no code implementations • 10 Mar 2017 • Ruoyu Liu, Yao Zhao, Liang Zheng, Shikui Wei, Yi Yang
Additionally, a trivial solution, \ie, directly using the predicted class label for cross-media retrieval, is tested.
no code implementations • 2 Aug 2015 • Ruoyu Liu, Yao Zhao, Shikui Wei, Yi Yang
The convolutional neural network (CNN) features can give a good description of image content, which usually represent images with unique global vectors.