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

ISBN-13: 9789819985425 / Angielski

Qingshan Liu; Hanzi Wang; Zhanyu Ma

Spis treści

A Quantum-based Attention Mechanism in Scene Text Detection.- NCMatch: Semi-Supervised Learning with Noisy Labels via Noisy Sample Filter and Contrastive Learning.- Data-free Low-bit Quantization via Dynamic Multi-teacher Knowledge Distillation.- LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation.- DUFormer: Solving Power Line Detection Task in Aerial Images using Semantic Segmentation.- Space-Transform Margin Loss with Mixup for Long-tailed Visual Recognition.- A Multi-Perspective Squeeze Excitation Classifier Based on Vision Transformer for Few Shot Image Classification.- ITCNN: Incremental Learning Network Based on ITDA and Tree Hierarchical CNN.- Periodic-Aware Network for Fine-grained Action Recognition.- Learning Domain-invariant Representations from Text for Domain Generalization.- TSTD:A Cross-modal Two Stages Network with New Trans-Decoder for Point Cloud Semantic Segmentation.- NeuralMAE: Data-Efficient Neural Architecture Predictor with Masked Autoencoder.- Co-Regularized Facial Age Estimation with Graph-Causal Learning.- Online Distillation and Preferences Fusion for Graph Convolutional Network-based Sequential Recommendation.- Grassmann Graph Embedding for Few-Shot Class Incremental Learning.- Global Variational Convolution Network for Semi-Supervised Node Classification on Large-scale Graphs.- Frequency Domain Distillation for Data-Free Quantization of Vision Transformer.- An ANN-Guided Approach to Task-Free Continual Learning with Spiking Neural Networks.- Multi-Adversarial Adaptive Transformers for Joint Multi-Agent Trajectory Prediction.- Enhancing Open-Set Object Detection via Uncertainty-Boxes Identification.- Interventional Supervised Learning for Person Re-Identification.- DP-INNet: Dual-Path Implicit Neural Network for Spatial and Spectral Features Fusion in Pan-sharpening.- Stable Visual Pattern Mining via Pattern Probability Distribution.- Dynamic Visual Prompt Tuning for Parameter Efficient Transfer Learning.- C-volution: A Hybrid operator for Visual Recognition.- Motor Imagery EEG Recognition Based on an Improved Convolutional Neural Network with Parallel Gate Recurrent Unit.- A Stable Vision Transformer for Out-of-Distribution Generalization.- Few-Shot Classification with Semantic Augmented Activators.- MixPose: 3D Human Pose Estimation with Mixed Encoder.- Image Manipulation Detection Based on Ringed Residual Edge Artifact Enhancement and Multiple Attention Mechanisms.- Improving Masked Autoencoders by Learning Where to Mask.- An Audio Correlation-Based Graph Neural Network for Depression Recognition.- Dynamic Gesture Recognition based on 3D Central Difference Separable Residual LSTM Coordinate Attention Networks.- QESAR: Query Effective Decision-based Attack on Skeletal Action Recognition.- A Closer Look at Few-shot Object Detection.- Learning-without-Forgetting via Memory Index in Incremental Object Detection.- SAMDConv: Spatially Adaptive Multi-scale Dilated Convolution.- SADD:Generative Adversarial Networks via Self-Attention and Dual Discriminator in Unsupervised Domain Adaptation.- ELFLN: An Efficient Lightweight Facial Landmark Network Based on Hybrid Knowledge Distillation.- Enhancing Continual Noisy Label Learning with Uncertainty-based Sample Selection and Feature Enhancement