2794 papers
This paper proposes a lightweight, improved YOLOv8n model for UAV-based forest fire detection that integrates dynamic convolution, a multi-aware detection head, and cross-spatial attention to significantly enhance small target accuracy and reduce false alarms while maintaining a compact size suitable for real-time onboard deployment.
The paper proposes SCEESR, a novel one-step diffusion-based super-resolution framework that utilizes a ControlNet mechanism for semantic edge guidance and a hybrid loss function to effectively balance structural integrity, perceptual quality, and inference speed in real-world image restoration.
This paper proposes FMA-DETR, an adaptive Transformer framework that integrates a Feature Refinement Network, a Multi-scale Spatial-Channel Mixed Attention module, and an Adaptive Frequency-aware Fusion module to effectively overcome speckle noise and background complexity for high-accuracy dense small target detection in SAR images.
This study evaluates the ability of various large language models to understand Korean indirect speech acts by constructing a specialized dataset and employing both automated and human assessments, revealing that while proprietary models like Claude3-Opus outperform open-source alternatives, none yet match human-level proficiency in interpreting context-dependent intentions.
The paper proposes EGDIS, an edge-guided document image steganography method that utilizes an adaptive Canny algorithm and a Transformer-based Cross-Attention Fusion Network to integrate edge features with raw images and secret messages, thereby achieving superior embedding performance and visual quality on standard datasets.
This paper proposes an autonomous collision avoidance decision-making method for Unmanned Surface Vehicles (USVs) that integrates UAV visual perception with a Prioritized Experience Replay-enhanced Dueling Double Deep Q-Network (PD3QN) algorithm and a COLREGs-compliant reward function to achieve safe, efficient, and adaptable navigation.
This paper presents an interpretable computational framework that leverages multisensory tactile data, particularly thermal and compliance cues from pressing, static, and sliding interactions, to effectively model human material perception and enhance robotic tactile recognition.
This paper presents a manually annotated Bulgarian dataset to evaluate bias detection, revealing high agreement among human annotators but significant divergence between humans and large language models, while demonstrating that Bulgarian-language prompting improves model alignment with human judgments.
This paper proposes an improved Informer-based model incorporating a standard deviation-based dynamic denoising algorithm and a volatility-aware adaptive sampling mechanism to enhance the accuracy and stability of enterprise cost predictions, demonstrating superior performance over existing methods on both enterprise and benchmark datasets.
This paper introduces CLEM, a behavior-centric software quality framework that measures structural change absorption through version-control heuristics to classify development activities and generate neutral or context-weighted metrics, demonstrating its ability to distinguish structural patterns across diverse repositories while showing limited correlation with defect prediction.