MultiMedia Modeling

Poster Papers.- Multi-Scale Comparison Network for Few-Shot Learning.- Semantic and Morphological Information guided Chinese Text Classification.- A Delay-aware Adaptation Framework for Cloud Gaming under the Computation Constraint of User Devices.- Efficient Edge Caching for High-Quality 360-Degree Video Delivery.- Inferring Emphasis for Real Voice Data: an Attentive Multimodal Neural Network Approach.- PRIME: Block-wise Missingness Handling for Multi-modalities in Intelligent Tutoring Systems.- A New Local Transformation Module for Few-shot Segmentation.- Background Segmentation for Vehicle Re-Identification.- Face Tells Detailed Expression: Generating Comprehensive Facial Expression Sentence through Facial Action Units.- A Deep Convolutional Deblurring and Detection Neural Network for Localizing Text in Videos.- Generate images with obfuscated attributes for private image classifcation.- Context-Aware Residual Network with Promotion Gates for Single Image Super-Resolution.- A Compact Deep Neural Network for Single Image Super-Resolution.- An Efficient Algorithm of Facial Expression Recognition by TSG-RNN Network.- Structured Neural Motifs: Scene Graph Parsing via Enhanced Context.- Perceptual Localization of Virtual Sound Source Based on Loudspeaker Triplet.- TK-Text: Multi-shaped Scene Text Detection via Instance Segmentation.- More-Natural Mimetic Words Generation for Fine-grained Gait Description.- Lite Hourglass Network for Multi-person Pose Estimation.- SS1: AI-Powered 3D Vision.- Single View Depth Estimation via Dense Convolution Network with Self-supervision.- Multi-Data UAV Images for Large Scale Reconstruction of Buildings.- Deformed Phase Prediction Using SVM for Structured Light Depth Generation.- Extraction of Multi-class Multi-instance Geometric Primitives from Point Clouds Using Energy Minimization.- Similarity Graph Convolutional Construction Network for Interactive Action Recognition.- Content-Aware Cubemap Projection for Panoramic Image via Deep Q-Learning.- Robust RGB-D Data Registration Based on Correntropy and Bi-directional Distance.- InSphereNet: a Concise Representation and Classification Method for 3D Object.- 3-D Oral Shape Retrieval Using Registration Algorithm.- Face Super-Resolution by Learning Multi-view Texture Compensation.- Light Field Salient Object Detection via Hybrid Priors.- SS2: Multimedia Analytics: Perspectives, Tools and Applications.- Multimedia Analytics Challenges and Opportunities for Creating Interactive Radio Content.- Interactive Search and Exploration in Discussion Forums Using Multimodal Embeddings.- An inverse mapping with manifold alignment for zero-shot learning.- Baseline Analysis of a Conventional and Virtual Reality Lifelog Retrieval System.- An Extensible Framework for Interactive Real-time Visualizations of Large-scale Heterogeneous Multimedia Information from Online Sources.- SS3: MDRE: Multimedia Datasets for Repeatable Experimentation.- GLENDA: Gynecologic Laparoscopy Endometriosis Dataset.- Kvasir-SEG: A Segmented Polyp Dataset.- Rethinking the Test Collection Methodology for Personal Self-Tracking Data.- Experiences and Insights from the Collection of a Novel Multimedia EEG Dataset.- SS4: MMAC: Multi-Modal Affective Computing of Large-Scale Multimedia Data.- Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection.- Enhanced Gaze Following via Object Detection and Human Pose Estimation.- Region Based Adversarial Synthesis of Facial Action Units.- Facial Expression Restoration Based on Improved Graph Convolutional Networks.- Global Affective Video Content Regression Based on Complementary Audio-Visual Features.- SS5: MULTIMED: Multimedia and Multimodal Analytics in the Medical Domain and Pervasive Environments.- Using Publicly Available Medical Images from the Open Access Literature and Social Networks for Model Training and Knowledge Extraction.- AttenNet: Deep Attention based Retinal Disease Classification in OCT Images.- NOVA: A Tool for Explanatory Multimodal Behavior Analysis and its Application to Psychotherapy.- Instrument Recognition in Laparoscopy for Technical Skill Assessment.- Real-time Recognition of Daily Actions Based on 3D Joint Movements and Fisher Encoding.- Model-based and Class-based Fusion of Multisensor Data.- Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos.- SS6: Intelligent Multimedia Security.- Compact Position-aware Attention Network for Image Semantic Segmentation.- Law is Order: Protecting Multimedia Network Transmission by Game Theory and Mechanism Design.- Rational Delegation Computing Using Information Theory and Game Theory Approach.- Multi-hop Interactive Cross-modal Retrieval.- Demo Papers.- Browsing Visual Sentiment Datasets using Psycholinguistic Groundings.- Framework Design for Multiplayer Motion Sensing Game in Mixture Reality.- Lyrics-Conditioned Neural Melody Generation.- A Web-based Visualization Tool for 3D Spatial Coverage Measurement of Aerial Images.- An Attention Based Speaker-Independent Audio-Visual Deep Learning Model for Speech Enhancement.- DIME: An Online Tool for the Visual Comparison of Cross-Modal Retrieval Models.- Real-time Demonstration of Personal Audio and 3D Audio Rendering Using Line Array Systems.- CNN-based Multi-Scale Super-Resolution Architecture on FPGA for 4K/8K UHD Applications.- Effective Utilization of Hybrid Residual Modules in Deep Neural Networks for Super Resolution.- VBS Papers.- diveXplore 4.0: The ITEC Deep Interactive Video Exploration System at VBS2020.- Combining Boolean and Multimedia Retrieval in vitrivr for Large-Scale Video Search.- An Interactive Video Search Platform for Multi-modal Retrieval with Advanced Concepts.- VIREO @ Video Browser Showdown 2020.- VERGE in VBS 2020.- VIRET at Video Browser Showdown 2020.- SOM-Hunter: Video Browsing with Relevance-to-SOM Feedback Loop.- Exquisitor at the Video Browser Showdown 2020.- Deep Learning-Based Video Retrieval using Object Relationships and Associated Audio Classes.- IVIST: Interactive Video Search Tool in VBS 2020.