Cross-posted a short time ago from the Google Research Blog to the Official Google Blog, the research team is presenting a paper (see below) at the CVPR Conference in Miami that explains "a new technology that enables computers to quickly and efficiently identify images of more than 50,000 landmarks from all over the world with 80% accuracy".
The Computer Vision and Pattern Recognition conference is put on the by the IEEE Computer Society and is ongoing now until June 25th.
You can read the entire Google paper here (Note: will open as a PDF).
You can also follow the CVPR conference on Twitter @CVPR or check out their Facebook page here.