Embedded Files
Overview
Overview
Victims of human trafficking are often photographed in hotel rooms as in the below examples. Identifying these hotels is vital to these trafficking investigations but poses particular challenges due to low quality of images and uncommon camera angles.
Even without victims in the images, hotel identification in general is a challenging fine-grained visual recognition task with a huge number of classes and potentially high intraclass and low interclass variation. In order to support research into this challenging task and create image search tools for human trafficking investigators, we created the TraffickCam mobile application, which allows every day travelers to submit photos of their hotel room. Read more about TraffickCam on TechCrunch.
In this contest, competitors are tasked with identifying the hotel seen in test images from the TraffickCam dataset, which are based on a large gallery of training images with known hotel IDs.
Our team currently supports an image search system used at the National Center for Missing and Exploited Children in human trafficking investigations. Novel and interesting approaches have the potential to be incorporated in this search system.
Competition
Competition
Start Date: 16 March 2022
End Date: 31th May 2022
Kaggle URL: https://www.kaggle.com/c/hotel-id-to-combat-human-trafficking-2022-fgvc9/
Organizers
Organizers
Abby Stylianou (Saint Louis University)
Rashmi Kamath (Saint Louis University)
Robert Pless (Saint Louis University)
Richard Souvenir (Temple University)
Example images from one hotel in the TraffickCam dataset are shown below:
Example images from one hotel in the TraffickCam dataset are shown below:
Page updated
Google Sites
Report abuse