Prcv 2023

245 papers

Top Research Directions

Research directions most represented by Prcv 2023 papers.

Unified Backbones for Multimodal Understanding and Generation 1
Exploiting Internal Patch Recurrence across Image Scales 1
Progressive Alignment for Multimodal Representation Learning 1
The Challenge of Limited Object Diversity in Visual Datasets 1
Beyond Zero Shot Prompting in Large Language Models 1
Bootstrapping Dense Vision Labels Without Manual Annotation 1
The Computational Complexity of Hybrid Vision Architectures 1
Composite Loss Functions for Perceptual Image Restoration 1
Aligning Global Semantics with Local Spatial Precision 1
Preserving Manifold Geometry in Latent Spaces 1
Cross-Modal Pseudo-Label Projection for 3D Perception 1
Resolving Multi-View Semantic Inconsistency in 3D Scenes 1
Geometric Structure Preservation in Latent Space Learning 1
Reconstructing Thin Structures in 3D Geometry 1
Overcoming Local Receptive Field Constraints in Visual Models 1

Top Authors

AuthorPapers
Xinghao Ding8
Yue Huang8
Fei Chao5
Xingbo Dong5
Da-Han Wang4
Hui He4
Hui Zhang4
Linlin Shen4
Pingyang Dai4
Yang Lu4
Yan Zhang4
Cheng Wang3
Hanzi Wang3
Huchuan Lu3
Jinqiao Wang3
Kongming Liang3
Meng Wang3
Shaohui Lin3
Wei-Shi Zheng3
Weizhe Zhang3

Impactful Papers

Papers from Prcv 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Local Neighbor Propagation Embedding
Low-Light Image Enhancement Based on Mutual Guidance Between Enhancing Strength and Image Appearance
MaskDiffuse: Text-Guided Face Mask Removal Based on Diffusion Models
Matching-to-Detecting: Establishing Dense and Reliable Correspondences Between Images
MCKIE: Multi-class Key Information Extraction from Complex Documents Based on Graph Convolutional Network
Memory-Augmented Spatial-Temporal Consistency Network for Video Anomaly Detection
MGT: Modality-Guided Transformer for Infrared and Visible Image Fusion
Minimum Assumption Reconstruction Attacks: Rise of Security and Privacy Threats Against Face Recognition
Mining Temporal Inconsistency with 3D Face Model for Deepfake Video Detection
Misalignment Insensitive Perceptual Metric for Full Reference Image Quality Assessment
MKB: Multi-Kernel Bures Metric for Nighttime Aerial Tracking
Modality Balancing Mechanism for RGB-Infrared Object Detection in Aerial Image
Modality Interference Decoupling and Representation Alignment for Caricature-Visual Face Recognition
MS UX-Net: A Multi-scale Depth-Wise Convolution Network for Medical Image Segmentation
Multi-agent Perception via Co-attentive Communication Mechanism
Multi-atlas Representations Based on Graph Convolutional Networks for Autism Spectrum Disorder Diagnosis
Multi-behavior Enhanced Graph Neural Networks for Social Recommendation
Multi-domain Information Fusion for Key-Points Guided GAN Inversion
Multi-head Attention Induced Dynamic Hypergraph Convolutional Networks
Multi-modal Graph and Sequence Fusion Learning for Recommendation
Multi-modal Instance Refinement for Cross-Domain Action Recognition
Multi-modality Fusion Based Lung Cancer Survival Analysis with Self-supervised Whole Slide Image Representation Learning
Multimodal Topic and Sentiment Recognition for Chinese Data Based on Pre-trained Encoders
Multi-source Information Fusion for Depression Detection
Multi-stream-Based Low-Latency Viewport Switching Scheme for Panoramic Videos
Multi-task Self-supervised Few-Shot Detection
MVP-SEG: Multi-view Prompt Learning for Open-Vocabulary Semantic Segmentation
Network Transplanting for the Functionally Modular Architecture
Object-Aware Transfer-Based Black-Box Adversarial Attack on Object Detector
OKGR: Occluded Keypoint Generation and Refinement for 3D Object Detection
One Step Large-Scale Multi-view Subspace Clustering Based on Orthogonal Matrix Factorization with Consensus Graph Learning
Only Classification Head Is Sufficient for Medical Image Segmentation
Out-of-Distribution with Text-to-Image Diffusion Models
Ped-Mix: Mix Pedestrians for Occluded Person Re-identification
Penalty-Aware Memory Loss for Deep Metric Learning
Plugging Stylized Controls in Open-Stylized Image Captioning
Preference Contrastive Learning for Personalized Recommendation
PRFNet: Progressive Region Focusing Network for Polyp Segmentation
Progressive Point Cloud Generating by Shape Decomposing and Upsampling
Prompt Based Lifelong Person Re-identification
Prototypical Transformer for Weakly Supervised Action Segmentation
Pseudo Labels Refinement with Stable Cluster Reconstruction for Unsupervised Re-identification
Quality-Aware CLIP for Blind Image Quality Assessment
RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution
RecFormer: Recurrent Multi-modal Transformer with History-Aware Contrastive Learning for Visual Dialog
Recognizer Embedding Diffusion Generation for Few-Shot SAR Recognization
RECO: Rotation Equivariant COnvolutional Neural Network for Human Trajectory Forecasting
Reliable Boundary Samples-Based Proxy Pairs for Unsupervised Person Re-identification
Repdistiller: Knowledge Distillation Scaled by Re-parameterization for Crowd Counting
RGB-D Road Segmentation Based on Geometric Prior Information

« prev Page 4/5 next »