دانلود کتاب Pattern Recognition and Computer Vision: 4th Chinese Conference, PRCV 2021, Beijing, China, October 29 – November 1, 2021, Proceedings, Part II (Image ... Vision, Pattern Recognition, and Graphics)

فهرست مطالب :

Preface
Organization
Contents – Part II
Computer Vision, Theories and Applications
Dynamic Fusion Network for Light Field Depth Estimation
1 Introduction
2 Related Work
3 Method
3.1 The Overall Architecture
3.2 Pyramid ConvGRU
3.3 Multi-modal Dynamic Fusion Module (MDFM)
4 Experiments
4.1 Experiments Setup
4.2 Ablation Studies
4.3 Comparison with State-of-the-arts
5 Conclusion
References
Metric Calibration of Aerial On-Board Multiple Non-overlapping Cameras Based on Visual and Inertial Measurement Data
1 Introduction
2 Related Works
3 Metric Calibration Based on Visual and Inertial Measurement Data
3.1 Notation and Problem Formulation
3.2 Relative Pose Estimation via Structure from Motion
3.3 Inertial Measurement Data Based Metric Scale Factor Estimation
4 Experimental Results
4.1 Equipment
4.2 Metric Calibration of the Aerial On-Board Non-overlapping Camera System
4.3 Metric Calibration of an Industrial Non-overlapping Camera System
4.4 Experiments of Applications for Object Metric 3D Reconstruction
5 Conclusions
References
SEINet: Semantic-Edge Interaction Network for Image Manipulation Localization
1 Introduction
2 Related Work
3 Method
3.1 Cross Interaction Pattern
3.2 Aggregate Interaction Module
3.3 Bidirectional Fusion Module
3.4 Training Loss
4 Experiments
4.1 Datasets and Implementation Details
4.2 Evaluation Metrics
4.3 Ablation Studies
4.4 Robustness Analysis
4.5 Comparing with State-of-the-Art
5 Conclusion
References
Video-Based Reconstruction of Smooth 3D Human Body Motion
1 Introduction
2 Related Work
2.1 3D Human Mesh from Single Images
2.2 3D Human Mesh from Video
2.3 GANs for Modeling
3 Approach
3.1 3D Body Representation
3.2 Temporal Encoder
3.3 Constraint Loss
3.4 Motion Discriminator
4 Experiments
4.1 Implement Details
4.2 Comparison to Other Methods
4.3 Ablation Experiments
5 Conclusion
References
A Unified Modular Framework with Deep Graph Convolutional Networks for Multi-label Image Recognition
1 Introduction
2 Related Work
3 Proposed Method
3.1 Image Feature Extraction Module
3.2 Label Semantic Extraction Module
3.3 Prediction Results and Training Scheme
4 Experiments
4.1 Evaluation Metrics
4.2 Implementation Details
4.3 Experimental Results
4.4 Ablation Studies
4.5 Adjacency Matrix Visualization
5 Conclusion
References
3D Correspondence Grouping with Compatibility Features
1 Introduction
2 Related Work
2.1 3D Correspondence Grouping
2.2 Learning for Correspondence Grouping
3 Methodology
3.1 Compatibility Check
3.2 CF Feature Extraction
3.3 CF Classification
4 Experiments
4.1 Experimental Setup
4.2 Method Analysis
4.3 Comparative Results and Visualization
5 Conclusions
References
Contour-Aware Panoptic Segmentation Network
1 Introduction
2 Related Work
3 Approach
3.1 Panoptic Contour Branch
3.2 Panoptic Segmentation Branch
3.3 Structure Loss Function
4 Experiments
4.1 Dataset
4.2 Evaluation Metrics
4.3 Implementation Details
4.4 Comparisons with Other Methods
4.5 Ablative Analysis
5 Conclusion
References
VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-Based Convolutional Autoencoder
1 Introduction
2 Realted Work
2.1 Handcraft-Based Methods
2.2 CNN-Based Methods
2.3 AE-Based Methods
3 VGG16-Based Convolutional Autoencoder
3.1 Model Architecture
3.2 Training
3.3 Matching
4 Experiments
4.1 Datasets
4.2 State-of-the-Art Approaches
4.3 Ground Truth
4.4 Comparison and Discussion
5 Conclusion
References
Slice Sequential Network: A Lightweight Unsupervised Point Cloud Completion Network
1 Introduction
2 Related Work
2.1 3D Learning
2.2 3D Completion
3 Our Method
3.1 Overview
3.2 Slicer
3.3 Multi-scale Point Encoder
3.4 Sequential Predictor
3.5 Shape Prediction Decoder
3.6 Loss Function
4 Experiments
4.1 Datasets and Implementation Details
4.2 Point Cloud Completion Results
4.3 Analysis of Encoder
4.4 Robustness to Occlusion
4.5 Comparison of Complexity
5 Ablation Study
6 Conclusion
References
From Digital Model to Reality Application: A Domain Adaptation Method for Rail Defect Detection
1 Introduction
2 Preliminaries
3 Method
3.1 DT-Based Virtual Data Generation
3.2 Dummy-Target Domain
3.3 DA-YOLO
4 Experiment
4.1 Dataset and Evaluation Metrics
4.2 Experiment Settings
4.3 Experimental Results
5 Conclusion
References
FMixAugment for Semi-supervised Learning with Consistency Regularization
1 Introduction
2 Related Work
3 Methods
3.1 FMixAugment: MixAugment Combined with FMask
3.2 Improved Consistency Regularization
3.3 Dynamic Growth Threshold
4 Experiments
4.1 Implementation Details
4.2 Experimental Results
4.3 Ablation Study
5 Conclusion and Future Work
References
IDANet: Iterative D-LinkNets with Attention for Road Extraction from High-Resolution Satellite Imagery
1 Introduction
2 Related Work
3 Methodology
3.1 Overview
3.2 Basic Iteration Module
3.3 Iterative Architecture
4 Experiment
4.1 Datasets
4.2 Implementation Details
5 Results
5.1 Comparison of Road Segmentation Methods
5.2 Ablation Experiment
5.3 The Influence of Network Iteration
6 Conclusion
References
Disentangling Deep Network for Reconstructing 3D Object Shapes from Single 2D Images
1 Introduction
2 Related Works
3 Disentangling Deep Network
3.1 Network Architecture
3.2 Learning Objective Functions
3.3 Training Strategy
4 Experiments
4.1 Implementation Details
4.2 Ablation Analysis
4.3 3D Reconstruction
4.4 Effects of 3D Shape Identity
5 Conclusion
References
AnchorConv: Anchor Convolution for Point Clouds Analysis
1 Introduction
2 Related Work
3 Proposed Method
3.1 AnchorConv
3.2 Anchor Reweighting Module
3.3 Network Architectures
4 Experiments
4.1 Classification on ModelNet40
4.2 ShapeNet Part Segmentation
4.3 3D Segmentation of Indoor Scene
4.4 3D Segmentation of Outdoor Scene
4.5 Ablation Study
4.6 Qualitative Results
5 Conclusion
References
IFR: Iterative Fusion Based Recognizer for Low Quality Scene Text Recognition
1 Introduction
2 Related Works
3 Method
3.1 Iterative Collaboration
3.2 Fusion Module RRF
3.3 Loss Functions
3.4 Paired Training Data Generate
4 Experiments
4.1 Datasets and Implementation Details
4.2 Ablation Study
4.3 Comparisons with State-of-the-Arts
5 Conclusion
References
Immersive Traditional Chinese Portrait Painting: Research on Style Transfer and Face Replacement
1 Introduction
2 Related Work
2.1 Neural Style Transfer
2.2 Face Replacement
3 The P-CP Method
3.1 Network Architecture
3.2 Neural Style Transfer Network
3.3 Face Replacement
4 Experiment
4.1 Comparison of Different Traditional Chinese Painting Styles
4.2 Image Detail Exploration and Optimization
4.3 Improvement of Face Replacement with Style Transfer
5 Conclusion
References
Multi-camera Extrinsic Auto-calibration Using Pedestrians in Occluded Environments
1 Introduction
2 Related Work
3 Calibration Based on 3D Positions
3.1 3D Head Positions in Local Camera Coordinates
3.2 Registration of 3D Point Sets
4 Refinement
5 Experiments and Results
6 Conclusion
References
Dual-Layer Barcodes
1 Introduction
2 Related Work
2.1 Steganography
2.2 Watermarking
2.3 Barcode
3 Method
3.1 Encoder
3.2 Decoder
3.3 Noise Layer
3.4 Discriminator
4 Experiments and Analysis
4.1 Dataset and Experimental Setting
4.2 Implementation Details
4.3 Metrics
5 Discussion
