The benchmarks section lists all benchmarks using a given dataset or any of
its variants. We use variants to distinguish between results evaluated on
slightly different versions of the same dataset. For example, ImageNet 32⨉32
and ImageNet 64⨉64 are variants of the ImageNet dataset.
The Image-MusicEmotion-Matching-Net (IMEMNet) dataset is a dataset for continuous emotion-based image and music matching. It has over 140K image-music pairs.