in Human Vision System7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
OtaTakashiBlending CNNs with Different Signal Lengths for Real-time EEG Classification Sensitive to the Change5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
OtakaKokiA Computer Simulation Method for the Motion Sharpening Phenomenon in Human Vision System7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
ParkJae-HyunImproved Lung Cancer Detection in Ultra Low dose CT with Combined AI-based Nodule Detection and Denoising Techniques7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
ParkJaeminLow-light Image Enhancement via Channel-wise Intensity Transformation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
ParkJeeyoonNeural Network Based Fast Transform Skip Decision for VVC Screen Content Coding7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
PedsuwunSitthipongMultiple Non-Local Attentions with Self-Similarity Exemplars Mining Module for Image Super-resolution5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
PengChiVehicle Re-Identification System for Road Side Unit Application4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
PereiraFernandoConventional versus Learning-based Video Coding Benchmarking: Where Are We?3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
PhanthunaNattapongWhiteness Equipment of Plastic Pellets via Digital Image ProcessingPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
PhanthunaPiyatidaWhiteness Equipment of Plastic Pellets via Digital Image ProcessingPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
PoonsriArisaEfficient integration of partial point clouds with few geometric features using improved colored ICP algorithm6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
ProngerSamanthaMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
PunChi-ManA Single-Target License Plate Detection with Attention7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
PunChi ManMultimedia Information Security, Forensic and PrivacyTutorial 1Jan 4 (Tue)1400-1700 hrs
PurevsurenEnkhtaivanGeneration of Dynamic Images for Fake-face Detection3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
QianKemaoGabor’s two inventions6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
QinXukunCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
RajakAmirRobust Real Time Video Face Recognition System for Unconstrained Environments7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
RigallEricApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
RigallEricIVTEN: Integration of Visual-Textual Entities using Graphs for Temporal Activity Localization via Natural Language in Video7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
RomanRobitzki SaschaInverse Kinematics in VR Motion Mirroring1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
RoumenovRaytchev BisserReal-time volume rendering running on an AR device in medical applicationsPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
Sae-TangWannidaA High Accuracy Circle Detection Method Using Multi-Angle Rotating Equilateral TrianglePoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
Sae-TangWannidaA Hybrid Automatic Defect Detection Method for Thai Woven Fabrics Using CNNs Combined with an ANN3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
SaifuddinAliAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
SaitoTakumiPose Estimation Using Object Contour and Projection Distortion for Dynamic Projection Mapping6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
SakaiKentaroOn the colored holographic moving pictures employing the blue-violet color light sourcePoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
SAKAMAKanatoPerformance Analysis of Generated Predictive Frames Using PredNet Bi-directionally7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
SakaueFumihikoModelling Reflections on Complex Microstructures for Multiplex Image Projection1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
SakaueFumihikoAdaptive Image Projection onto Scattering MediumPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
SakazawaShigeyukiOn the tolerance of CNN watermarking against model optimizationsPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
SakazawaShigeyukiA feasibility study of watermark embedding in RNN models3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
SakuraiKeigoExplainable Artist Recommendation Based on Reinforcement Knowledge Graph Exploration2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
SamuraToshikazuAutomatic Extraction of Ridge and Valley Lines based on Overground and Underground Openness 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
Sanchez-PerezGabrielComparison of Real-time CNN-based Methods for Finger-level Hand Segmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
SatoJunModelling Reflections on Complex Microstructures for Multiplex Image Projection1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
SatoJunAdaptive Image Projection onto Scattering MediumPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
SatoKokiOn the colored holographic moving pictures employing the blue-violet color light sourcePoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
SatoMieFood Image Generation and Appetite Evaluation Based on Appetite Factor Analysis by Image Features6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
SatoMieA Study of the Effects on Psychological Time Range Changed by FearPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
SatoShunichiImaging Method using Multi-Threshold Pattern for Photon Detection of Quanta Image Sensor1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
SawaiKeiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
SawanoHiroakiEstimating the number of Table Tennis Rallies in a Match Video2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
SeahHock SooneXpressive B-Spline Curves: a Pilot Study on a Flexible Shape Representation 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
SeinoYutaDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
