Pattern Recognition and Computer Vision 7th Chinese Conference, PRCV 2024, Urumqi, China, October 18–20, 2024, Proceedings, Part IV

This 15-volume set LNCS 15031-15045 constitutes the refereed proceedings of the 7th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2024, held in Urumqi, China, during October 18–20, 2024.
The 579 full papers presented were carefully reviewed and selected from 1526 submissions. The papers cover various topics in the broad areas of pattern recognition and computer vision, including machine learning, pattern classification and cluster analysis, neural network and deep learning, low-level vision and image processing, object detection and recognition, 3D vision and reconstruction, action recognition, video analysis and understanding, document analysis and recognition, biometrics, medical image analysis, and various applications.

Contextual Feature-Based Medical Visual Question Answering Aided by Learnable Matrix.- ImgQuant: Towards adversarial defense with robust boundary via dual-image quantization.- Swelling-ViT: Rethink Data-efficient Vision Transformer from Locality.- Target-Specific Domain Adaptation via Geometry-Correlation Prediction for Point Cloud.- Dual-stream Network of Vision Mamba and CNN with Auto-scaling for Remote Sensing Image Segmentation.- PRM: A Pixel-Region-Matching Approach for Fast Video Object Segmentation.- A Novel Combined GAN for Defects Generation using Masking Mechanisms.- Semi-supervised lightweight fabric defect detection.- Semi-adaptive Synergetic Two-way Pseudoinverse Learning System.- Invariant Risk Minimization Augmentation for Graph Contrastive Learning.- Enhancing Fast Adversarial Training with Learnable Adversarial Perturbations.- DTAFORMER: Directional Time Attention Transformer For Long-Term Series Forecasting.- Unpaired Multi-scenario Sketch Synthesis via Texture Enhancement.- ISO-VTON: Fine-Grained Style-Local Flows with Dual Cross-Attention for Immersive Outfitting.- Near-surface Air Temperature Inversion Study Based on U-Net Family with Multi-source Data.- Relation Detection with Transformers for Panoptic Scene Graph Generation.- WEDNet: A Wavelet Enhanced Detail Network for Low-Light Image Enhancement.- Textureness-Aware Neural Network for Edge Detection.- Enhancing the Transferability and Stealth of Deepfake Detection Attacks Through Latent Diffusion Models.- Backdoor Richer Watermarks using Dynamic Mask Covering for Dual Identity Verification.- Pedestrian Trajectory Prediction using Spatio-Temporal VAE.- Real-Time DEtection TRansformer with Bi-Level Routing Attention.- NFP-UNet: Deep Learning Estimation of Placeable Areas for 2D Irregular Packing.- Advancements in Photorealistic Style Translation with a Hybrid  Generative Adversarial Network.- Transformer Image Quality Assessment Based on Multi-Directional Feature Extraction.- MRGAN: LightWeight Monaural Speech Enhancement using GAN Network.- Data augmentation guided Decouple Knowledge Distillation for low-resolution fine-grained image classification.- GAN-Diffusion Relay Model: Advancing Semantic Image Synthesis.- Virtual Student Distribution Knowledge Distillation for Long-tailed Recognition.- Open-Vocabulary Instance Segmentation-Boundary IS-Goal.- 3DLaneFormer: End-to-End 3D Lane Detection with Voxel Descriptors.- More Like Real World Game Challenge for Partially Observable Multi-Agent Cooperation.- Centroid-centered Modeling for Efficient Vision Transformer Pre-training.- Spectral–Spatial Blockwise Masked Transformer With Contrastive Multi-View Learning for Hyperspectral Image Classification.- Local reactivation for communication efficient federated learning based on sparse gradient deviation.