LEADER 13615nam 22008655 450 001 996587868503316 005 20231225195642.0 010 $a981-9985-46-3 024 7 $a10.1007/978-981-99-8546-3 035 $a(MiAaPQ)EBC31040364 035 $a(Au-PeEL)EBL31040364 035 $a(DE-He213)978-981-99-8546-3 035 $a(EXLCZ)9929467402600041 100 $a20231225d2024 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aPattern Recognition and Computer Vision$b[electronic resource] $e6th Chinese Conference, PRCV 2023, Xiamen, China, October 13?15, 2023, Proceedings, Part IX /$fedited by Qingshan Liu, Hanzi Wang, Zhanyu Ma, Weishi Zheng, Hongbin Zha, Xilin Chen, Liang Wang, Rongrong Ji 205 $a1st ed. 2024. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2024. 215 $a1 online resource (520 pages) 225 1 $aLecture Notes in Computer Science,$x1611-3349 ;$v14433 311 08$aPrint version: Liu, Qingshan Pattern Recognition and Computer Vision Singapore : Springer,c2024 9789819985456 327 $aIntro -- Preface -- Organization -- Contents - Part IX -- Neural Network and Deep Learning II -- Decoupled Contrastive Learning for Long-Tailed Distribution -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Online Tail Samples Discovery -- 3.2 Hard Negatives Generation -- 3.3 Contrastive Loss Reweighting -- 4 Experiments -- 4.1 Linear Probing Evaluations -- 4.2 Analysis -- 5 Conclusion -- References -- MFNet: A Channel Segmentation-Based Hierarchical Network for Multi-food Recognition -- 1 Introduction -- 2 Related Work -- 3 Food Image Datasets Construction -- 3.1 Food Images Collection -- 3.2 Annotation and Statistics -- 4 Method -- 4.1 CWF: Channel-Level Whole Image Food Information Acquisition -- 4.2 SGC: Spatial-Level Global Information Constraints -- 4.3 SPF: Spatial-Level Part Image Food Information Acquisition -- 5 Experiments -- 5.1 Datasets and Evaluation Metrics -- 5.2 Implementation Details -- 5.3 Performance Comparison with Other Method -- 5.4 Ablation Study -- 5.5 Visualization Result -- 6 Conclusion -- References -- Improving the Adversarial Robustness of Object Detection with Contrastive Learning -- 1 Introduction -- 2 Related Work -- 2.1 Adversarial Attacks -- 2.2 Adversarial Defenses -- 2.3 Contrastive Learning -- 3 Proposed Method -- 3.1 Contrastive Learning Module -- 3.2 Contrastive Adversarial SSD -- 3.3 Contrastive Adversarial YOLO -- 3.4 Adversarial Training with Contrastive Learning -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Defense Capability Evaluation -- 5 Conclusion -- References -- CAWNet: A Channel Attention Watermarking Attack Network Based on CWABlock -- 1 Introduction -- 2 Related Work -- 2.1 Attacked Watermarking Algorithm -- 2.2 Watermarking Attack Techniques -- 3 The Proposed Method -- 3.1 CAWNet -- 3.2 Attention Mechanism -- 3.3 CWABlock -- 4 Experiments and Results Analysis. 327 $a4.1 Evaluation Criteria -- 4.2 Ablation Experiment -- 4.3 Effects of Traditional Attack and Different Deep Learning Attack Methods -- 4.4 Stability and Suitability Testing -- 5 Conclusion -- References -- Global Consistency Enhancement Network for Weakly-Supervised Semantic Segmentation -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Middle-Level Feature Auxiliary -- 3.2 Intra-class Consistency Enhancement -- 3.3 Critical Region Suppression -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Implementation Details -- 4.3 CAM Performance -- 4.4 Segmentation Performance -- 4.5 Ablation Study -- 5 Conclusion -- References -- Enhancing Model Robustness Against Adversarial Attacks with an Anti-adversarial Module -- 1 Introduction -- 2 Related Works -- 2.1 Gradient Masking -- 2.2 Adversarial Examples Detection -- 2.3 Robust Optimization -- 3 Methods -- 3.1 Counter-Adversarial Module -- 3.2 Enhancing Defense Against Black-Box Attacks -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 Main Results -- 4.3 Ablation Study -- 5 Conclusion -- References -- FGPTQ-ViT: Fine-Grained Post-training Quantization for Vision Transformers -- 1 Introduction -- 2 Related Work -- 2.1 CNN Quantization -- 2.2 Vision Transformer Quantization -- 3 Method -- 3.1 FGPTQ-ViT Framework -- 3.2 Fine-Grained ViT Quantization -- 3.3 Adaptive Piecewise Point Search Algorithm -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Experimental Results -- 4.3 Ablation Study -- 5 Conclusion -- References -- Learning Hierarchical Representations in Temporal and Frequency Domains for Time Series Forecasting -- 1 Introduction -- 2 Related Work -- 2.1 Convolutional and Transformer Models -- 2.2 Fourier Transform and Decomposition Models -- 3 Proposed Approach -- 3.1 Time Series Hierarchical Decomposition -- 3.2 Trend Forecasting Module -- 3.3 Seasonal Forecasting Module -- 4 Experiments. 