guodaosun/CompoVIS download history
guodaosun/CompoVIS is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 27 times (9 in the last 7 days), and 956 times in total. It ranks #297,781 among datasets by monthly downloads.
CLEVR-Per Dataset README Overview CLEVR-Per is a cross-modal dataset integrating images, baseline (true) captions, and permuted (false) captions to facilitate research on "compositional understanding" tasks in vision-language models. The dataset is designed to explore VLMs' abi