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.
UltraLAMBDAis a large-scale dataset of ads sourced from brand videos on platforms such as YouTube and Facebook Ads, as well as from CommonCrawl. The memorability scores for the ads are assigned by our model Henry.