Pattern Recognition and Computer Vision: 5th Chinese Conference, Prcv 2022, Shenzhen, China, November 4-7, 2022, Proceedings, Part II

ISBN-13: 9783031189098 / Angielski / Miękka / 2022 / 723 str.

Shiqi Yu; Zhaoxiang Zhang; Pong C. Yuen

Opis

The 4-volume set LNCS 13534, 13535, 13536 and 13537 constitutes the refereed proceedings of the 5th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2022, held in Shenzhen, China, in November 2022.

The 233 full papers presented were carefully reviewed and selected from 564 submissions. The papers have been organized in the following topical sections: Theories and Feature Extraction; Machine learning, Multimedia and Multimodal; Optimization and Neural Network and Deep Learning; Biomedical Image Processing and Analysis; Pattern Classification and Clustering; 3D Computer Vision and Reconstruction, Robots and Autonomous Driving; Recognition, Remote Sensing; Vision Analysis and Understanding; Image Processing and Low-level Vision; Object Detection, Segmentation and Tracking.

Spis treści

​Biomedical Image Processing and Analysis.- ED-AnoNet: Elastic Distortion-Based Unsupervised Network for OCT Image Anomaly Detection.- BiDFNet: Bi-decoder and Feedback Network for Automatic Polyp Segmentation with Vision Transformers.- FundusGAN: A One-Stage Single Input GAN for Fundus Synthesis.- DIT-NET: Joint Deformable Network and Intra-class Transfer GAN for cross-domain 3D Neonatal Brain MRI segmentation.- Classification of sMRI Images for Alzheimer's Disease by Using Neural Networks.- Semi-Supervised Distillation Learning Based on Swin Transformer for MRI Reconstruction.- Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification.- Automatic glottis segmentation method based on lightweight U-net.- Decouple U-Net: A Method for the Segmentation and Counting of Macrophages in Whole Slide Imaging.- A Zero-training Method for RSVP-based Brain Computer Interface.- An improved tensor network for image classification in histopathology.- DeepEnReg: Joint Enhancement and Ane Registration for Low-contrast Medical Images.- Fluorescence Microscopy Images Segmentation based on Prototypical Networks with a few Annotations.- SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image.- Cascade Multiscale Swin-Conv Network for Fast MRI Reconstruction.- DEST: Deep Enhanced Swin Transformer toward Better Scoring for NAFLD.- CTCNet: A Bi-directional Cascaded Segmentation Network Combining Transformers with CNNs for Skin Lesions.- MR Image Denoising Based On Improved Multipath Matching Pursuit Algorithm.- Statistical characteristics of 3-D PET imaging: a comparison between conventional and total-body PET scanners.- Unsupervised medical image registration based on multi-scale cascade network.- A Novel Local-global Spatial Attention Network for Cortical Cataract Classification in AS-OCT.- PRGAN: A Progressive Refined GAN for Lesion Localization and Segmentation on High-Resolution Retinal fundus Photography.- Multiscale Autoencoder with Structural-Functional Attention Network for Alzheimer's Disease Prediction.- Robust Liver Segmentation Using Boundary Preserving Dual Attention Network.- msFormer: Adaptive Multi-Modality 3D Transformer for Medical Image Segmentation.- Semi-supervised Medical Image Segmentation with Semantic Distance Distribution Consistency Learning.- MultiGAN: multi-domain image translation from OCT to OCTA_ TransPND: A Transformer based Pulmonary Nodule Diagnosis Method on CT Image.- Adversarial Learning Based Structural Brain-network Generative Model for Analyzing Mild Cognitive Impairment.- A 2.5D Coarse-to-fine Framework for 3D Cardiac CT View Planning.- Weakly Supervised Semantic Segmentation of Echocardiography Videos

via Multi-level Features Selection.- DPformer: Dual-path transformers for geometric and appearance

features reasoning in diabetic retinopathy grading.- Deep Supervoxel Mapping Learning for Dense Correspondence of Cone-Beam Computed Tomography.- Manifold-Driven and Feature Replay Lifelong Representation Learning on Person ReID.- Multi-source information-shared domain adaptation for EEG emotion recognition.- Spatial-Channel Mixed Attention based Network for Remote Heart Rate Estimation.- Weighted Graph Based Feature Representation for Finger-Vein Recognition.- Self-Supervised Face Anti-Spoofng via Anti-Contrastive Learning.- Counterfactual Image Enhancement for Explanation of Face Swap Deepfakes.- Improving Pre-trained Masked Autoencoder with Locality Enhancement for Person Re-identification.- MINIPI : a MultI-scale Neural network based impulse radio ultra-wideband radar Indoor Personnel Identification method.- PSU-Net: Paired Spatial U-Net for hand segmentation with complex  backgrounds.- Pattern Classification and Clustering.- Human Knowledge-Guided and Task-Augmented Deep Learning for Glioma Grading.- Learning to Cluster Faces with Mixed Face Quality.- Capturing Prior Knowledge in Soft Labels for Classification with Limited or Imbalanced Data.- Coupled Learning for Kernel Representation and Graph Tensor in Multi-view Subspace Clustering.- Combating Noisy Labels via Contrastive Learning with Challenging Pairs.- Semantic Center Guided Windows Attention Fusion Framework for Food Recognition.- Adversarial Bidirectional Feature Generation for Generalized Zero-Shot Learning under Unreliable Semantics.- Exploiting Robust Memory Features for Unsupervised Reidentification.- TIR: A Two-stage Insect Recognition method for convolutional neural network.- Discerning Coteaching: A Deep Framework for Automatic Identification of Noise Labels.- VDSSA: Ventral & Dorsal Sequential Self-attention AutoEncoder for Cognitive-Consistency Disentanglement.- Bayesian Neural Networks with Covariate Shift Correction for Classification in -ray Astrophysics.