6 Conclusion
References
Graph Matching Based Robust Line Segment Correspondence for Active Camera Relocalization
1 Introduction
2 Method
2.1 System Overview
2.2 Robust Line Segment Matching
2.3 Active Camera Relocation
3 Experiments
3.1 Experimental Setup
3.2 Analysis of Line Segment Matching
3.3 Analysis of Relocalization Accuracy and Convergence Speed
3.4 Analysis of Robustness in Hard Scenes
4 Conclusion
References
Unsupervised Learning Framework for 3D Reconstruction from Face Sketch
1 Introduction
2 Related Work
2.1 Image-to-Image Translation
2.2 3D Shape Reconstruction
3 Method
3.1 Dataset Construction
3.2 Network Architecture
3.3 Loss Functions
4 Experiments
4.1 Implementation Details
4.2 Quantitative Results and Ablation Study
4.3 Qualitative Results
5 Conclusion
References
HEI-Human: A Hybrid Explicit and Implicit Method for Single-View 3D Clothed Human Reconstruction
1 Introduction
2 Related Work
3 Methodology
3.1 Overview
3.2 Explicit Model
3.3 Implicit Model
3.4 Loss Functions
4 Experiments
4.1 Dataset and Protocol
4.2 Training Details
4.3 Quantitative Results
4.4 Qualitative Results
4.5 Ablation Studies
5 Conclusions
References
A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
1 Introduction
2 Methods
2.1 Generative Architecture Based on Tree-Structured GCN
2.2 Training of the Proposed GAN Model
3 Experiments
4 Conclusion
References
3D-SceneCaptioner: Visual Scene Captioning Network for Three-Dimensional Point Clouds
1 Introduction
2 Related Work
2.1 Point Cloud Processing
2.2 Scene Captioning
3 Method
3.1 Feature Extraction Module
3.2 Semantic Segmentation Module
3.3 Caption Generation Module
4 Experiments
4.1 Datasets
4.2 Experimental Settings
4.3 Comparative Analysis
4.4 Ablation Study
4.5 Qualitative Results and Visualization
5 Conclusion
References
Soccer Field Registration Based on Geometric Constraint and Deep Learning Method
1 Introduction
2 Related Work
3 Homography Matrix
4 Soccer Field Registration
4.1 Soccer Field Marker Lines Detection
4.2 Geometric Constraint Structure
4.3 Parameter Regression Model
4.4 Deep Learning Training Network
5 Experiments and Results
5.1 Data Augmentation
5.2 Performance Evaluation Indicator
5.3 Results
6 Conclusion
References
Enhancing Latent Features for Unsupervised Video Anomaly Detection
1 Introduction
2 Related Work
3 Proposed Method
3.1 Overview
3.2 Single Grid Feature Enhancement
3.3 Local Context Feature Enhancement
3.4 Training Objective and Abnormality Score
4 Experiments
4.1 Experimental Setting
4.2 Implementation Details
4.3 Ablation Study
4.4 More Results on Three Benchmark Datasets
4.5 Visualization
5 Conclusion
References
Adaptive Anomaly Detection Network for Unseen Scene Without Fine-Tuning
1 Introduction
2 Related Work
2.1 Anomaly Detection
2.2 Few-Shot Learning
3 Method
3.1 Segments Similarity Measurement
3.2 Relational Scene Awareness
3.3 Integration
4 Experiment
4.1 Dataset
4.2 Evaluation Metric
4.3 Implementation Details
4.4 Performance Comparison
4.5 Ablation Study
5 Conclusion
References
Facial Expression Recognition Based on Multi-scale Feature Fusion Convolutional Neural Network and Attention Mechanism
1 Introduction
2 Related Work
3 Proposed Model
3.1 The Algorithm Framework
3.2 Bottleneck Layer Module
3.3 Other Modules
4 Experiments
4.1 Datasets
4.2 Experiments on RAF-DB Dataset
4.3 Experiments on Other Datasets
5 Conclusion
References
Separable Reversible Data Hiding Based on Integer Mapping and Multi-MSB Prediction for Encrypted 3D Mesh Models
1 Introduction
2 Proposed Method
2.1 Pre-processing
2.2 Prediction Error Detection
2.3 Encryption
2.4 Data Hiding
2.5 Data Extraction and Mesh Recovery
3 Experimental Results and Discussion
