IAPR TC-12 dataset
收藏官方服务：
资源简介：
The dataset is public and contains 20,000 pairs of image text, all of which are labeled with at least one of the 255 tags. The image is represented by a 512-dimensional GIST feature vector, and the text is represented by a 2912-dimensional bag-of-word vector.
提供机构：
华东交通大学; 无创建时间：
2023-10-16
