Lin / Cheng / He Pattern Recognition and Computer Vision

7th Chinese Conference, PRCV 2024, Urumqi, China, October 18–20, 2024, Proceedings, Part III
Erscheinungsjahr 2024
ISBN: 978-981-97-8502-5
Verlag: Springer Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 15033, 512 Seiten, eBook

Reihe: Lecture Notes in Computer Science

This 15-volume set LNCS 15031-15045 constitutes the refereed proceedings of the 7th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2024, held in Urumqi, China, during October 18–20, 2024.

The 579 full papers presented were carefully reviewed and selected from 1526 submissions. The papers cover various topics in the broad areas of pattern recognition and computer vision, including machine learning, pattern classification and cluster analysis, neural network and deep learning, low-level vision and image processing, object detection and recognition, 3D vision and reconstruction, action recognition, video analysis and understanding, document analysis and recognition, biometrics, medical image analysis, and various applications.

Zielgruppe

Research

Autoren/Hrsg.

Lin, Zhouchen

Cheng, Ming-Ming

He, Ran

Ubul, Kurban

Silamu, Wushouer

Zha, Hongbin

Zhou, Jie

Liu, Cheng-Lin

Inhaltsverzeichnis

ST-RetNet: A Long-term Spatial-Temporal Traffic Flow Prediction Method.- Foreground-Background Partitioning and Feature Fusion for Weakly Supervised Fine-grained Image Recognition.- DARTS-CGW: Research on Differentiable Neural Architecture Search Algorithm Based on Coarse Gradient Weighting.- PanoDthNet: Depth estimation based on indoor and outdoor panoramic images.- A Supervised Domain Adaptation Method with Alignment Regularization for Low-light Facial Expression Recognition.- DiffuSaliency: Synthesizing Multi-Object Images with Masks for Semantic Segmentation Using Diffusion and Saliency Detection.- EFOA: Enhancing Out-of-Distribution Detection by Fake Outlier Augmentation.- Fine-tuning of CLIP in Few-shot Scenarios via Supervised Contrastive Learning.- A Stereo Matching Method for Specular Objects via Cascaded Network and Joint Supervision.- An Asymmetric Game Theoretic Learning Model.- Learning 360° Optical Flow using Tangent Images and Transformer.- ODAdapter: An effective method of Semi-Supervised Object Detection for Aerial Images.- Frequency-domain Transformation-based Dynamic Gesture Recognition with skeleton.- MRGN: Multiscale Relation-gated Graph Network for Entity Alignment.- Adaptive Selective Knowledge Distillation: not blindly accepting teachers as Oracles.- Periodic Iterative Segmentation-Colorization Training: Line Drawing Colorization Using Text Tag with CBAMCat.- Histogram Prediction and Equalization for Indoor Monocular Depth Estimation.- SheepNet: Rapid Sheep Face Recognition Based on Attention and Knowledge Distillation.- LPMANet:A Lightweight Partial Multilayer Aggregation Network for Tiny Drone Detection.- HiTraj: Heterogeneous Interaction Learning with Transformers for Trajectory Prediction.- Adaptive Knowledge Matching for Exemplar-Free Class-Incremental Learning

Focusing on Significant Guidance: Preliminary Knowledge Guided Distillation.- ESTOR:Enumerate-Specify-Tutor Mechanism Used of Lexicon in Chinese NER.- EBSD: Short Text Sentiment Classification Using Sentence Vector Enhancement Mechanism.- CEDP-YOLO: UAV Object Detection Based on Context Enhancement and Dynamic Perception.- TLLFusion: An End-to-End Transformer-Based Method for Low-Light Infrared and Visible Image Fusion.- BD-YOLO : High-precision lightweight concrete bubble detector based on YOLOv7.- Semantic Consistency-Enhanced Refined Hashing for Fine-Grained Image Retrieval.- Frequency Feature Enhanced Mix Calibration Attention Network for Sequential Recommendation.- CFMISA: Cross-modal Fusion of Modal Invariant and Specific Representations for Multimodal Sentiment Analysis.- A Privacy-Preserving Source Code Vulnerability Detection Method.- Physically Informed Prior and Cross-Correlation Constraint for Fine-grained Road Crack Segmentation.- AFSNet: Adaptive Feature Suppression Network for Remote Sensing Image Change Detection.- BIVL-Net: Bidirectional Vision-Language Guidance for Visual Question Answering.- Enhancing Task Identification through Pseudo-OOD Features for Class-Incremental Learning.