Pattern Recognition and Computer Vision: 6th Chinese Conference, Prcv 2023, Xiamen, China, October 13-15, 2023, Proceedings, Part X

ISBN-13: 9789819985487 / Angielski

Qingshan Liu; Hanzi Wang; Zhanyu Ma

Spis treści

Dual-stream Context-aware Neural Network for Survival Prediction from Whole Slide Images.- A multi-label image recognition algorithm based on spatial and semantic correlation interaction.- Hierarchical Spatial-Temporal Network for Skeleton-Based Temporal Action Segmentation.- Multi-Behavior Enhanced Graph Neural Networks for Social Recommendation.- A Complex-valued Neural Network based Robust Image Compression.- Binarizing Super-resolution Neural Network without Batch Normalization.- Infrared and Visible Image Fusion via Test-Time Training.- Graph-based Dependency-aware Non-Intrusive Load Monitoring.- Few-shot Object Detection via Classify-free RPN.- IPFR: Identity-Preserving Face Reenactment with Enhanced Domain Adversarial Training and Multi-level Identity Priors.- L2MNet: Enhancing Continual Semantic Segmentation with Mask Matching.- Adaptive Channel Pruning for Trainability Protection.- Exploiting Adaptive Crop and Deformable Convolution for Road Damage Detection.- Cascaded-scoring Tracklet Matching for Multi-object Tracking.- Boosting Generalization Performance in Person Re-Identification

Self-Guided Transformer for Video Super-Resolution.- SAMP: Sub-task Aware Model Pruning with Layer-wise Channel Balancing for Person Search.- MKB: Multi-kernel Bures Metric for Nighttime Aerial Tracking.- Deep Arbitrary-Scale Unfolding Network for Color-Guided Depth Map Super-Resolution.- SSDD-Net: A Lightweight and Efficient Deep Learning Model for Steel Surface Defect Detection.- Effective Small Ship Detection with Enhanced-YOLOv7.- PiDiNeXt: An Efficient Edge Detector based on Parallel Pixel Difference Networks.- Transpose and Mask: Simple and Effective Logit-Based Knowledge Distillation for Multi-Attribute and Multi-Label Classification.- CCSR-Net: Unfolding coupled convolutional sparse representation for multi-focus image fusion.- FASONet: A Feature Alignment-Based SAR and Optical Image Fusion Network  for Land Use Classification.- De Novo Design of Target-Specific Ligands Using BERT-Pretrained Transformer.- CLIP for Lightweight Semantic Segmentation.- Teacher-Student Cross-Domain Object Detection Model Combining Style Transfer and Adversarial Learning.- Computing 2D Skeleton via Generalized Electric Potential.- Illumination Insensitive Monocular Depth Estimation based on Scene Object Attention and Depth Map Fusion.- A Few-Shot Medical Image Segmentation Network with Boundary Category Correction.- Repdistiller: Knowledge Distillation Scaled by Re-parameterization for Crowd Counting.- Multi-depth Fusion Transformer and Batch Piecewise Loss for Visual Sentiment Analysis.- Expanding the Horizons: Exploring Further Steps in Open-Vocabulary Segmentation.- Exploring a Distillation with Embedded Prompts for Object Detection in Adverse Environments.- TEFNet: Target-Aware Enhanced Fusion Network for RGB-T Tracking.- DARN: Crowd Counting Network Guided by Double Attention Refinement.- DFR-ECAPA: Diffusion Feature Refinement for Speaker Verification based on ECAPA-TDNN.- Half Aggregation Transformer for Exposure Correction.- Deformable Spatial-Temporal Attention for Lightweight Video Super-Resolution