STAU-Net: A Spatial Structure Attention Network for 3D Coronary Artery Segmentation
Hierarchical Pretrained Backbone Vision Transformer for Image Classification in Histopathology
HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images
Unreliability-Aware Disentangling for Cross-Domain Semi-supervised Pedestrian Detection
Super-Attention for Exemplar-Based Image Colorization
Fully Transformer Network for Change Detection of Remote Sensing Images
ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval
MGTR: End-to-End Mutual Gaze Detection with Transformer
Decanus to Legatus: Synthetic Training for 2D-3D Human Pose Lifting
MatchFormer: Interleaving Attention in Transformers for Feature Matching
Deep Active Ensemble Sampling for Image Classification
CMT-Co: Contrastive Learning with Character Movement Task for Handwritten Text Recognition