3.1 Embedding Capacity
3.2 Geometric and Visual Quality
3.3 Performance Comparison
3.4 Feature Comparison
3.5 Performance Analysis on Dense Meshes
4 Conclusions
References
MPN: Multi-scale Progressive Restoration Network for Unsupervised Defect Detection
1 Introduction
2 Method
2.1 Pipeline
2.2 Self-synthesis Module
2.3 Progressive Restoration Network
2.4 Multi-scale Feature Fusion
3 Experiments
3.1 Empirical Setting
3.2 Results
3.3 Ablation Studies
3.4 Effects of Iterative Stage t
4 Conclusion
References
Scene-Aware Ensemble Learning for Robust Crowd Counting
1 Introduction
2 Related Work
2.1 Density-Based Crowd Counting
2.2 Scene Adaptation Task for Crowd Counting
3 Methodology
3.1 Scene-Oriented Multi-branch Density Map Generator
3.2 Scene-Aware Density Map Fusion Branch
3.3 Loss Function and Network Training
4 Experiments
4.1 Implementation and Settings
4.2 Datasets
4.3 Results on WorldExpo\'10
4.4 Results on ShanghaiTech and UCF_CC_50
4.5 Ablation Study
4.6 Visual Results on ShanghaiTech Samples
5 Conclusion
References
Complementary Temporal Classification Activation Maps in Temporal Action Localization
1 Introduction
2 Related Work
3 Our Approach
3.1 Feature Extraction Layer
3.2 Feature Embedding Layer
3.3 Complementary Temporal Class Activation Map
3.4 Model Optimization
4 Experiments and Analysises
4.1 Datasets
4.2 Implementation Details
4.3 Ablation Studies
4.4 Experimental Results on the THUMOS\'14 Dataset
4.5 Experimental Results on ActivityNet-1.2 Dataset
4.6 Results Analysis
5 Conclusion
References
Improve Semantic Correspondence by Filtering the Correlation Scores in both Image Space and Hough Space
1 Introduction
2 Related Work
3 The Proposed Method
4 Experiments
4.1 Benchmarks and Evaluation Metric
4.2 Implementation Details
4.3 Evaluation Results
5 Conclusion
References
A Simple Network with Progressive Structure for Salient Object Detection
1 Introduction
2 Related Works
3 Methodology
3.1 Overview of the Proposed Network
3.2 Progressive Fusion Architecture
3.3 Feature Fusion Module
3.4 Enhanced Loss
4 Experiments
4.1 Comparison with State-of-the-Arts
4.2 Ablation Studies
4.3 Visualization
5 Conclusion
References
Feature Enhancement and Multi-scale Cross-Modal Attention for RGB-D Salient Object Detection
1 Introduction
2 Our Method
2.1 Overview of Network Architecture
2.2 Feature Enhancement Module
2.3 Multi-scale Cross-Modal Attention Module
2.4 Loss Function
3 Experiments
3.1 Comparisons with State-of-the-Arts
4 Conclusion
References
Improving Unsupervised Learning of Monocular Depth and Ego-Motion via Stereo Network
1 Introduction
2 Related Work
2.1 Supervised Monocular Depth and Ego-Motion Estimation
2.2 Unsupervised Monocular Depth and Ego-Motion Estimation
3 Method
3.1 Problem Formulation
3.2 Two-Stage Unsupervised Learning Framework
3.3 Dense Feature Fusion
4 Experiments
4.1 Implementation Details
4.2 Main Results
4.3 Ablation Study
4.4 Make3D
5 Conclusion
References
A Non-autoregressive Decoding Model Based on Joint Classification for 3D Human Pose Regression
1 Introduction
2 Related Work
3 Network Architecture
4 Joint Classification
4.1 Classification Based on Connection
4.2 Global Correlation Based on Multi-head Attention Mechanism
4.3 Dynamic Classification Based on Global Correlation
5 Non-autoregressive Decoding Based on 3D Spatial Constraints
5.1 3D Spatial Constrains
5.2 Non-autoregressive Decoding and Decouple Correlation
5.3 Loss Function
6 Experiments
6.1 Implementation Details
6.2 Dataset and Evaluation Metric
6.3 Ablation Study
6.4 Comparison with the State-of-the-Art
7 Conclusions
References
Multimedia Processing and Analysis
Multiple Semantic Embedding with Graph Convolutional Networks for Multi-Label Image Classification
