DTCM: Diffusion Transformer-based High-fidelity Virtual Try-on with Token Concatenation and Region Masking

Mitigating Non-Discriminative Consistency Bias for Optical–SAR Ship Re-Identification

Task-Specific Multi-Branch Network: Toward Image Restoration under Multiple Weather Conditions

Fast Video Desnowing with Tri-Branch Spatio-Temporal Mixing

A Light-weight Self-Prompting Foundation Model for Automatous Video Object Segmentation

MGMMix: Motion-Guided Multi-scale MEMix for Micro-Expression Recognition

MART-DETR:Mamba-Enhanced Real-Time DETR for UAV Small Object Detection

Dual-stage Quality-Aware Alignment Framework for Zero-shot Referring Image Segmentation

DFF-D-FINE: A Dual-Focus Fusion and Feature-Preserving D-FINE Framework for UAV Tiny Object Detection

Source-free Cross-domain Knowledge Distillation for Nighttime Hazy Tracking

CRAFT: Calibrated Robust Adaptive Framework for Texture-heterogeneity

AHRS-Net: Anatomical Hierarchical Refining Semantic Network for Anatomy-aware Spatially Grounded Radiology Report Generation

GeoCon-Diff: Geometrically-Consistent Diffusion for High-Fidelity 3D Reconstruction from a Single Occluded Image

H-VLA: A Robust Neuro-Symbolic Framework via Cross-Modal Disagreement and Retrieval-Augmented Adaptation for Fine-Grained Defect Classification

METER-DETR: A Water Meter Reading Recognition Algorithm Based on RT-DETR Under Complex Imaging Conditions

ORCA: Orthogonal Residual Cross-modal Adaptation for Choroidal Thickness Estimation from Multimodal Fundus Images