Datasets › VizWiz-Captions

VizWiz-Captions

Introduced by Danna Gurari et al. in Captioning Images Taken by People Who Are Blind archive 2025-07-28

Consists of over 39,000 images originating from people who are blind that are each paired with five captions.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

No paper in the archive has a leaderboard row on this dataset; the archive counts 12 papers for it but never published that list.

No loader listed in the archive.

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

No language tagged.

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections