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.
A new Actor-identified A-AVA dataset based on the existing AVA dataset and the TAO dataset, by assigning the unique actor identity and actions to each actor.