5 datasets found

The CLEVR-Humans dataset consists of 32,164 questions asked by humans, containing words and reasoning steps that were unseen in CLEVR.

Reasoning detection dataset for multimodal large language models

The ReasonSeg dataset is a benchmark for reasoning segmentation tasks, which demands a nuanced comprehension of intricate queries to accurately pinpoint object regions.

Fashionpedia-Taste is an explainable fashion taste dataset that challenges computer vision systems to predict whether a subject like a fashion image and provide explanations...

A dataset for multi-turn dialogue reasoning.