Previous Research Topics

Title Interpretable (Explainable) Deep Learning
Content ¤ýXCAD (Explainable Computer Aided Diagnosis)
¤ýInvestigating Interpretability of Deep Networks
Title Deep learning object detection/recognition
Content ¤ýVisual Question Answering using Adaptive Attention Fusion Network
¤ýMedical Image Segmentation by using Iterative Deep Encoder-Decoder Network
¤ýSpatial-temporal Deep Feature Representation
¤ýMultiple Input Space Learning
¤ýDeep learning Landmark Detection
¤ýTwo-step Learning of Deep Convolutional Neural Network for Discriminative Face Recognition under Varying Illumination
¤ýLearning based hole filling method using deep convolutional neural network for view synthesis
¤ýLatent Feature Representation With 3-d Multi-view Deep Convolutional Neural Network for Bilateral Analysis In Digital Breast Tomosynthesis
¤ýPose-robust and Discriminative Feature Representation by Multi-task Deep Learning for Multi-view Face Recognition
Title Free view - 3D view/video generation
Content ¤ýVisual Quality Assessment of Synthesized 3D video for Free-viewpoint TV
¤ýRecent Result for 3D Free view generation for in IVY Lab(2015)
¤ýFast Temporally Consistent 3D Video Generation for 3D Video Contents
¤ýMulti-view 3D Video Synthesis with Spatio-Temporal Consistency and Binocular Symmetry for Free-viewpoint TV
¤ý3D Geometric Transformation based View Synthesis for Wide Angle View
Title Visual Recognition
Content ¤ýIntra-Class Variation Reduction for Subject Independent Facial Expression Recognition Collaborative Face Recognition in Social Network Site (SNS)
¤ýVideo Face Recognition for Surveillance System
¤ýFace Detection for Low Power Event Detection in Surveillance System
¤ýVideo Face Recognition for Surveillance System
¤ýFacial Emotion Recognition Using Color Texture Sparsity
¤ýFacial Age Classification for Unconstrained Face Images
¤ýLicense Plate Detection and Recognition for Degraded Surveillance Videos
¤ýImage Matching and Annotation Using Folksonomy
Title 3D image/video processing
Content ¤ýAttention model-based visual comfort assessment for stereoscopic 3D videos
¤ýPsychological vision experiments for visual discomfort measurement in stereoscopic displays
¤ýStereoscopic 3D quality analyzer and advanced depth control in stereoscopic displays
¤ýStereoscopic video analyzer, stereo video capture system
¤ýVisual comfort amelioration for 3D image/video
¤ýDisparity estimation, 3D image/video rendering, TOF depth camera fusion
Title Medical image processing (CAD: computer aided detection and diagnosis)
Content ¤ýDeep Learning- Automatic Malignancy Detection
¤ýImage enhancement
¤ýSuspicious region (mass and microcalcification) segmentation
¤ýDevelopment of multiresolution local texture features for mass classification
¤ýBoosting based Ensemble classifier modeling(design)
¤ýMammography Computer Aided Detection (CAD)
¤ýConspicuity-improved Synthetic Image generation for Digital Breast Tomosynthesis (DBT)
¤ýMicrocalcification enhancement for detection in DBT projection views
¤ýFeature extraction of DBT projection views
¤ýDBT Computer Aided Detection (CAD)
Title Color Face Recognition
Content ¤ýColor Face Recognition Algorithms for Low-resolution faces
¤ýInvestigation of Mismatch Effects on Color Face Recognition Algorithms
¤ýColor Face Recognition Algorithms Using Feature Selection
¤ýDevelopment of Color Local Texture Features for Color Face Recognition
Title Digital Broadcasting
Content ¤ýMobile MPEG-7 Application System
¤ýSemantic based Video Summary
¤ýMPEG-21 based Digital Broadcasting Contents
Title Content adaptation
Content ¤ýColor Adaptation
¤ýModality Conversion Preference And QoS
Title Video Near Duplication Detection
Content ¤ýRealtime near copy detection
¤ýSemantic video signature
¤ýHigh performance near copy detection of video
Title Biometric Data Processing
Content ¤ýBiometric based authentication system
¤ýPrivacy preservation of biometric data template
Title Face Indexing and Search in Multimedia Contents
Content ¤ýFace Annotation in Personal Photos by Leveraging Context to Face Recognition
¤ýCollaborative Face Recognition in Online Social Networks
¤ýFace Indexing and Search in Personal Videos using Fusion of Multiple Face observations
¤ýFace indexing Toward IPTV services
¤ýFace indexing Toward IPTV services
Title Ubiquitous Multimedia Processing
Content ¤ýUbiquitous Watermarking
¤ýActive Media
Title Media Transcoding
Content ¤ýRelated contents
Title Semantic based Video Analysis
Content ¤ýSemantic video categorization
¤ýSemantic concept detection using collective knowledge
¤ýVideo copy detection using semantic signature
Title Privacy Protection
Content ¤ýPrivacy protection in video content
¤ýVideo scrambling techniques
¤ýPersonal information based content sharing
Title Medical Imaging
Content ¤ýComputer Aided Diagnosis(CAD)
¤ýInternet Adaptation Tools for Color Deficiency
Title Image and Video Processing
Content ¤ýCompressed Domain Video Processing
¤ýImage / Video contents Indexing and retrieval
Title Multimedia Communication
Content ¤ýRelated Contents
Title Matching Pursuit Image/Video Coding
Content ¤ýLow Bit Rate Coding
¤ýAdaptive Coding in MRI
¤ýMotion Suppression by localization using wavelet transform
Title 3D video, Image Reconstruction and Enhancement
Content ¤ýPhase dependent contrast Enhancement
¤ýWindowed Fourier Transform Reconstruction
¤ýAdaptive Image Reconstruction
Title Functional Imaging
Content ¤ýWavelet based functional signal anaysis
¤ýTailored RF pulsing to enhance susceptibility effect in functional imaging