ICPR 2024

282 papers

Top Research Directions

Research directions most represented by ICPR 2024 papers.

Eliminating Spurious Feature Reliance in Medical Imaging Models 2
Preserving Model Utility During Machine Unlearning 2
Generalizing Deep Learning Methods Beyond Image Classification 2
Efficient Training and Inference for Diffusion Models 2
Machine Unlearning for Regulatory Data Deletion Requirements 2
Mitigating Input Perturbation Sensitivity in Deep Networks 2
Generalizing from Synthetic Data to the Real World 2
Feature Detection via Region Stability Across Thresholds 1
LiDAR Reflectivity for Material Aware 3D Perception 1
Direct Signal Prediction in Diffusion Models 1
Decoupling Latent Semantics from Pixel Reconstruction 1
Structural Alignment of Correlated Graphs 1
Continuous Quality Regression for Alignment and Evaluation 1
Viewpoint Specific Specialization in Deep Networks 1
Quantitative Geometric Descriptors for Medical Risk Stratification 1

Top Authors

AuthorPapers
Xiaojun Wu10
Tianyang Xu8
Congcong Wen5
Hao Huang5
Josef Kittler5
Nalini K. Ratha5
Yi Fang5
Concetto Spampinato4
Costantino Grana4
Federico Bolelli4
Rita Cucchiara4
Shuaihang Yuan4
Simone Palazzo4
Takashi Shibata4
Wei-Shi Zheng4
Anthony Tzes3
Elisa Ricci3
Jinkyu Kim3
Kun Zhu3
Marwan Torki3

Impactful Papers

Papers from ICPR 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Rare Fungi Image Classification Based on Few-Shot Learning and Data Augmentation
Reassembling Broken Objects Using Breaking Curves
Recognition of Online Handwritten Chinese Texts in Any Writing Direction via Stroke Classification Based Over-Segmentation
Recommendation of Data-Free Class-Incremental Learning Algorithms by Simulating Future Data
Reliable Semantic Understanding for Real World Zero-Shot Object Goal Navigation
Restoring Noisy Images Using Dual-Tail Encoder-Decoder Signal Separation Network
Rethinking Attention Module Design for Point Cloud Analysis
RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision
Robust Feature Space Organization with Distillation for Few-Shot Object Detection
ROI-Aware Dynamic Network Quantization for Neural Video Compression
RSTAN: Residual Spatio-Temporal Attention Network for End-to-End Human Fall Detection
S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-Based Learning for Action Recognition
SalFoM: Dynamic Saliency Prediction with Video Foundation Models
Sampling Rate Adaptive Speaker Verification from Raw Waveforms
Satellite State Prediction and Maneuver Detection Analysis Using NCDEs
SCP: A Structure Combination Pruning Method via Structured Sparse for Deep Convolutional Neural Networks
SDformerFlow: Spiking Neural Network Transformer for Event-based Optical Flow
SEANet: Rethinking Skip-Connections Design in Encoder-Decoder Networks via Synergistic Spatial-Spectral Fusion for LDCT Denoising
Sea-ShipNet: Detect Any Ship in SAR Images
SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning
Secure Sleep Apnea Detection with FHE and Deep Learning on ECG Signals
Self-distilled Dual-Network with Pixel Screening Loss for Blind Image Deblurring
Semantically Consistent Person Image Generation
Semantic Correlation Adaptation for Union-Set Multi-label Image Recognition
Single-Image Driven 3D Viewpoint Training Data Augmentation for Effective Label Recognition
SITAR: Semi-supervised Image Transformer for Action Recognition
Size-Modulated Deformable Attention in Spatio-Temporal Video Grounding Pipelines
Sketch2Seg: Sketch-Based Image Segmentation with Pre-trained Diffusion Model
SMFuse: Two-Stage Structural Map Aware Network for Multi-focus Image Fusion
Source-Free Test-Time Adaptation For Online Surface-Defect Detection
Spatio-Temporal Domain-Aware Network for Skeleton-Based Action Representation Learning
SPK: Semantic and Positional Knowledge for Zero-Shot Referring Expression Comprehension
Split-DNN Computing for Video Analytics
StableTalk: Advancing Audio-to-Talking Face Generation with Stable Diffusion and Vision Transformer
Stereographic Projection for Embedding Hierarchical Structures in Hyperbolic Space
STNet: Small Target Detection Network for IR Imagery
Supervised Mixup: Protecting the Likely Classes for Adversarial Robustness
Sustainable and Explainable Neural Network for Real-Time Time Series Classification
SWave: Improving Vocoder Efficiency by Straightening the Waveform Generation Path
Synthesizing Operationally Safe Controllers for Human-in-the-Loop Human-in-the-Plant Hybrid Close Loop Systems
Synthetic Video Generation for Weakly Supervised Cross-Domain Video Anomaly Detection
TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering
Task Consistent Prototype Learning for Incremental Few-Shot Semantic Segmentation
Task Oriented Image Quality Assessment for Synthesized Images
Task Success Classification with Final State of Future Prediction for Robot Control Planning
TaylorShift: Shifting the Complexity of Self-attention from Squared to Linear (and Back) Using Taylor-Softmax
TDiffSal: Text-Guided Diffusion Saliency Prediction Model for Images
Temporal Divide-and-Conquer Anomaly Actions Localization in Semi-supervised Videos with Hierarchical Transformer
Temporal Insight Enhancement: Mitigating Temporal Hallucination in Video Understanding by Multimodal Large Language Models
Text2Street: Controllable Text-to-Image Generation for Street Views

« prev Page 5/6 next »