Skip to Main content Skip to Navigation
Journal articles

What Makes Paris Look Like Paris?

Abstract : Given a large repository of geo-tagged imagery, we seek to automatically find visual elements, for example windows, balconies, and street signs, that are most distinctive for a certain geo-spatial area, for example the city of Paris. This is a tremendously difficult task as the visual features distinguishing architectural elements of different places can be very subtle. In addition, we face a hard search problem: given all possible patches in all images, which of them are both frequently occurring and geographically informative? To address these issues, we propose to use a discriminative clustering approach able to take into account the weak geographic supervision. We show that geographically representative image elements can be discovered automatically from Google Street View imagery in a discriminative manner. We demonstrate that these elements are visually interpretable and perceptually geo-informative. The discovered visual elements can also support a variety of computational geography tasks, such as mapping architectural correspondences and influences within and across cities, finding representative elements at different geo-spatial scales, and geographically informed image retrieval.
Document type :
Journal articles
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.inria.fr/hal-01248528
Contributor : Josef Sivic <>
Submitted on : Thursday, December 31, 2015 - 12:16:00 AM
Last modification on : Wednesday, November 18, 2020 - 4:18:06 PM
Long-term archiving on: : Tuesday, April 5, 2016 - 9:47:23 AM

File

Doersch15author.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei Efros. What Makes Paris Look Like Paris?. Communications of the ACM, Association for Computing Machinery, 2015, 58 (12), pp.103-110. ⟨10.1145/2830541⟩. ⟨hal-01248528⟩

Share

Metrics

Record views

382

Files downloads

867