Open limycml opened 5 years ago
These datasets can be downloaded from the following URLs: 1 Wikipedia: http://www.svcl.ucsd.edu/projects/crossmodal/ 2 NUS-WIDE: http://lms.comp.nus.edu.sg/research/NUS-WIDE.htm 3 XMediaNet: http://www.icst.pku.edu.cn/mipl/XMedia/
For the reason of the license, please download the raw data and extract the features using the VGG19 and Sentence CNN. Please refer to our paper to get the details of extraction. For text, the Sentence CNN code can be obtained from https://github.com/yoonkim/CNN_sentence.
Thanks for your attention.
Thanks for providing PASCAL dataset. Could you please provide the other three datasets?