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.
Deep Soccer Captioning is a dataset consists of 22k caption-clip pairs and three visual features (images, optical flow, inpainting) for 500 hours of SoccerNet videos.