Demonstration
EVA: Engine for Visual Annotation
Jia Deng · Joanathan Krause · Zhiheng Huang · Alexander C Berg · Li Fei-Fei
Harrah's Special Events Center, 2nd Floor -Tahoe A & B
[
Abstract
]
Abstract:
The EVA system, powered by ImageNet, recognizes over 20K visual classes. Using the DARTS algorithm (Deng et al. 2012), EVA is able to name objects in an image as informatively as possible while ensuring an arbitrarily high accuracy. This live demo showcases EVA on images supplied by a user.
Live content is unavailable. Log in and register to view live content