Pattern Recognition and Computer Vision 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13–15, 2023, Proceedings, Part III

Loss Filtering Factor for Crowd Counting.- Classifier Decoupled Training for Black-Box Unsupervised Domain Adaptation.- Unsupervised Concept Drift Detection via Imbalanced Cluster Discriminator Learning.- Unsupervised Domain Adaptation for Optical Flow Estimation.- Continuous Exploration via Multiple Perspectives in Sparse Reward Environment.- Network Transplanting for the Functionally Modular Architecture.- TiAM-GAN: Titanium Alloy Microstructure Image Generation Network.- A Robust Detection and Correction Framework for GNN-based Vertical Federated Learning.- QEA-Net: Quantum-Effects-based Attention Networks.- Learning Scene Graph for Better Cross-Domain Image Captioning.- Enhancing Rule Learning on Knowledge Graphs through Joint Ontology and Instance Guidance.- Explore Across-Dimensional Feature Correlations for Few-Shot Learning.- Pairwise-emotion Data Distribution Smoothing for Emotion Recognition.- SIEFusion: Infrared and Visible Image Fusion via Semantic Information Enhancement.- DeepChrom: A Diffusion-Based Framework for Long-Tailed Chromatin State Prediction.- Adaptable Conservative Q-Learning for Offline Reinforcement Learning.- Boosting Out-of-Distribution Detection with Sample Weighting.- Causal discovery via the subsample based reward and punishment mechanism.- Local Neighbor Propagation Embedding.- Inter-class sparsity based non-negative transition sub-space learning.- Incremental Learning Based on Dual-branch Network.- Inter-Image Discrepancy Knowledge Distillation for Semantic Segmentation.- Cascaded Bilinear Mapping Collaborative Hybrid Attention Modality Fusion Model.- CasFormer: Cascaded Transformer based on Dynamic Voxel Pyramid for 3D Object Detection from Point Clouds.- Generalizable and Accurate 6D Object Pose Estimation Network.- An Internal-external Constrained Distillation Framework for Continual Semantic Segmentation.- MTD: Multi-Timestep Detector for Delayed Streaming Perception.- Semi-Direct SLAM with Manhattan for Indoor Low-texture Environment.- L2T-BEV: Local Lane Topology Prediction from Onboard Surround-View Cameras in Bird’s Eye View Perspective.- CCLane: Concise Curve Anchor-based Lane Detection Model with MLP-Mixer.- Uncertainty-aware Boundary Attention Network for Real-time Semantic Segmentation.- URFormer: Unified Representation LiDAR-Camera 3D Object Detection with Transformer.- A Single-Stage 3D Object Detection Method Based on Sparse Attention Mechanism.- WaRoNav: Warehouse Robot Navigation Based on Multi-View Visual-Inertial Fusion.- Enhancing Lidar and Radar Fusion for Vehicle Detection in Adverse Weather via Cross-Modality Semantic Consistency.- Enhancing Active Visual Tracking under Distractor Environments.- Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentation.- Cross-task Physical Adversarial Attack against Lane Detection System Based on LED Illumination Modulation.- RECO: Rotation Equivariant COnvolutional Neural Network for Human Trajectory Forecasting.- FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection