Pattern Recognition and Computer Vision : 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13–15, 2023, Proceedings, Part III / edited by Qingshan Liu, Hanzi Wang, Zhanyu Ma, Weishi Zheng, Hongbin Zha, Xilin Chen, Liang Wang, Rongrong Ji.

Format:

Book

Contributor:

Liu, Qingshan, Editor.

Wang, Hanzi., Editor.

Ma, Zhanyu., Editor.

Zheng, Weishi., Editor.

Zha, Hongbin, Editor.

Chen, Xilin, Editor.

Wang, Liang, Editor.

Ji, Rongrong, Editor.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 14427

Language:

English

Subjects (All):

Image processing--Digital techniques.

Image processing.

Computer vision.

Artificial intelligence.

Application software.

Computer networks.

Computer systems.

Machine learning.

Computer Imaging, Vision, Pattern Recognition and Graphics.

Artificial Intelligence.

Computer and Information Systems Applications.

Computer Communication Networks.

Computer System Implementation.

Machine Learning.

Local Subjects:

Computer Imaging, Vision, Pattern Recognition and Graphics.

Artificial Intelligence.

Computer and Information Systems Applications.

Computer Communication Networks.

Computer System Implementation.

Machine Learning.

Physical Description:

1 online resource (XIV, 521 p. 179 illus., 174 illus. in color.)

Edition:

1st ed. 2024.

Place of Publication:

Singapore : Springer Nature Singapore : Imprint: Springer, 2024.

Summary:

The 13-volume set LNCS 14425-14437 constitutes the refereed proceedings of the 6th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2023, held in Xiamen, China, during October 13–15, 2023. The 532 full papers presented in these volumes were selected from 1420 submissions. The papers have been organized in the following topical sections: Action Recognition, Multi-Modal Information Processing, 3D Vision and Reconstruction, Character Recognition, Fundamental Theory of Computer Vision, Machine Learning, Vision Problems in Robotics, Autonomous Driving, Pattern Classification and Cluster Analysis, Performance Evaluation and Benchmarks, Remote Sensing Image Interpretation, Biometric Recognition, Face Recognition and Pose Recognition, Structural Pattern Recognition, Computational Photography, Sensing and Display Technology, Video Analysis and Understanding, Vision Applications and Systems, Document Analysis and Recognition, Feature Extraction and Feature Selection, Multimedia Analysis and Reasoning, Optimization and Learning methods, Neural Network and Deep Learning, Low-Level Vision and Image Processing, Object Detection, Tracking and Identification, Medical Image Processing and Analysis. .

Contents:

Intro

Preface

Organization

Contents - Part III

Machine Learning

Loss Filtering Factor for Crowd Counting

1 Introduction

2 Related Work

3 Proposed Method

3.1 Background and Motivation

3.2 Loss Filtering Factor

4 Experiments

4.1 Evaluation Metrics

4.2 Datasets

4.3 Neural Network Model

4.4 Experimental Evaluations

4.5 Key Issues and Discussion

5 Conclusions and Future Work

References

Classifier Decoupled Training for Black-Box Unsupervised Domain Adaptation

3 Method

3.1 Problem Definition

3.2 Overall Framework

3.3 Classifier Decoupled Training (CDT)

3.4 ETP-Entropy Sampling

4 Experiment

4.1 Setup

4.2 Performance Comparison

4.3 Analysis

5 Conclusion

Unsupervised Concept Drift Detection via Imbalanced Cluster Discriminator Learning

2 Related Works

2.1 Concept Drift Detection

2.2 Imbalance Data Clustering

3 Propose Method

3.1 Imbalanced Distribution Learning

3.2 Multi-cluster Descriptor Training

3.3 Concept Drift Detection Based on MCD

4.1 Experimental Setup

4.2 Comparative Results

4.3 Ablation Study

4.4 Study on Imbalance Rate and Drift Severity

Unsupervised Domain Adaptation for Optical Flow Estimation

3.1 Overview

3.2 Domain Adaptive Autoencoder

3.3 Incorporating with RAFT

3.4 Overall Objective

3.5 Network Architecture

4.2 Experiment Results

Continuous Exploration via Multiple Perspectives in Sparse Reward Environment

3.1 Continuous Exploration via Multiple Perspectives

3.2 Global Reward Model.

3.3 Local Reward Model

4.1 Comparison Algorithms and Evaluation Metrics

4.2 Network Architectures and Hyperparameters

4.3 Experimental Results

Network Transplanting for the Functionally Modular Architecture

3 Network Transplanting

3.1 Space-Projection Problem of Standard Distillation and Jacobian Distillation

3.2 Solution: Learning with Back-Distillation

4.1 Implementation Details

4.2 Experimental Results and Analysis

TiAM-GAN: Titanium Alloy Microstructure Image Generation Network

2.1 Image Generation

2.2 Mixture Density Network

3.1 Framework

3.2 Feature-Fusion CcGAN

3.3 Feature-Extraction-Mapping GAN

4.1 Dataset

4.2 Metric

4.3 Comparison Experiment

4.4 Ablation Experiment

A Robust Detection and Correction Framework for GNN-Based Vertical Federated Learning

