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 ShapeIt dataset introduced by Alper et al. (2023) consists of 109 nouns and noun phrases along with the basic shape normally associated with that item, chosen from the set {circle, rectangle, triangle}.