2816 papers
The paper proposes LDMFNet, a lightweight dual-modal fusion network featuring a dual-feature backbone and specialized attention modules to achieve accurate, efficient multispectral object detection across various datasets while outperforming existing algorithms in precision and generalization.
The paper proposes BMTransUNet, a boundary-aware gated multimodal Transformer U-Net that integrates RGB and DSM data through adaptive fusion, Vision Transformer-based context modeling, and edge-enhanced skip connections to achieve superior semantic segmentation accuracy in remote sensing images.
This paper proposes a robust, two-phase filtering scheme that combines fuzzy cellular automata with Jaccard similarity and Hamming distance measures to effectively detect and remove salt and pepper noise while preserving fine image details and outperforming existing techniques.
This paper proposes the STAM framework, which integrates contrastive learning for scene-aware embeddings with a transformer encoder guided by Multi-Instance Learning attention, to effectively address contextual and temporal limitations in video anomaly detection and achieve superior accuracy on benchmark datasets.
SemPix3D proposes a hybrid framework combining a Neural Radiance Field for 3D-aware label map generation and a StyleGAN-based generator to synthesize high-quality, consistent multi-view RGB images, achieving significant improvements in diversity and FID scores over existing methods.
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.