El. knyga: Pattern Recognition and Computer Vision: 5th Chinese Conference, PRCV 2022, Shenzhen, China, November 4-7, 2022, Proceedings, Part I

Theories and Feature Extraction.- Architecture Colorization via
Self-Supervised Learning and Instance Segmentation.- Dual-rank attention
module for fine-grained vehicle model recognition.- Multi-View Geometry
Distillation for Cloth-changing Person ReID.- Triplet Ratio Loss for Robust
Person Re-identification.- TFAtrack:Temporal Feature Aggregration for UAV
Tracking and A Unified Benchmark.- Correlated Matching and Structure Learning
for Unsupervised Domain Adaptation.- Rider Re-identification Based on Pyramid
Attention.- Temporal Correlation-Diversity Representations for Video-based
Person Re-Identication.- FIMF Score-CAM: Score-CAM Based Visual Explanations
via Fast Integrating Multiple Features of Local Space for Deep
Networks.- Learning Adaptive Progressive Representation for Group
Re-identification.- General High-Pass Convolution: A Novel Convolutional
Layer for Image Manipulation Detection.- Machine learning, Multimedia and
Multimodal.- Thangka Mural Line Drawing Based on Dense and Dual-Residual
Architecture.- Self-Supervised Adaptive Kernel Nonnegative Matrix
Factorization.- Driver Behavior Decision Making based on Multi-Action Deep
Q Network in Dynamic Traffic Scenes.- Federated Twin Support Vector Machine.-
Adversarial VAE with Normalizing Flows for
Multi-Dimensional Classification.- Fuzzy Twin Bounded Large Margin
Distribution Machines.- Harnessing Multi-Semantic Hypergraph for Few-Shot
Learning.- Deep Relevant Feature Focusing for Out-of-Distribution
Generalization.- Attributes based Visible-Infrared Person
Re-identification.- A Real-Time Polyp Detection Framework for Colonoscopy
Video.- Dunhuang Mural Line Drawing Based on Bi-Dexined Network and Adaptive
Weight Learning.- Attention-based Fusion of Directed Rotation Graphs for
Skeleton-based Dynamic Hand Gesture Recognition.- SteelyGAN: Semantic
Unsupervised Symbolic Music GenreTransfer.- Self-Supervised Learning for
Sketch-Based 3D Shape Retrieval.- Preference-aware Modality Representation
and Fusion for Micro-video Recommendation.- Multi-Intent Compatible
Transformer Network for Recommendation.- OpenMedIA: Open-Source Medical Image
Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms.-
CLIP Meets Video Captioning: Concept-Aware Representation Learning Does
Matter.- Attention-guided Multi-modal and Multi-scale fusion for
Multispectral Pedestrian Detection.- XPNet: Cross-Domain Prototypical Network
for Zero-Shot Sketch-Based Image Retrieval.- A high-order tensor completion
algorithm based on Fully-Connected Tensor Network weighted
optimization.- Momentum Distillation Improves Multimodal Sentiment Analysis.-
Synthesizing Counterfactual Samples for Overcoming Moment Biases in Temporal
Video Grounding.- Multi-Grained Cascade Interaction Network for Temporal
Activity Localization via Language.- Part-based Multi-Scale Attention Network
for Text-based Person Search.- Deliberate Multi-Attention Network for Image
Captioning.- CTFusion: Convolutions Integrate with Transformers for
Multi-modal Image Fusion.- Heterogeneous Graph-based Finger Trimodal
Fusion.- Disentangled OCR: A More Granular Information for
Text-to-Image" Retrieval.- Optimization and Neural Network and Deep
Learning.- Cloth-Aware Center Cluster Loss for Cloth-Changing
Person Re-identification.- Efficient Channel Pruning via Architecture-Guided
Search Space Shrinking.- EFG-Net: A Unified Framework for Estimating Eye Gaze
and Face Gaze Simultaneously.- Local Point Matching Network for Stabilized
Crowd Counting and Localization.- Discriminative Distillation to Reduce Class
Confusion in Continual Learning.- Enhancing Transferability of Adversarial
Examples with Spatial Momentum.- AIA: Attention in Attention within
Collaborate Domains.- Infrared and Near-Infrared Image Generation via Content
Consistency and Style Adversarial Learning.- Adaptive Open Set Recognition
with Multi-Modal Joint Metric Learning.- Prior-Guided Multi-Scale Fusion
Transformer for Face Attribute Recognition.- KITPose: Keypoint-Interactive
Transformer for Animal Pose Estimation.- Few-Shot Object Detection via
Understanding Convolution and Attention.- Every Corporation Owns Its
Structure: Corporate Credit Rating via Graph Neural Networks.- Unsupervised
Image Translation with GAN Prior.- An adaptive PCA-like asynchronously deep
reservoir computing for modeling data-driven soft sensors.- Double Recursive
Sparse Self-Attention Based Crowd Counting In The Cluttered Background.-
BiTMulV: Bidirectional-Decoding based Transformer With Multi-View Visual
Representation for Image Captioning.- An improved lightweight network based
on MobileNetV3 for palmprint recognition.- A Radar HRRP Target Recognition
Method Based on Conditional Wasserstein VAEGAN and 1-D CNN.- Partial Least
Square Regression via Three-factor SVD-type Manifold Optimization for EEG
Decoding.- Single Deterministic Neural Network with Hierarchical Gaussian
Mixture Model for Uncertainty Quantification.- Exploring Masked Image
Modeling for Face Anti-Spoofing.