EVA: Engine for Visual Annotation
Jia Deng ⋅ Joanathan Krause ⋅ Zhiheng Huang ⋅ Alexander C Berg ⋅ Li Fei-Fei
2012 Demonstration
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.
Chat is not available.
Successful Page Load