Computer Vision and Pattern Recognition: Adaptive Fine-Grained Region Matching for Image Harmonization -- Inscription-Image Inpainting with Edge Structure Reconstruction -- RatiO R-CNN: An Efficient and Accurate Detection Method for Oriented Object Detection -- Student Classroom Behavior Detection based on YOLOv7+BRA and Multi-Model Fusion -- Tiny-YOLOv7: Tiny Object Detection Model for Drone Imagery -- Revisiting TENT for Test-Time Adaption Semantic Segmentation and Classification Head Adjustment -- Single Image Dehazing with Deep-Image-Prior Networks -- Learning Sparse Neural Networks with Identity Layers -- Dense Small Object Detection based on Improved Deep Separable Convolution YOLOv5- A Multimodal Text Block Segmentation Framework for Photo Translation -- End-to-end Multilingual Text Recognition Based on Byte Modeling -- Disentangled Shape and Pose Based on Attention and Mesh Autoencoder -- Wavelet Knowledge Distillation via Decoupled Target for Scene Text Detection -- MGP-Net:Margin-Global information optimization-Prototype Network For few-shot Ancient Inscriptions Classification -- Structure-aware Point Cloud Completion -- Foreign Object Detection based on Compositional scene Modeling -- Computer Graphics and Visualization: Geometric Encoding-based Attention Mechanism for Point Cloud Registration Network -- End-to-end phase retrieval from single-shot fringe image for 3D face reconstruction -- Multi-modal Stream Fusion for Skeleton-Based Action Recognition -- 3D Object Recognition Based on Point Cloud Geometry Construction and Embeddable Attention -- The Research Landscape of Site-Specific Art in Public Art Map Quantification Based on Citespace -- Research on Emotional Classification and Literary Narrative Visualization Based on Graph Convolutional Neural Network -- Novel 3D model zero-watermarking using geometrical and statistical features -- Compression, Transmission, Retrieval: Edge-Guided Interpretable Neural Network for Image Compressive Sensing Reconstruction -- Patch-wise LiDAR Point Cloud Geometry Compression based on Autoencoder -- Astronomical Image Coding Based on Graph Fourier Transform -- A novel homogenized chaotic system compressed sensing image encryption algorithm -- Reversible data hiding in encrypted images based on quantization prediction error -- Improving Text Image Super-Resolution using Optimal Transport -- GAN-based Image Compression with Improved RDO Process -- Video Coding for Machines Based on Motion Assisted Saliency Analysis -- CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval -- Flexible Hierarchical Parallel Processing for AVS3 Video Coding -- Content-Adaptive Block Clustering for Improving VVC Adaptive Loop Filtering.

The five-volume set LNCS 14355, 14356, 14357, 14358 and 14359 constitutes the refereed proceedings of the 12th International Conference on Image and Graphics, ICIG 2023, held in Nanjing, China, during September 22-24, 2023. The 166 papers presented in the proceedings set were carefully reviewed and selected from 409 submissions. They were organized in topical sections as follows: computer vision and pattern recognition; computer graphics and visualization; compression, transmission, retrieval; artificial intelligence; biological and medical image processing; color and multispectral processing; computational imaging; multi-view and stereoscopic processing; multimedia security; surveillance and remote sensing, and virtual reality. The ICIG 2023 is a biennial conference that focuses on innovative technologies of image, video and graphics processing and fostering innovation, entrepreneurship, and networking. It will feature world-classplenary speakers, exhibits, and high-quality peer reviewed oral and poster presentations.