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Notations and Problem Formulation
3.2 Direction-Guided Feature Embedding Learning
3.3 GCNs-Based Semantic Embedding Learning
3.4 Adaptive Weighted Label Ranking
4 Experiments
4.1 Experimental Setup
4.2 Experiment Results
4.3 Ablation Experiment
5 Conclusion
References
AMEN: Adversarial Multi-space Embedding Network for Text-Based Person Re-identification
1 Introduction
2 Related Works
2.1 Person Re-identification
2.2 Text-Based Person Re-identification
3 Methodology
3.1 Feature Extraction
3.2 Feature Reconstruction
3.3 Loss Functions and Training Strategy
4 Experiments
4.1 Experimental Setup
4.2 Ablation Analysis
4.3 Comparison with Other State-of-the-Art Methods
5 Conclusion
References
AFM-RNN: A Sequent Prediction Model for Delineating Building Rooftops from Remote Sensing Images by Integrating RNN with Attraction Field Map
1 Introduction
2 Related Work
2.1 Instance Segmentation
2.2 Edge Representation Approach
2.3 Multi-task Learning
3 Methods
3.1 NDDR-CNNs
3.2 AFM Attention Mechanisms
3.3 Recurrent Decoder
4 Experiments
4.1 Datasets and Evaluation Metrics
4.2 Training Details
4.3 Results and Comparisons
4.4 Ablation Experiments
5 Conclusions
References
Attribute-Level Interest Matching Network for Personalized Recommendation
1 Introduction
2 Related Work
3 Attribute-Level Interest Matching Network
3.1 Knowledge Representation Learning
3.2 Attribute-Level Interest Extraction
3.3 Attribute-Level Interest Matching Layer
3.4 Model Optimization
4 Experiment
4.1 Experimental Settings
4.2 Performance Comparison
4.3 Case Study
5 Conclusion
References
Variational Deep Representation Learning for Cross-Modal Retrieval
1 Introduction
2 Proposed Method
2.1 Notations
2.2 Modality-Specific VAE
2.3 MI Maximization
2.4 Semantic Alignment
3 Experiments
3.1 Datasets and Evaluation Metric
3.2 Results and Analysis
4 Conclusion
References
Vein Centerline Extraction of Visible Images Based on Tracking Method
1 Introduction
2 Image Preprocessing
3 Vein Centerline Extraction
3.1 Determination of Initial Points and Direction
3.2 Tracking Process
4 Experiments and Discussion
4.1 Subjective Evaluation
4.2 Objective Evaluation
4.3 Evaluation by Vein Pattern Matching
5 Conclusion
References
Discrete Bidirectional Matrix Factorization Hashing for Zero-Shot Cross-Media Retrieval
1 Introduction
2 Proposed Method
2.1 Notations
2.2 Objective Function
2.3 Optimization Algorithm
2.4 Out-of-Sample Extension
3 Experiments and Results Analysis
3.1 Experiment Settings
3.2 Zero-Shot Retrieval
3.3 Standard Retrieval
3.4 Ablation Study
3.5 Convergence
4 Conclusion
References
Dual Stream Fusion Network for Multi-spectral High Resolution Remote Sensing Image Segmentation
1 Introduction
2 Related Work
3 Proposed Method
3.1 Dual-Stream Fusion
3.2 Stage Pyramid Pooling
4 Experiments and Analysis
4.1 Data Description
4.2 Experimental Settings
4.3 Results and Analysis
5 Conclusion
References
Multi-scale Extracting and Second-Order Statistics for Lightweight Steganalysis
1 Introduction
2 Related Works
3 Proposed Method
3.1 Preprocessing Layer
3.2 Feature Extraction Layer
3.3 Downsample Module
3.4 Mutli-order Statistics
4 Experiments
4.1 The Environments
4.2 Cross-Domain Steganalysis Experiments
4.3 Steganalysis Experiments Result
5 Conclusion
References
HTCN: Harmonious Text Colorization Network for Visual-Textual Presentation Design
1 Introduction
2 Related Works
3 Proposed Method
3.1 Overall Framework
3.2 Text Colorization Network
3.3 Text Readability Scoring Network
3.4 Color Harmony Scoring Network
3.5 Loss Function
4 Experiments
4.1 Datasets
4.2 Implementation Details
4.3 Effectiveness of Network Design
4.4 Comparison with Other Methods
4.5 User Study
5 Conclusion
References
A Fast Method for Extracting Parameters of Circular Objects
1 Introduction
2 Hough Voting
2.1 Hough Space
2.2 Functional Equation of Voting Value A()
2.3 Functional Equation of Mean Voting Distance m()
3 Parameters Extracting
3.1 The Radius Extraction
3.2 The Center Extraction
4 Experimental Results
4.1 Test with Synthetic Images
4.2 Test on Real World Images
4.3 Applications in Cyclone Centers Location
5 Conclusions
References
GGRNet: Global Graph Reasoning Network for Salient Object Detection in Optical Remote Sensing Images
1 Introduction
2 Related Works
2.1 Salient Object Detection in NSIs
2.2 Salient Object Detection in Optical RSIs
2.3 Graph-Based Reasoning
3 Method
3.1 Overview
3.2 Encoder-Decoder Network
3.3 Graph Reasoning with Global Information
3.4 Attention Mechanism in the Graph Reasoning
4 Experiments and Results
4.1 Dataset and Evaluation Metrics
4.2 Training Strategies and Implementation Details
4.3 Comparison with State-of-the-Art Methods
4.4 Ablation Study
5 Conclusion
References
A Combination Classifier of Polarimetric SAR Image Based on D-S Evidence Theory
1 Introduction
2 Preliminaries
2.1 The Base Classifiers
2.2 Dempster-Shafer Evidence Theory
2.3 Confusion Matrix
3 The Proposed Approach
4 Experiments with Flevoland Dataset
5 Conclusion
References
Image Tampering Localization Using Unified Two-Stream Features Enhanced with Channel and Spatial Attention
1 Introduction
2 Proposed Method
2.1 Overall Framework
2.2 Attention-Based Feature Fusion Module
2.3 Feature Integration for Pixel-Level Prediction
2.4 Loss Functions
3 Experiments
3.1 Experimental Settings
3.2 Performance of the Pre-trained Model
3.3 Localization Performance for Realistic Datasets
3.4 Robustness Analysis
4 Conclusions
References
An End-to-End Mutual Enhancement Network Toward Image Compression and Semantic Segmentation
1 Introduction
2 Related Works
2.1 Learning-Based Compression
2.2 Video Coding for Machines
3 Proposed Method
3.1 Encoder
3.2 Decoder
3.3 Enhancement Module
4 Experiments
4.1 Results on Image Compression
4.2 Results on Semantic Segmentation
5 Conclusion
References
Deep Double Center Hashing for Face Image Retrieval
1 Introduction
2 Related Work
2.1 Deep Hashing in General Images Retrieval
2.2 Deep Hashing in Face Images Retrieval
3 Deep Double Center Hashing
3.1 Motivations
3.2 The Proposed DDCH Model
3.3 Loss Functions for End-to-End Training
4 Experiments
4.1 Datasets and Evaluation Metric
4.2 Comparison with Baselines
4.3 Ablation Study
4.4 Visualization
5 Conclusion
References
A Novel Method of Cropped Images Forensics in Social Networks
1 Introduction
2 Related Works
3 Proposed Method
3.1 Aligned and Non-aligned Crop
3.2 BAGS in Re-compression
3.3 BAGS in Social Networks
4 Experimental Results
4.1 Experiments on Re-compression
4.2 Experiments on Social Networks (Facebook)
4.3 Experiments on Wechat Moments
5 Conclusion
References
MGD-GAN: Text-to-Pedestrian Generation Through Multi-grained Discrimination
1 Introduction
2 Related Works
3 Multi-Grained Discrimination Enhanced Generative Adversarial Network
3.1 Multi-stage Generation Strategy
3.2 VISA-HPD: Visual-Semantic Attention Enhanced Human-Part-based Discriminator
3.3 Self-cross-attended Global Discriminator
3.4 Objective Functions
4 Pose Score and Pose Variance
5 Experiments
5.1 Quantitative Evaluation
5.2 Qualitative Evaluation
5.3 Ablation Study
6 Conclusion
References
Correction to: Pattern Recognition and Computer Vision
Correction to: H. Ma et al. (Eds.): Pattern Recognition and Computer Vision, LNCS 13020, https://doi.org/10.1007/978-3-030-88007-1
Author Index