Digital Multimedia Communications

This volume contains 27 selected papers presented at IFTC 2024: 21st International Forum of Digital Multimedia Communication, held in Lingshui, Hainan, China, on November 28-29, 2024.

The 55 full papers included in this 2-volume set were carefully reviewed and selected from 146 submissions. They were organized in topical sections as follows:

CCIS 2441: Affective Computing, Graphics & Image Processing for Virtual Reality, Large Language Models, Multimedia Communication, Application of Deep Learning and Video Analysis.

CCIS 2442: Human and Interactive Media, Image Processing, Quality Assessment and Source Coding.

Rotation-Equivariant Human Motion Prediction via Quaternion Graph Convolutional Network. - HomeArena: A Playground for Household Appliance Intelligence Development and Evaluation. - Virtual Digital Intelligence in Broadcasting Television and Online Audiovisual Fields: Applications and Risks. - Research on Cross-Modal Recommendation System Based on Deep Neural Network. - MIMCN: Multi-Interest Modeling with Capsule Network for News Recommendation. - FastTalker: Co-Speech Gesture Generation via Fast-Order Diffusion ODE Solver. - Multiplayer Interaction Feature Extraction for Skeleton-Based Action Recognition. - Bidirectional Information Fusion Time Series Transformer for Telecom Fraud Detection. - SSSGT: Silent Spiral Sparse Graph Transformer for Social Bots. - USIAL-VC: A One-Shot Voice Conversion by U-Net-Based Encoder and Speaker Identity Adaptive Learning. - PolyMotion-7K: A Multimodal-Driven Polyglot Avatar Motion Dataset. - MGTR-Avatar: Multi-Scale Gaussian Triplane Representation for High-Fidelity 3D Facial Model Reconstruction from a Monocular Video. - Learning Subimage-Adaptive Convolution Block for Real-Time Single Image Super-Resolution. - Light Field Image Super-Resolution Network Based on Attention Mechanism. - A Quantitative Method for Visual Appearance Recognition of Swollen Eyes Based on 3D Information of Eye-Related Key Points. - Siamese Dual-Stage Network with Hierarchical Fusion for Remote Sensing Image Dehazing. - CS2DMNet: Color Space Feature Interaction and Dual-Domain Multi-Scale Collaboration Network for Low-Light Image Enhancement. - A Near-Infrared Vein Image Semantic Segmentation and Localization
Method Based on Dual-Branch Information Fusion. - Remote Photoplethysmography Signal Measurement from Facial Videos Based on Enhanced Hybrid Convolutional Neural Network with Waveform Consistency Loss Function. - Lightweight Spatio-Temporal Attention Network for Video
Super-Resolution. - Video QoE Modeling by Spatial-Temporal Resolutions. - An End-to-End Full-Reference and No-Reference Quality Assessment Model for 360° VR Videos. - Do High Metrics Equal Enhanced Cognitive Performance? Exploring Objective and Subjective Assessments in Digital Human Quality. - Quality Assessment Indicators and Method of High-Resolution Space-Borne SAR Systems. - Objective Evaluation of Ambisonics Recording Performance Using Arbitrary Microphone Arrays. - Frame-Level Complexity Control for Practical Encoder x265. - A Human-Computer-Friendly Scalable Image Coding Scheme Based on the Canny Edge Detection Algorithm.