Computer Vision, Theories and Applications -- Dynamic Fusion Network For Light Field Depth Estimation -- Metric Calibration of Aerial on-board Multiple Non-overlapping Cameras based on Visual and Inertial Measurement Data -- SEINet: Semantic-Edge Interaction Network for Image Manipulation Localization -- Video-Based Reconstruction of Smooth 3D Human Body Motion -- A Unified Modular Framework with Deep Graph Convolutional Networks for Multi-Label Image Recognition -- 3D Correspondence Grouping with Compatibility Features -- Contour-Aware Panoptic Segmentation Network -- VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-based Convolutional Autoencoder -- Slice Sequential Network: A Lightweight Unsupervised Point Cloud Completion Network -- From Digital Model to Reality Application: A Domain Adaptation Method for Rail Defect Detection -- FMixAugment for Semi-Supervised Learning with Consistency Regularization -- IDANet: Iterative D-LinkNets with Attention for Road Extraction from High-resolution Satellite Imagery -- Disentangling Deep Network for Reconstructing 3D Object Shapes from Single 2D Images -- AnchorConv: Anchor Convolution for Point Clouds Analysis -- IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition -- Immersive Traditional Chinese Portrait Painting: Research on Style Transfer and Face Replacement -- Multi-camera extrinsic auto-calibration using pedestrians in occluded environments -- Dual-Layer Barcodes -- Graph Matching based Robust Line Segment Correspondence for Active Camera Relocalization -- Unsupervised learning framework for 3D reconstruction from face sketch -- HEI-Human: A Hybrid Explicit and Implicit Method for Single-view 3D Clothed Human Reconstruction -- A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction -- 3D-SceneCaptioner: Visual Scene Captioning Network for Three-Dimensional Point Clouds -- Soccer Field Registration Based on Geometric Constraint and Deep Learning Method -- Enhancing Latent Features for Unsupervised Video Anomaly Detection -- Adaptive Anomaly Detection Network for Unseen Scene Without Fine-tuning -- Facial Expression Recognition Based on Multi-scale Feature Fusion Convolutional Neural Network and Attention Mechanism -- Separable Reversible Data Hiding based on Integer Mapping and Multi-MSB Prediction for Encrypted 3D Mesh Models -- MPN: Multi-Scale Progressive Restoration Network For Unsupervised Defect Detection -- Scene-Aware Ensemble Learning For Robust Crowd Counting -- Complementary Temporal Classification Activation Maps in Temporal Action Localization -- Improve Semantic Correspondence by Filtering the Correlation Scores in both Image Space and Hough Space -- A Simple Network with Progressive Structure for Salient Object Detection -- Feature Enhancement and Multi-Scale Cross-Modal Attention for RGB-D Salient Object Detection -- Improving Unsupervised Learning of Monocular Depth and Ego-motion via Stereo Network -- A non-autoregressivedecoding model based on joint classification for 3D human pose regression -- Multimedia Processing and Analysis -- Multiple Semantic Embedding with Graph Convolutional Networks for Multi-Label Image Classification -- AMEN: Adversarial Multi-Space Embedding Network for Text-based Person Re-identification -- AFM-RNN: A Sequent Prediction Model for Delineating Building Rooftops from Remote Sensing Images by Integrating RNN with Attraction Field Map -- Attribute-level Interest Matching Network for Personalized Recommendation -- Variational Deep Representation Learning for Cross-Modal Retrieval -- Vein Centerline Extraction of Visible images Based on Tracking Method -- Discrete Bidirectional Matrix Factorization Hashing for Zero-Shot Cross-Media Retrieval -- Dual Stream Fusion Network for Multi-spectral High Resolution Remote Sensing Image Segmentation -- Multi-scale Extracting and Second-order Statistics for Lightweight Steganalysis -- HTCN: Harmonious Text Colorization Network for Visual-Textual Presentation Design -- A Fast Method for Extracting parameters of Circular Objects -- GGRNet: Global Graph Reasoning Network for Salient Object Detection in Optical Remote Sensing Images -- A Combination Classifier of Polarimetric SAR image Based on D-S Evidence Theory -- Image Tampering Localization Using Unified Two-Stream Features Enhanced with Channel and Spatial Attention -- An End-to-End Mutual Enhancement Network toward Image Compression and Semantic Segmentation -- Deep Double Center Hashing for Face Image Retrieval -- A Novel Method of Cropped Images Forensics in Social Networks -- MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination.

The 4-volume set LNCS 13019, 13020, 13021 and 13022 constitutes the refereed proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2021, held in Beijing, China, in October-November 2021. The 201 full papers presented were carefully reviewed and selected from 513 submissions. The papers have been organized in the following topical sections: Object Detection, Tracking and Recognition; Computer Vision, Theories and Applications, Multimedia Processing and Analysis; Low-level Vision and Image Processing; Biomedical Image Processing and Analysis; Machine Learning, Neural Network and Deep Learning, and New Advances in Visual Perception and Understanding.