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.
COME15K is an RGB-D saliency detection dataset which contains 15,625 image pairs with high quality polygon-/scribble-/object-/instance-/rank-level annotations.