Prcv 2024

221 papers

Top Research Directions

Research directions most represented by Prcv 2024 papers.

Why Standard Training Budgets Underestimate Model Potential 1
Training-Time Auxiliary Supervision for Zero-Overhead Inference 1
Learnable Residual Scaling for Deep Networks 1
Real Time View Synthesis with 3D Gaussian Splatting 1
Adaptive Attention Sparsity for Efficient Transformers 1
Resolving Feature Matching Ambiguities in Stereo Vision 1
Learning Dense Object Boundaries from Sparse Supervision 1
Synthetic Viewpoint Augmentation for Robust Visual Learning 1
Synthetic Anomalies and Distillation for Robust Anomaly Detection 1
Preventing Entropy Collapse in Reinforcement Learning 1
Preserving Structural Fidelity in Generative Medical Imaging 1
Robustness to Clinical Noise and Imaging Artifacts 1
Optimizing the Mixing Ratio of Synthetic and Real Data 1
Multi-resolution Hash Encoding for Coordinate Based Networks 1
Modeling Temporal Dependencies with Recurrent Neural Networks 1

Top Authors

AuthorPapers
Huchuan Lu4
Xiaojun Wu4
Bin Li3
Haoji Hu3
Lechao Cheng3
Miao Zhang3
Mingliang Xu3
Richang Hong3
Ruixuan Wang3
Xiaoheng Jiang3
Yijun Bei3
Zunlei Feng3
Chao Gou2
Chengji Wang2
Dongyu Zhang2
Feng Lu2
Huaibo Huang2
Jiangnan Ye2
Jiankang Chen2
Jie Cao2

Impactful Papers

Papers from Prcv 2024 that shaped research clusters.

Influential

Papers

Title
Focal Aggregation Transformer for Light Field Image Super-Resolution
Focal Perception Transformer for Light Field Salient Object Detection
Foreground-Background Partitioning and Feature Fusion for Weakly Supervised Fine-Grained Image Recognition
Frequency Adapter and Spatial Prompt Network for All-in-One Blind Image Restoration
Frequency-Domain Transformation-Based Dynamic Gesture Recognition with Skeleton
Fusion Network Based on Motion Learning and Image Feature Representation for Micro-Expression Recognition
Generalizing Soft Actor-Critic Algorithms to Discrete Action Spaces
Generative Steganography Based on Dual-Branch Flow
GOP: A Group Object Perception Framework for Optical Remote Sensing
GridMask: An Efficient Scheme for Real Time Curved Scene Text Detection
Growing with the Help of Multiple Teachers: Lightweight and Noise-Resistant Student Model for Medical Image Classification
H2LMER: A Cross Frame-Rate Representation Alignment Framework for Micro-expression Recognition
Histogram Prediction and Equalization for Indoor Monocular Depth Estimation
Image-Centered Pseudo Label Generation for Weakly Supervised Text-Based Person Re-Identification
Improve Corruption Robustness of Intracellular Structures Segmentation in Fluorescence Microscopy Images
[inline-graphic not available: see fulltext] TableRocket: An Efficient and Effective Framework for Table Reconstruction
Instance-Level Scaling and Dynamic Margin-Alignment Knowledge Distillation
Integrated Recognition of Arbitrary-Oriented Multi-line Billet Number
Inter-Class Correlation-Based Online Knowledge Distillation
Interpretable Unsupervised Homography Estimation
Joint Multi-person Body Detection and Orientation Estimation Via One Unified Embedding
JPA: A Joint-Part Attention for Mitigating Overfocusing on 3D Human Pose Estimation
L2FIG-Tracker: L2-Norm Based Fusion with Illumination Guidance for RGB-D Object Tracking
Language-Skeleton Pre-training to Collaborate with Self-Supervised Human Action Recognition
LarvSeg: Exploring Image Classification Data for Large Vocabulary Semantic Segmentation via Category-Wise Attentive Classifier
Learning 360° Optical Flow Using Tangent Images and Transformer
Learning Fine-Grained and Semantically Aware Mamba Representations for Tampered Text Detection in Images
Learning Frequency and Structure in UDA for Medical Object Detection
Learning Fully Parametric Subspace Clustering
Lightweight and Multi-scale Adaptive Network for Infrared Small Target Detection
Local Point Matching for Collaborative Image Registration and RGBT Anti-UAV Tracking
Low-Light Light-Field Image Enhancement With Geometry Consistency
MagicGS: Combining 2D and 3D Priors for Effective 3D Content Generation
Making the Primary Task Primary: Boosting Few-Shot Classification by Gradient-Biased Multi-task Learning
Mamba-FETrack: Frame-Event Tracking via State Space Model
MaskEditor: Instruct 3D Object Editing with Learned Masks
Masked Visual Pre-training for RGB-D and RGB-T Salient Object Detection
Mask-Guided Clothes-Irrelevant and Background-Irrelevant Network with Knowledge Propagation for Cloth-Changing Person Re-identification
MedPrompt: Cross-modal Prompting for Multi-task Medical Image Translation
Meply: A Large-scale Dataset and Baseline Evaluations for Metastatic Perirectal Lymph Node Detection and Segmentation
Mitigating Hallucination in Visual-Language Models via Re-balancing Contrastive Decoding
MIT: Multi-cue Injected Transformer for Two-Stage HOI Detection
Mixture-of-Hand-Experts: Repainting the Deformed Hand Images Generated by Diffusion Models
Modality-Shared Prototypes for Enhanced Unsupervised Visible-Infrared Person Re-Identification
MOFTrack: Multi-object Formation Tracking in Remote Sensing Videos
MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling
MRGN: Multiscale Relation-Gated Graph Network for Entity Alignment
MTFusion: Reconstructing Any 3D Object from Single Image Using Multi-word Textual Inversion
Multi-3D Occlusion Mask Learning for Flexible Occlusion Removal in Neural Radiance Fields
Multi-class Token-Guided End-to-End Weakly Supervised Image Semantic Segmentation Method

« prev Page 3/5 next »