Read more
This book constitutes the refereed proceedings of the 20th International Forum on Digital Multimedia Communication, IFTC 2023, held in Beijing, China, December 21-22, 2023.
The 57 full papers included in this book were carefully reviewed and selected from 150 submissions. They were organized in topical sections as follows:
CCIS 2066: Image Processing, Media Computing, Metaverse and Virtual Reality, and Multimedia Communication.
CCIS 2067: Quality Assessment, Source Coding, and Application of AI.
List of contents
.- Image Processing.
.- AquaSAM: Underwater Image Foreground Segmentation.
.- RAUNE-Net: A Residual and Attention-Driven Underwater Image Enhancement Method.
.- Depth Map Super-Resolution via Asymmetrically Guided Feature Selection and Spatial Affine Transformation.
.- Welding Defect Detection Using X-ray Images Based on Deep Segmentation Network.
.- Wide Activation Fourier Channel Attention Network for Super-Resolution.
.- LightNet+: Boosted Light-weighted Network for Smoke Semantic Segmentation.
.- Local Dynamic Filter Network for Low-Light Enhancement and Deblurring.
.- Spatial-Angular Decoupling Interaction Networks for Light Field Angular Super-Resolution.
.- Coding Prior-Driven JPEG Image Artifact Removal.
.- Media Computing.
.- Where to Forget: A New Attention Stability Metric for Continual Learning Evaluation.
.- Unbiased Image Caption Generation Based on Dynamic Counterfactual Inference.
.- Modeling and Analysis of Rumor Propagation Dynamics in Social Media.
.- Bridging Recommendations Across Domains: An Overview of Cross-Domain Recommendation.
.- Sequence Modeling Based Data Augmentation for Micro-Expression Recognition.
.- Dual Transformer with Gated-Attention Fusion for News Disaster Image Captioning.
.- Constructing Personal Knowledge Graph from Conversation via Deep Reinforcement Learning.
.- Exploring the Efficacy of Interactive Digital Humans in Cultural Communication.
.- Metaverse and Virtual Reality.
.- EHA3D: Expressive Head Avatar via Disentangled Latent Code.
.- Motion-Aware Topology Learning for Skeleton-Based Action Recognition.
.- MFNCA: Multi-level Fusion Network Based on Cross Attention for 3D Point Cloud Object Detection.
.- ART-InvRec: Acquiring Rotation Invariance of 3D Object Reconstruction via Adversarial Rotation.
.- Multi-View Object Classification Based on Deep Models.
.- Combined Particle Filter and Its Application on Human Pose Estimation.
.- A Human Posture Estimation Method for Image Interaction System Based on ECA.
.- PU-SSIM: A Perceptual Constraint for Point Cloud Up-Sampling.
.- Quality Enhancement via Spatial-Angular Deformable Convolution for Compressed Light Field.
.- Multimedia Communication.
.- Link-Breakage Recovery Strategies for Tactical MANET Based on OLSR.
.- Design of Distributed Synchronization Header for Short Burst Communication with Low Earth Orbit Satellites.
.- User Preferences Based Preloading and ABR Algorithm for Short Video Streaming.
