Gianluca Francini

Latest

• Learnable Descriptors for Visual Search
• Learning and adapting robust features for satellite image segmentation on heterogeneous data sets
• Robust license plate recognition using neural networks trained on synthetic images
• Vehicle joint make and model recognition with multiscale attention windows
• Feature fusion for robust patch matching with compact binary descriptors
• Learning sparse neural networks via sensitivity-driven regularization
• Satellite image segmentation with deep residual architectures for time-critical applications
• Automatic License Plate recognition with Convolutional Neural Networks trained on synthetic data
• Fine-grained vehicle classification using deep residual networks with multiscale attention windows