Some tasks are inferred based on the benchmarks list.
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 PIPA database is collected from Flickr photo albums for the task of person recognition. Then the dataset is extended with 26,915 person pair annotations based on the social domain theory.