1

Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching
Where is your place, Visual Place Recognition?
Zero-Shot Domain Adaptation with a Physics Prior
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation
Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation