ICMLA 2011 StreetView Recognition Challenge

Recognition is a fundamental problem in machine learning and computer vision. In this challenge, we introduce a few datasets from Google StreetView which include street scenes of urban areas.

We propose two tasks:

  1. Business recognition
  2. Object recognition

For the first task we recommend to recognize businesses including: bank, gas station, parking garage, hotel, restaurant. For the second task we recommend object categories of stop sign, ATM machine, bus stop, street sign, fire hydrant. Participants are encouraged to submit their results for just one of the tasks or for the two of them, and for one or multiple categories, or for new categories defined for street scenes. Methods trained on other datasets are allowed, but results on the given StreetView datasets are required in the submission.

The datasets contain Google StreetView images from Pittsburgh and San Francisco. Please email your name, affiliation and address to meihan@google.com to download the datasets.

A short paper (4 pages) describing the proposed algorithms and results on the provided datasets should be submitted through the main conference submission website. These papers will be reviewed mainly based on:

  • Originality and technical soundness of the employed algorithms
  • Performance in either or both of the recognition tasks

Accepted papers will be published in the ICMLA’11 conference proceedings.


Paper Submission Deadline:September 25, 2011
Notification of acceptance:September 28, 2011
Camera-ready papers & Pre-registration: October 1, 2011
The ICMLA Conference:December 18-21, 2011

The authors should submit their papers through the main conference submission website. Papers must correspond to the requirements detailed in the instructions to authors. Accepted papers must be presented by one of the authors in order to be published in the conference proceeding. If you have any questions, do not hesitate to direct your questions to the organizers.

All challenge submissions will be handled electronically. Please click here for details.

ICMLA’11 Challenge Session Chair
Mei Han, Google Research, Mountain View, USA