327 $a4.1 Dataset -- 4.2 Baselines and Setup -- 4.3 Implement Details and Evaluation Metrics -- 4.4 Main Results -- 4.5 Ablation Study -- 5 Conclusion -- References -- DeCAB: Debiased Semi-supervised Learning for Imbalanced Open-Set Data -- 1 Introduction -- 2 Related Work -- 2.1 General SSL Methods -- 2.2 Imbalanced SSL Methods -- 2.3 Open-Set SSL Methods -- 3 Proposed Method -- 3.1 Problem Setting and Notations -- 3.2 Class-Aware Threshold -- 3.3 Selective Sample Reweighting -- 3.4 Positive-Pair Reweighting -- 3.5 Overall Training Objective -- 4 Experimental Results -- 4.1 Experimental Settings -- 4.2 Numerical Comparison -- 4.3 Analysis on Impact of OOD Data -- 4.4 Ablation Experiments -- 5 Conclusion -- A Analysis of the Effect of OOD Data to SSL Methods -- B Algorithm Flowchart -- C Visualized Comparison -- References -- An Effective Visible-Infrared Person Re-identification Network Based on Second-Order Attention and Mixed Intermediate Modality -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Second-Order Attention Module -- 3.2 Mixed Intermediate Modality Module -- 3.3 Optimization -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Comparison with State-of-the-Art Methods -- 4.4 Ablation Study -- 5 Conclusion -- References -- Quadratic Polynomial Residual Network for No-Reference Image Quality Assessment -- 1 Introduction -- 2 Related Work -- 2.1 IQA and Information Entropy -- 2.2 IQA and Deep Learning -- 3 Design of Network -- 3.1 Two-Dimensional Information Entropy for Patch Sampling -- 3.2 Network Architecture -- 4 Experiment Result -- 5 Conclusion -- References -- Interactive Learning for Interpretable Visual Recognition via Semantic-Aware Self-Teaching Framework -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Patch Selection Strategy -- 3.2 Semantic-Aware Self-Teaching -- 4 Experiments. 327 $a5 Conclusion -- References -- Adaptive and Compact Graph Convolutional Network for Micro-expression Recognition -- 1 Introduction -- 2 Related Work -- 2.1 Structure Graph -- 3 Method -- 3.1 Cheek Included Facial Graph -- 3.2 Tightly Connected Strategy -- 3.3 Small Region Module -- 3.4 Adaptive and Compact Graph Convolutional Network -- 4 Experiments -- 4.1 Datasets and Implementation Details -- 4.2 Quantitative Results -- 4.3 Ablation Study -- 5 Conclusion -- References -- Consistency Guided Multiview Hypergraph Embedding Learning with Multiatlas-Based Functional Connectivity Networks Using Resting-State fMRI -- 1 Introduction -- 2 Methods -- 2.1 Hypergraph and Hypergraph Construction with FCN -- 2.2 Proposed CG-MHGEL with Multiatlas-Based FCNs -- 3 Experiment -- 3.1 Experimental Settings -- 3.2 Experimental Results and Analysis -- 4 Conclusion -- References -- A Diffusion Simulation User Behavior Perception Attention Network for Information Diffusion Prediction -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Problem Definition -- 3.2 Model Framework -- 3.3 Diffusion Simulation User Behavior Embedding -- 3.4 User Behavior Fusion Transformer -- 3.5 Cascade Perception Attention Network -- 3.6 Diffusion Prediction -- 4 Experiment -- 4.1 Results -- 5 Conclusion -- References -- A Representation Learning Link Prediction Approach Using Line Graph Neural Networks -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 The NLG-GNN Framework -- 4 Experimental Setup -- 4.1 Experimental Results -- 5 Conclusion -- References -- Event Sparse Net: Sparse Dynamic Graph Multi-representation Learning with Temporal Attention for Event-Based Data -- 1 Introduction -- 2 Related Work -- 2.1 Graph Representations -- 2.2 Dynamic Graph Neural Network -- 3 Methods -- 3.1 Local Self Attention -- 3.2 Global Temporal Attention -- 4 Experiments -- 4.1 Datasets. 