SEKIGUCHShunichiPerformance Analysis of Generated Predictive Frames Using PredNet Bi-directionally7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
SeoJeongilCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
SeoJeongilDescriptor based video coding for machine for multi-task2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
ShengLong ShiContinuous Dynamic Collision Detection in VR Pool4C: VR and ARJan 6 (Thu)1000-1130 hrs
ShiehChin-ShiuhAn Ensemble Learning Approach to Chip Defect Detection in Optic Inspection2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
ShihZen-ChungA Context-Aware Anchor-free Tiny Object Detector for Aerial Images5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
ShimekakeToyokazuEmpty Mug Detection in Pubs and Restaurants Using a Ceiling Camera6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
ShimizuMasahitoClassification of Pancreatic Tumors using Colored Two-dimensional Histograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
ShimojoShinsukeInvestigation of Influence of Loss Function Weights of Cycle-Consistent Adversarial Networks on Generation of Pareidolia Stimuli3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ShinjuT.Estimation of Parameters for Rendering Fog from a Single Image4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
ShishidoHidehikoPosture Estimation for the Visually Impaired People Using Human Skeleton with White Cane2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
SHISHIDOHidehikoThree-Stage Navigation to Hand Size Object for Visually Impaired6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
SHISHIDOHidehikoSwimmer Position Estimation and Stroke Analysis Based on Head Recognition5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
SHISHIDOHidehikoA Frame-by-Frame Integrated Environment Map Building Method in Cooperative SLAM2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ShishikuiYoshiakiUHDTV - Present and FutureInvited Lecture 3Jan 5 (Wed)1640-1720 hrs
SiuWan-ChiAn indoor visual positioning system using points of interest detection for mobile robot application6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
SiuWan-ChiRobust Lane Detection through Automatic Trajectory Analysis with Deep Learning and Big Data Environment7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
SomekhMichael G.Coded Diffraction Pattern Phase Retrieval with Green Noise Masks4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
SongByung CheolRegion-aware Point Cloud Sampling for Hand Gesture RecognitionPoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
SoonSeah HockInverse Kinematics in VR Motion Mirroring1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
SrisukSuttipatFast Aerial Image Segmentation based on Feature Pyramid NetworkPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
SuJiann-AnnUtilizing CU Partition Mode Inheritance to speed up H.266/VVC Intra-Frame CodingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
SugiyamShuntaImproving the Accuracy of the Color Constancy Network by Object Detection5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
SuiYiliangeXpressive B-Spline Curves: a Pilot Study on a Flexible Shape Representation 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
SumiyaYutoVectorized Computing for Edge-Avoiding Wavelet1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
SumiyaYutoPolynomial Fitting for Period Prediction in Sliding-DCT-Based Filtering3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
SunXinApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
SunJinghaoSwin transformer and fusion for underwater image enhancementPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
SuzukAkihiroFood Image Generation and Appetite Evaluation Based on Appetite Factor Analysis by Image Features6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
SuzukiTakuziA study of Automatic generation of motif tag in Nishiki-ePoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
SuzukiYumaHuman Retrieval from Large-Scale Video Data Based on Types and Colors of ClothingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
TadamuraKatsumiAutomatic Extraction of Ridge and Valley Lines based on Overground and Underground Openness 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
TagamiRinaTemplate Matching Using a Small Number of Pixels Selected by Distinctiveness of Quantized Hue ValuesPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
TakahashiHirokiComparison of Real-time CNN-based Methods for Finger-level Hand Segmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
TakahashiNaohiroModelling Reflections on Complex Microstructures for Multiplex Image Projection1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
TakahashiRyoDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
TakahashiSoushiDesign of Non-Separable Oversampled Lapped Transform via Stochastic Optimization for Image Restoration4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
TakahashiTokiichiroA Hand Gesture Recognition Interface for Switching VR Operation Modes4C: VR and ARJan 6 (Thu)1000-1130 hrs
TakahashiTsukasaA Study on Algorithm to Extract Stone Tool Surfaces from Measured Point Clouds of Joining Materials Based on Images6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
TakakiShotaStudy on Bottom Sediment Classification by Complementary Use of Seafloor Images and Environmental Sounds4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
TakanoKunihikoOn the colored holographic moving pictures employing the blue-violet color light sourcePoster III: VR and 3D ApplicationsJan 6 (Thu)1400-1530 hrs
TakayamaNatsukiComparison of Real-time CNN-based Methods for Finger-level Hand Segmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
TakeuchiYumaDevelopment of a Video Support System for Teaching Basketball Shoot Forms in Physical Education ClassesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
TakeuchiaYujiClassification of Pancreatic Tumor susing Colored Two-dimensional Histograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
TakiTsuyoshiDevelopment of a Video Support System for Teaching Basketball Shoot Forms in Physical Education ClassesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
TamakiToruEstimating the number of Table Tennis Rallies in a Match Video2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
TamakiToruOn the Instability of Unsupervised Domain Adaptation with ADDAPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
TamamotoTakumiExtraction of Perilla frutescens Area in Farmland Using Camera on a Self-Propelled Robot and Examine of Evaluation Methode5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
TanGrace Feng LingAutomated Lung Ultrasound (LUS) Image Assessment Using Artificial Intelligence To Estimate Fluid Overload In Dialysis PatientsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
TanHoai ThangSiren Tracking System with Emergency Support using Self-Organizing MapPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
TandianusBudiantoeXpressive B-Spline Curves: a Pilot Study on a Flexible Shape Representation 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
TodaMasashiStudy on Bottom Sediment Classification by Complementary Use of Seafloor Images and Environmental Sounds4B: Multimedia Systems and ApplicationsJan 6 (Thu)1000-1130 hrs
TogoRenExplainable Artist Recommendation Based on Reinforcement Knowledge Graph Exploration2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
ToizumeAkane.Method of Hiding Phase-shift Pattern for Depth Estimation in Interactive Art5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
TokaiShogoEfficient integration of partial point clouds with few geometric features using improved colored ICP algorithm6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
TsaiI-HsingAn Ensemble Learning Approach to Chip Defect Detection in Optic Inspection2B: Multimedia Applications and Systems (Best Paper Session IV)Jan 5 (Wed)1330-1500 hrs
TsangSik-HoDeep Learning Based Post Processing Techniques for Quality Enhancement in Screen Content Coding3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
TsurusakiHirokiFast Decision Method for Adaptive Motion Vector Resolution in Versatile Video Coding3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
TsurusakiHirokiFast Decision Method for Merge with Motion Vector Difference in
Versatile Video Coding
3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
UchidaKentaA Hand Gesture Recognition Interface for Switching VR Operation Modes4C: VR and ARJan 6 (Thu)1000-1130 hrs
UekiKazuyaEnglish Language Learning Materials with Automatic Question Creation and Scoring FunctionsPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
UekiKazuyaHuman Retrieval from Large-Scale Video Data Based on Types and Colors of ClothingPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
UmebayashiShuhoA study on 5-D light field compression using multi-focus images3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
UnnoKyoheiImproved Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
UnnoKyoheiSimplified Vertex Projection and Sorting on TrisoupPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
UnnoKyoheiFast Decision Method for Adaptive Motion Vector Resolution in Versatile Video Coding3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
UnnoKyoheiFast Decision Method for Merge with Motion Vector Difference in
Versatile Video Coding
3B: Video Coding (Best Paper Session VI)Jan 5 (Wed)1500-1630 hrs
UrakawaRyotaA Method of Composition Evaluation for PhotographsPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
UrumaKazunoriDepth image restoration algorithm using graph signal processing based image colorization6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
VienAn GiaLow-light Image Enhancement via Channel-wise Intensity Transformation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
WanShuaiGeometry Reconstruction for Spatial Scalability in Point Cloud Compression Based on Neighbour Occupancies6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
WangLi-WenRobust Lane Detection through Automatic Trajectory Analysis with Deep Learning and Big Data Environment7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
WangShaozhiMulti-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
WangXianglongCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
WangZhechengGeometry Reconstruction for Spatial Scalability in Point Cloud Compression Based on Neighbour Occupancies6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
WatanabeSotaDataset Generation with GAN for Reflection Image Removal on Eyeglasses7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
WatanabeYasuakiMixed Reality Visualization of Room Impulse Responses on Two Planes by Moving Microphone7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
WayDer-LorA Context-Aware Anchor-free Tiny Object Detector for Aerial Images5A: Image Processing and Classification IIJan 6 (Thu)1130-1300 hrs
WengJiahaoHierarchical Visual Interface for Educational Video Retrieval and Summarization3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
WooKin-SangAn indoor visual positioning system using points of interest detection for mobile robot application6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs
WuZhongkeeXpressive B-Spline Curves: a Pilot Study on a Flexible Shape Representation 1B: Computer Graphics and Virtual Reality (Best Paper Session II)Jan 5 (Wed)1100-1230 hrs
XiaoJunMulti-scale Feature Fusion Network for High Dynamic Range Imaging1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
XieC.Immersive 3D Flow Visualization Based on Enhanced Texture Convolution and Volume Rendering 7C: Immersive ApplicationsJan 6 (Thu)1530-1700 hrs
XieHaoranHierarchical Visual Interface for Educational Video Retrieval and Summarization3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
XieHaoranInteractive 3D Character Modeling from 2D Orthogonal Drawings with Annotations5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
XieHaoranInteractive Drawing Interface with 3D Animal Model Retrieval3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
