2787 papers
This paper proposes a hybrid image compression pipeline using JPEG-XL for luminance and JPEG-2000 for chrominance, demonstrating that color components can be aggressively compressed (up to 3,000:1) while maintaining high perceptual quality and significantly reducing storage requirements.
This paper proposes a novel blockchain-based framework for distributed IoT security that integrates federated learning, IPFS, and lightweight cryptography to overcome scalability and resource constraints, achieving near-perfect accuracy (99.88%) and robust anomaly detection for real-time predictive maintenance across diverse applications.
This paper introduces LEGR, an end-to-end framework for Table Structure Recognition that replaces static geometric heuristics with learnable relational edge features and a cascaded Graph Attention Network refinement module to achieve robust, domain-invariant performance by iteratively correcting predictions through learned global layout reasoning.
This study presents an explainable Android-based decision support system that utilizes an optimized XGBoost model and a computationally efficient Monte Carlo SHAP algorithm to provide real-time, interpretable predictions of high-performance concrete compressive strength directly on mobile devices.
This paper proposes a unified dual-balance framework that addresses both label and modality imbalances in long-tailed multimodal relation extraction through a modality-branch fusion strategy for cross-modal consistency and a prior-aware class calibrator for improved tail relation recognition, demonstrating competitive performance on MNRE and MORE benchmarks.
The paper proposes Multiple Approximate-Response Agents (MARA), a parallelizable primal recovery method that generates multiple bounded-suboptimal responses to dual price queries and combines them to rapidly achieve feasible, near-optimal solutions in distributed optimization without increasing wall-clock time.
This paper introduces FPA-Net, a dual-branch deep network that leverages complex-valued frequency modeling and position-aware attention mechanisms within the HVI color space to achieve state-of-the-art low-light image enhancement with superior structural fidelity and color consistency.
This paper proposes the MeanRadius-SMOTE Graph Neural Network (MRS-GNN), a novel framework that addresses class imbalance in fault and intrusion detection by generating synthetic nodes in the embedding space and creating specialized edges to preserve graph topology, thereby significantly improving classification accuracy and AUC-ROC under extreme imbalance conditions.
This paper proposes a secure and efficient authentication scheme for Vehicular Ad-hoc Networks (VANETs) that combines ECDSA, ECDH, and HMAC with SHA-256 to ensure message integrity and session key establishment, while employing dynamic pseudonyms for privacy, a public-key-based revocation list for efficient certificate management, and GPS-based time synchronization to prevent replay attacks.
This paper proposes a robust ensemble deep learning framework that combines DenseNet, ResNet, and Xception models via majority voting to achieve high-accuracy detection of forest fires and smoke, outperforming individual models on both fire-only and fire-and-smoke datasets.