2.1 Attack and Defense in Graph Neural Networks

2.2 Attack and Defense in Vertical Federated Learning

2.3 Attack and Defense in GNN-Based Vertical Federated Learning

3 Methodology

3.1 GNN-Based Vertical Federated Learning

3.2 Threat Model

3.3 Framework Overview

3.4 Malicious Participant Detection

3.5 Malicious Embedding Correction

4.1 Experiment Settings

4.2 Detection Performance(RQ1)

4.3 Defense Performance(RQ2-RQ3)

QEA-Net: Quantum-Effects-based Attention Networks

2.1 Revisiting QSM

2.2 Attention Mechanism in CNNs

3 Quantum-Effects-based Attention Networks

3.1 Spatial Attention Module Based on Quantum Effects

4 Experiments.

4.1 Implementation Details

4.2 Comparisons Using Different Deep CNNs

4.3 Comparisons Using MLP-Mixer

Learning Scene Graph for Better Cross-Domain Image Captioning

2.1 Scene Graph

2.2 Cross Domain Image Captioning

3 Methods

3.1 The Principle of SGCDIC

3.2 Parameters Updating

3.3 Object Geometry Consistency Losses and Semantic Similarity

4 Experiments and Results Analysis

4.1 Datasets and Implementation Details

4.2 Quantitative Comparison

4.3 Qualitative Comparison

Enhancing Rule Learning on Knowledge Graphs Through Joint Ontology and Instance Guidance

2.1 Reasoning with Embeddings

2.2 Reasoning with Rules

3.1 Framework Details

4.2 Results

5 Conclusions

Explore Across-Dimensional Feature Correlations for Few-Shot Learning

2.1 Few-Shot Learning

2.2 Attention Mechanisms in Few-Shot Learning

3.1 Preliminary

3.3 Three-Dimensional Offset Position Encoding (TOPE)

3.4 Across-Dimensional Attention (ADA)

3.5 Learning Object

4.1 Experiment Setup

4.2 Comparison with State-of-the-art

4.3 Ablation Studies

4.4 Convergence Analysis

4.5 Visualization

Pairwise-Emotion Data Distribution Smoothing for Emotion Recognition

2 Method

2.1 Pairwise Data Distribution Smoothing

2.2 CLTNet

3 Experiment

3.1 Dataset and Evaluation Metrics

3.2 Implementation Details

3.3 Validation Experiment

3.4 Ablation Study

4 Conclusion

SIEFusion: Infrared and Visible Image Fusion via Semantic Information Enhancement.

1 Introduction

2.1 Problem Formulation

2.2 Network Architecture

2.3 Loss Function

3 Experiments

3.1 Experimental Configurations

3.2 Results and Analysis

3.3 Ablation Study

3.4 Segmentation Performance

DeepChrom: A Diffusion-Based Framework for Long-Tailed Chromatin State Prediction

2.1 Chromatin State Prediction

2.2 Long-Tailed Learning

3.1 Methodology Overview

3.2 Pseudo Sequences Generation

3.3 Chromatin State Prediction

3.4 Equalization Loss

4.1 Experimental Settings

4.2 Effectiveness of Our Proposed Long-Tailed Learning Methods

5 Conclusion and Discussion

Adaptable Conservative Q-Learning for Offline Reinforcement Learning

3 Prelinminaries

4 Methodology

4.1 Adaptable Conservative Q-Learning

4.2 Variants and Practical Object

4.3 Implementation Settings

5 Experiments

5.1 Experimental Details

5.2 Q-Value Distribution and Effect of the Percentile

5.3 Deep Offline RL Benchmarks

5.4 Ablation Study

6 Conclusion

Boosting Out-of-Distribution Detection with Sample Weighting

3.1 Problem Setting

3.2 Weighted Distance as Score Function

3.3 Contrastive Training for OOD Detection

4.1 Common Setup

4.2 Main Results

Causal Discovery via the Subsample Based Reward and Punishment Mechanism

3 Introduction to the Algorithmic Framework

3.1 Introduction to SRPM Method

3.2 Correlation Measures and Hypothesis Testing

3.3 Skeleton Discovery Algorithm Based on SRPM Method (SRPM-SK).

4 Experimental Results and Analysis

4.1 Benchmark Network and Data Sets

4.2 High Dimensional Network Analysis

4.3 Real Data Analysis

5 Conclusion and Outlook

Local Neighbor Propagation Embedding

3 Local Neighbor Propagation Embedding

3.1 Motivation

3.2 Mathematical Background

3.3 Local Neighbor Propagation Framework

3.4 Computational Complexity

4 Experimental Results

4.1 Synthetic Datasets

4.2 Real-World Datasets

Inter-class Sparsity Based Non-negative Transition Sub-space Learning

2.1 Notations

2.2 StLSR

2.3 ICS_DLSR

2.4 SN-TSL

3 The Proposed Method

3.1 Problem Formulation and Learning Model

3.2 Solution to ICSN-TSL

3.3 Classification

3.4 Computational Time Complexity

3.5 Convergence Analysis

4 Experiments and Analysis

4.1 Data Sets

4.3 Parameter Sensitivity Analysis

4.4 Ablation Study

Incremental Learning Based on Dual-Branch Network

3.1 Problem Description

3.2 Baseline Method

3.3 Model Extension

3.4 Two Distillation

3.5 Two Stage Training

3.6 Sample Update Policy

4 Experience

4.1 Baseline Result

4.2 Result on Imagenet100

Inter-image Discrepancy Knowledge Distillation for Semantic Segmentation

2.2 Overview

2.3 Attention Discrepancy Distillation

2.4 Soft Probability Distillation

2.5 Optimization

3.1 Datasets and Setups

3.2 Comparisons with Recent Methods

3.3 Ablation Studies

Vision Problems in Robotics, Autonomous Driving.

Cascaded Bilinear Mapping Collaborative Hybrid Attention Modality Fusion Model.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

9789819984350

9819984351

OCLC:

1416340849