STFusion: Strided Temporal Feature Fusion for Multi-View 3D Object Detection

IBS-EMA: Mitigating Test-Time Prompt Distribution Shift for Medical Segment Anything Models

CARR: Cross-modal Adaptation with Reverse Reasoning for Medical Visual Question Answering

Improving Cross-Date Generalization in Multispectral Crop-Weed Segmentation via Shallow Feature-Statistics Mixing

DTDN: A Deep Transfer Diagnostic Network with Hierarchical Alignment for Cross-Domain Industrial Fault Detection

CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models

A Review of Deep Learning-Based Digital Restoration Methods for Murals

AEFNet: Adaptive Edge Fusion Network for Railway Color Steel Building Detection

WMCrack: a hybrid CNN-Mamba network based on Haar wavelet transform for pavement crack segmentation

Geometric-Equivariant Blind-Spot Network for Self-Supervised Intra-operative OCT Denoising

Graph-structured sparse transformer with semantic priors for multimodal video summarization

URF-Loc: Uncertainty-Aware Frequency-Spatial Network for GNSS-Denied UAV Geo-Localization

OSO-DETR: Optimized Small-Object Detection with an Efficient DETR

SOG-Net: A Hybrid CNN-Transformer Network with Spectrum-Aware Purification and Semantic-Geometric Decoupling for Skin Lesion Segmentation

Strong Baselines and Structural Enhancement for Multispectral Crop–Weed Segmentation

VGM-Encoder: Dual-Encoder with Adaptive Expert Prediction Fusion for High-Resolution Remote Sensing Semantic Segmentation