Two full papers accepted at GIScience 2018


Two full papers have been accepted for oral presentation at the GIScience conference this year!

In the first paper, we conduct empirical studies that examine the localness of place names and their changes with geographic distance.

In the second paper, we use recurrent neural networks to learn spatial patterns to help improve image classification for different place types, resulting in a 40% increase in accuracy compared with CNN models purely based on visual signals.

We will be presenting our papers in Melbourne, Australia in August. Hope to see you there!