MultiMedia Modeling

Audio and Signal Processing.- Light Field Reconstruction using Dynamically Generated Filters.- Speaker-Aware Speech Emotion Recognition by Fusing Amplitude and Phase Information.- Gen-Res-Net: a Novel Generative Model for Singing Voice Separation.- A Distinct Synthesizer Convolutional TasNet for Singing Voice Separation.- Exploiting the Importance of Personalization When Selecting Music for Relaxation.- Coding and HVS.- An Efficient Encoding Method for Video Compositing in HEVC.- VHS to HDTV Video Translation using Multi-task Adversarial Learning.- Improving Just Noticeable Difference Model by Leveraging Temporal HVS Perception Characteristics.- Down-Sampling Based Video Coding with Degradation-aware Restoration-Reconstruction Deep Neural Network.- Beyond Literal Visual Modeling: Understanding Image Metaphor based on Literal-Implied Concept Mapping.- Color Processing and Art.- Deep Palette-based Color Decomposition for Image Recoloring with Aesthetic Suggestion.- On Creating Multimedia Interfaces for Hybrid Biological-Digital Art Installations.- Image Captioning based on Visual and Semantic Attention.- An Illumination Insensitive and Structure-aware Image Color Layer Decomposition Method.- CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator.- Detection and Classification.- Multi-Condition Place Generator for Robust Place Recognition.- Guided Refine-Head for Object Detection.- Towards Accurate Panel Detection in Manga: A Combined Effort of CNN and Heuristics.- Subclass Deep Neural Networks: Re-enabling Neglected Classes in Deep Network Training for Multimedia Classification.- Automatic Material Classification using Thermal Finger Impression.- Face.- Face Attributes Recognition Based on One-way Inferential Correlation between Attributes.- Eulerian Motion Based 3DCNN Architecture for Facial Micro-expression Recognition.- Emotion Recognition with Facial Landmark Heatmaps.- One-shot Face Recognition with Feature Rectification via Adversarial Learning.- Visual Sentiment Analysis by Leveraging Local Regions and Human Faces.- Image Processing.- Prediction-error Value Ordering for High-fidelity Reversible Data Hiding.- Classroom Attention Analysis Based on Multiple Euler Angles Constraint and Head Pose Estimation.- Multi-branch Body Region Alignment Network for Person Re-Identification.- DeepStroke: Understanding Glyph Structure with Semantic Segmentation and Tabu Search.- 3D Spatial Coverage Measurement of Aerial Images.- Learning and Knowledge Representation.- Instance Image Retrieval with Generative Adversarial Training.- An Effective Way to Boost Black-box Adversarial Attack.- Crowd Knowledge Enhanced Multimodal Conversational Assistant in Travel Domain.- Improved Model Structure with Cosine Margin OIM Loss For End-to-End Person Search.- Effective Barcode Hunter via Semantic Segmentation in the Wild.- Video Processing.- Wonderful Clips of Playing Basketball: A Database forLocalizing Wonderful Actions.- Structural Pyramid Network for Cascaded Optical Flow Estimation.- Real-time Multiple Pedestrians Tracking in Multi-camera System.- Learning Multi-feature based Spatially Regularized and Scale Adaptive Correlation Filters for Visual Tracking.- Unsupervised Video Summarization via Attention-Driven Adversarial Learning.- Poster Papers.- Efficient HEVC Downscale Transcoding Based on Coding Unit Information Mapping.- Fine-grain level sports video search engine.- The Korean Sign Language Dataset for Action Recognition.- SEE-LPR: A Semantic Segmentation based End-to-End System for Unconstrained License Plate Detection and Recognition.- Action Co-Localization in an Untrimmed Video by Graph Neural Networks.- A Novel Attention Enhanced Dense Network For Image Super-Resolution.- Marine Biometric Recognition Algorithm Based on YOLOv3-GAN Network.- Multi-scale Spatial Location Preference for Semantic Segmentation.- HRTF Representation with Convolutional Auto-Encoder.- Unsupervised Feature Propagation for Video Object Detection using Generative Adversarial Networks.- OmniEyes: Analysis and Synthesis of Artistically Painted Eyes.- LDSNE: Learning Structural Network Embeddings by Encoding Local Distances.- FurcaNeXt: End-to-End Monaural Speech Separation with Dynamic Gated Dilated Temporal Convolutional Networks.- Multi-step Coding Structure of Spatial Audio Object Coding.- Thermal Face Recognition based on Transformation by Residual U-Net and Pixel Shuffle Upsampling.- K-SVD Based Point Cloud Coding for RGB-D Video Compression Using 3D Super-point Clustering.- Resolution Booster: Global Structure Preserving Stitching Method For Ultra-High Resolution Image Translation.- Cross Fusion for Egocentric Interactive Action Recognition.- Improving Brain Tumor Segmentation with Dilated Pseudo-3D Convolution and Multi-direction Fusion.- Texture-based Fast CU Size Decision and Intra Mode Decision Algorithm for VVC.- An Efficient Hierarchical Near-Duplicate Video Detection Algorithm Based on Deep Semantic Features.- Meta Transfer Learning for Adaptive Vehicle Tracking in UAV Videos.- Adversarial Query-by-Image Video Retrieval Based on Attention Mechanism.- Joint Sketch-Attribute Learning for Fine-Grained Face Synthesis.- High Accuracy Perceptual video hashing via Low-Rank decomposition and DWT.- HMM-Based Person Re-Identification in Large-scale Open Scenario.- No Reference Image Quality Assessment by Information Decomposition.