Image and Graphics 12th International Conference, ICIG 2023, Nanjing, China, September 22–24, 2023, Proceedings, Part IV

Artificial intelligence: Deep Discriminative Hashing for Cross-modal Hashing based Computer-aided Diagnosis.- Image Super-Resolution via Deep Dictionary Learning.- ACLM: Adaptive Compensatory Label Mining for Facial Expression Recognition.- Semantic-Guided Multi-Feature Fusion for Accurate Video Captioning.- Scale-Adaptive Multi-Area Representation for Instance Segmentation.- Multi-Level Semantic Extraction using Graph Pooling Network for Text Representation.- Research on Strategies for Tripeaks variant with various layouts.- A neural network model with the ringed residual block and attention mechanism for image forgery localization.- ACMA-GAN: Adaptive Cross-Modal Attention for Text-to-Image Generation.- Registration-propagated Liver Tumor Segmentation for  Non-enhanced CT-based Interventions.- FML-MIS: A Scheme of Privacy Protection and Model Generalization for Medical Images Segmentation via Federated Meta-learning.- RoICLIP: Text-Enhanced UAV-based Video Object Detection.- Class Incremental Learning with Important and Diverse Memory.- Core Issues and Key Arguments of ChatGPT: Topic Mining and Sentiment Analysis Based on U.S. News Reports.- Joint Memory Propagation and Rectification for Video Object Segmentation.- A noval intelligent assessment based on audio-visual data for Chinese zither fingerings.- A Full-level Based Network to Detect Every Aircraft in Airport Scene.- Fusing Multi-scale Residual Network for Skeleton Detection.- LogoNet: a fine-grained network for instance-level logo sketch retrieval.- NCCNet: Arbitrary Neural Style Transfer with Multi-Channel Conversion.- BRMR : TAL Based on Boundary Refinement and Multi-scale Regression.- AE-Reorient: Active Exploration based Reorientation for Robotic Pick-and-Place.- A novel contactless prediction algorithm of indoor thermal comfort based on posture estimation.- A real-time wind turbine blade damage detection method  based on an improved YOLOv5 algorithm.- Intensify Perception Transformer Generative Adversarial Network for Image Super-Resolution.- Referring Expression Comprehension Based on Cross Modal Feature Fusion and Iterative Reasoning.- ADS-B-based Spatial-Temporal multi-scale object detection network for airport scenes.- Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification.- Learning to Fuse Residual and Conditional Information for Video Compression and Reconstruction.- A two-stage 3D object detection algorithm based on deep learning.- Dual Temporal Memory Network for Video Salient Object Detection.- Cross-Modality Fused Graph Convolutional Network for Image-Text Sentiment Analysis.- Local and Global Feature Interaction Network for Endoscope Image classification.