XieHaoranSketch-based 3D Shape Modeling from Sparse Point Clouds3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
XieHaoranInteractive Shadow Generation System for Spatial Augmented Reality4C: VR and ARJan 6 (Thu)1000-1130 hrs
XieNingScale Adaptive Structure Tensor Based Rolling Trilateral Filter4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
YamajiYudaiOn the tolerance of CNN watermarking against model optimizationsPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
YamanakaTakeruFingerprint Minutiae Detection using Improved Tamura’s ThinningPoster IV: Image Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
YAMASAKIRikuA Frame-by-Frame Integrated Environment Map Building Method in Cooperative SLAM2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
YamazakiYukiRaden Code: A study of Matching Algorithm for Raden Based on Phase Information6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
YangXiHierarchical Visual Interface for Educational Video Retrieval and Summarization3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
YangXiSketch-based 3D Shape Modeling from Sparse Point Clouds3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
YangYangCalibration of multispectral photometric stereo point source based on standard block5C: 3D Processing and ApplicationsJan 6 (Thu)1130-1300 hrs
YangYutingApplication of GoogLeNet for Ocean-Front Tracking4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
YataNorikoA Study of Lightweighting Method Using Reinforcement Learning6C: Machine Learning and ApplicationsJan 6 (Thu)1400-1530 hrs
YataNorikoA study of Automatic generation of motif tag in Nishiki-ePoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
YataNorikoImproving the Accuracy of the Color Constancy Network by Object Detection5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
YataNorikoA Study of Multimodal Head and Gaze Orientation Prediction Techniques in Virtual Space4C: VR and ARJan 6 (Thu)1000-1130 hrs
YataNorikoA study of colored point cloud completion for a human head6A: Point Cloud Processing and ApplicationsJan 6 (Thu)1400-1530 hrs
YeQiuliangCoded Diffraction Pattern Phase Retrieval with Green Noise Masks4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
YeungChun-YinLDCCRN: Robust Deep Learning-based Speech EnhancementPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
YimJonghoonEnhancing Angular Resolution using Layers Obtained from Light Field Superpixel Segmentation1A Image Processing (Best Paper Session I)Jan 5 (Wed)1100-1230 hrs
YoonKyoungroCompression of Thermal Images for Machine Vision based on Objectness Measure2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
YoonYong-UkA method of feature map reordering for machine vision based on channel correlation2C: Video Coding for Machine (Special Session)Jan 5 (Wed)1330-1500 hrs
YoshidaShogoInteractive Shadow Generation System for Spatial Augmented Reality4C: VR and ARJan 6 (Thu)1000-1130 hrs
YoshidaToshiyukiCNN-based realization of Depth from Defocus technique7B: Deep Learning and Applications IIIJan 6 (Thu)1530-1700 hrs
YoshidaToshiyukiImprovement of Cell Image Analysis System based on CNNPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
YuHuiSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
YunZhichaoSaliency Detection Based on Center Prior and U-Net5B: Deep Learning and Applications IIJan 6 (Thu)1130-1300 hrs
ZhangChaoDiversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ZhangChaoTemplate Matching via Search History Driven Genetic Algorithm2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ZhangChaoHierarchical Visual Interface for Educational Video Retrieval and Summarization3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ZhangChaoMeasuring Speaking Time from Privacy-Preserving Videos3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ZhangJingAnomaly Object Detection in X-ray Images with Gabor Convolution and Bigger Discriminative RoI Pooling2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ZhangLeiGradient Centralization and Feature Gradient Decent for Deep Neural Network OptimizationKeynote 1Jan 5 (Wed)0920-1000 hrs
ZhangXiaohuaScale Adaptive Structure Tensor Based Rolling Trilateral Filter4A: Image Processing and Classification IJan 6 (Thu)1000-1130 hrs
ZhangYiAbnormal object detection in X-ray images with self-normalizing channel attention and efficient data augmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ZhangYutongAnomaly Object Detection in X-ray Images with Gabor Convolution and Bigger Discriminative RoI Pooling2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ZhangYutongAbnormal object detection in X-ray images with self-normalizing channel attention and efficient data augmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ZhaoQiluIVTEN: Integration of Visual-Textual Entities using Graphs for Temporal Activity Localization via Natural Language in Video7A: Video Processing and ApplicationsJan 6 (Thu)1530-1700 hrs
ZhaoShuofengDiversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder3C: Intelligent System Design (Special Session)Jan 5 (Wed)1500-1630 hrs
ZhouXiangrongDetection and classification of 32 tooth types in dental panoramic radiographs using single CNN model and post-processingPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
ZhouXiangrongClassification of Pancreatic Tumors using Colored Two-dimensional Histograms from Ultrasound Endoscopic ImagesPoster II: Multimedia Systems and Applications IIJan 6 (Thu)1130-1300 hrs
ZhouXiangrongAutomated Segmentation of Oblique Abdominal Muscle Based on Body Cavity Segmentation in Torso CT Images using U-NetPoster I: Deep Learning and Applications IJan 6 (Thu)1000-1130 hrs
ZhuoLiAnomaly Object Detection in X-ray Images with Gabor Convolution and Bigger Discriminative RoI Pooling2A: Computer Vision (Best Paper Session III)Jan 5 (Wed)1330-1500 hrs
ZhuoLiAbnormal object detection in X-ray images with self-normalizing channel attention and efficient data augmentation3A: Machine Learning (Best Paper Session V)Jan 5 (Wed)1500-1630 hrs
ZouYuxuanGabor’s two inventions6B: Image Understanding and RecognitionJan 6 (Thu)1400-1530 hrs