Location Recognition Over Large Time Lags
This addresses a domain-specific challenge in cultural heritage and computer vision, but it is incremental as it builds on existing feature analysis and domain adaptation methods.
The paper tackles the problem of automatically matching ancient photos to modern ones for cultural heritage mapping by analyzing features robust to large time lags and showing that domain adaptation improves performance.
Would it be possible to automatically associate ancient pictures to modern ones and create fancy cultural heritage city maps? We introduce here the task of recognizing the location depicted in an old photo given modern annotated images collected from the Internet. We present an extensive analysis on different features, looking for the most discriminative and most robust to the image variability induced by large time lags. Moreover, we show that the described task benefits from domain adaptation.