ibm-research/WikiVQABench download history
ibm-research/WikiVQABench is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 242 times (51 in the last 7 days), and 898 times in total. It ranks #77,613 among datasets by monthly downloads.
Dataset Card for WikiVQABench Dataset Summary WikiVQABench is a human-curated knowledge-grounded VQA benchmark constructed by systematically combining Wikipedia images, their associated article captions, and structured knowledge from Wikidata. We used large language mod
Open ibm-research/WikiVQABench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.