327 $a4.2 Setup -- 4.3 Continuous Data Inductive Learning -- 4.4 Discrete Data Inductive Learning -- 4.5 Discrete Data Transductive Learning -- 5 Conclusion -- References -- Federated Learning Based on Diffusion Model to Cope with Non-IID Data -- 1 Introduction -- 2 Method -- 2.1 The First Stage -- 2.2 The Second Stage -- 2.3 The Third Stage -- 3 Experiments -- 3.1 Setup -- 3.2 Performance Comparison -- 3.3 Experimental Factors Analysis -- 4 Conclusion -- References -- SFRSwin: A Shallow Significant Feature Retention Swin Transformer for Fine-Grained Image Classification of Wildlife Species -- 1 Introduction -- 2 Related Works -- 2.1 Convolutional Neural Network -- 2.2 Vision Transformer -- 3 Methodology -- 3.1 Self-attentive Mechanism Based on Shifted Windows -- 3.2 Random Data Enhancement -- 4 Evaluation -- 4.1 Datasets and Implementation Details -- 4.2 Model Complexity Analysis -- 5 Conclusion -- References -- A Robust and High Accurate Method for Hand Kinematics Decoding from Neural Populations -- 1 Introduction -- 2 Related Works -- 2.1 iBMI Cortical Control Decoding Algorithm -- 2.2 Attention Module -- 3 Method -- 3.1 Neural Recording System and Behavioral Task -- 3.2 Experimental Procedure of the Cortical Control -- 3.3 Temporal-Attention QRNN -- 3.4 Evaluation Metrics -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Comparison of Decoding Results -- 4.3 Discussion -- 5 Conclusion -- References -- Multi-head Attention Induced Dynamic Hypergraph Convolutional Networks -- 1 Introduction -- 2 Related Work -- 2.1 Neural Networks on Graph -- 2.2 Neural Networks on Hypergraph -- 3 Methodology -- 3.1 Definitions and Notations -- 3.2 Hypergraph Construction -- 3.3 Vertex Convolution -- 3.4 Hyperedge Convolution -- 3.5 The Proposed Algorithm -- 4 Experiments -- 4.1 Datasets -- 4.2 Experimental Settings -- 4.3 Results and Discussion. 327 $a4.4 Ablation Studies. 330 $aThe 13-volume set LNCS 14425-14437 constitutes the refereed proceedings of the 6th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2023, held in Xiamen, China, during October 13?15, 2023. The 532 full papers presented in these volumes were selected from 1420 submissions. The papers have been organized in the following topical sections: Action Recognition, Multi-Modal Information Processing, 3D Vision and Reconstruction, Character Recognition, Fundamental Theory of Computer Vision, Machine Learning, Vision Problems in Robotics, Autonomous Driving, Pattern Classification and Cluster Analysis, Performance Evaluation and Benchmarks, Remote Sensing Image Interpretation, Biometric Recognition, Face Recognition and Pose Recognition, Structural Pattern Recognition, Computational Photography, Sensing and Display Technology, Video Analysis and Understanding, Vision Applications and Systems, Document Analysis and Recognition, Feature Extraction and Feature Selection, Multimedia Analysis and Reasoning, Optimization and Learning methods, Neural Network and Deep Learning, Low-Level Vision and Image Processing, Object Detection, Tracking and Identification, Medical Image Processing and Analysis. . 410 0$aLecture Notes in Computer Science,$x1611-3349 ;$v14433 606 $aImage processing$xDigital techniques 606 $aComputer vision 606 $aArtificial intelligence 606 $aApplication software 606 $aComputer networks 606 $aComputer systems 606 $aMachine learning 606 $aComputer Imaging, Vision, Pattern Recognition and Graphics 606 $aArtificial Intelligence 606 $aComputer and Information Systems Applications 606 $aComputer Communication Networks 606 $aComputer System Implementation 606 $aMachine Learning 615 0$aImage processing$xDigital techniques. 615 0$aComputer vision. 615 0$aArtificial intelligence. 615 0$aApplication software. 615 0$aComputer networks. 615 0$aComputer systems. 615 0$aMachine learning. 615 14$aComputer Imaging, Vision, Pattern Recognition and Graphics. 615 24$aArtificial Intelligence. 615 24$aComputer and Information Systems Applications. 615 24$aComputer Communication Networks. 615 24$aComputer System Implementation. 615 24$aMachine Learning. 676 $a006 700 $aLiu$b Qingshan$01586078 701 $aWang$b Hanzi$0927694 701 $aMa$b Zhanyu$01586079 701 $aZheng$b Weishi$01586080 701 $aZha$b Hongbin$01586081 701 $aChen$b Xilin$01586082 701 $aWang$b Liang$01071990 701 $aJi$b Rongrong$01586083 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996587868503316 996 $aPattern Recognition and Computer Vision$93872352 997 $aUNISA