Digital Multimedia Communications [electronic resource] : 19th International Forum, IFTC 2022, Shanghai, China, December 8–9, 2022, Revised Selected Papers /

Computer Vision -- Pedestrian Re-recognition Based on Memory Network and Graph Structure -- Pedestrian Attribute Recognition Method Based on Multi-Source Teacher Model Fusion -- Dense 3D Reconstruction of Non-Cooperative Target Based on Pose Measurement -- River Turbidity Monitoring Based on Semi-Supervised Transfer Learning -- The Fusion Oil Leakage Detection Model for Substation Oil-Filled Equipment -- A Generic Image Feature Extraction Method Towards Multiple Vision Tasks -- Image Analysis -- A Lightweight Segmentation Network Based on Weak Supervision for COVID-19 Detection -- Bit-Depth Enhancement with Distortion Sensitivity -- Combining Transformer and Convolutional Neural Network for Smoke Detection -- Generative Model Watermarking Based on Human Visual System -- Feature Adaptation Predictive Coding for Quantized Block Compressive Sensing of COVID-19 X-Ray Images -- Deep FourierKernel Exploitation in Blind Image Super-Resolution -- Pyramid Channel Attention Combined Adaptive Multi-Column Network for SISR -- FPGA-Based Hardware Implementation of JPEG XS Encoder -- A Correction-Based Dynamic Enhancement Framework Towards Underwater Detection -- Water Segmentation via Asymmetric Multiscale Interaction Network -- Quality Assessment -- MSPP-IQA: Adaptive Blind Image Quality Assessment Based on Multi-Level Spatial Pyramid Pooling -- Subjective and Objective Emotional Consistency Assessment for UGC Short Videos -- Few-Reference Image Quality Assessment with Multiple Information Measurement Fusion -- L2RT-FIQA: Face Image Quality Assessment via Learning-to-Rank Transformer -- Blindly Evaluate the Quality of Underwater Images via Multi-Perceptual Properties -- Video Processing -- Adaptive Amplitude Modulation and Recovery Method for Video Coding -- Tracking of Aerial Cooperative Target by Satellite-Based Optical Cameras -- Regression Augmented Global Attention Network for Query-Focused Video Summarization -- Deep Video Matting with Temporal Consistency -- Deep Flow-Guided Video Dehazing Based on Multi-Scale Recurrent Network -- Fast Skip Inter Coding Decision Algorithm for VVC -- Machine Learning -- SMA-Net: Sobel Operator Combined with Multi-Attention Networks for COVID-19 Lesion Segmentation -- ViT-Siamese Cascade Network for Transmission Image Deduplication -- Adversarial Example Defense via Perturbation Grading Strategy -- Audio and Speech Processing -- Perceptual Quality Assessment of TTS-Synthesized Speech -- An Adaptive Musical Vibrotactile System (MuViT) for Modern Smartphones -- Big Data -- A Random Forest-Based Model for Fusion of Organization Master Data -- The Effects of Air Pollution and Meteorological Factors in the Transmission and Lethality of COVID-19 -- A Defect Detection Method for Small Fittings of Power Transmission Based on Improved SLIC -- Federated Learning for Industrial Entity Extraction -- Interactive Sharing Method of Power Grid Dispatching and Control Operation Data Based on Data Classification and Grading -- On the Robustness of “Robust Reversible Data Hiding Scheme Based on Two-Layer Embedding Strategy” -- Latent Energy Based Model with Classifier Guidance -- Evaluation Technology of Power Regulation Data Assets. .

This book constitutes the refereed proceedings of the 19th International Forum on Digital Multimedia Communication, IFTC 2022, held in Shanghai, China, December 8–9, 2022. The 40 full papers included in this book were carefully reviewed and selected from 112 submissions. They were organized in topical sections as follows: Computer Vision; Image Analysis; Quality Assessment; Video Processing; Machine Learning; and Big data.