Datasets › VizWiz

VizWiz (VizWiz-VQA)

Introduced by Danna Gurari et al. in VizWiz Grand Challenge: Answering Visual Questions from Blind People1 Jan 2018 archive 2025-07-28

The VizWiz-VQA dataset originates from a natural visual question answering setting where blind people each took an image and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. The proposed challenge addresses the following two tasks for this dataset: predict the answer to a visual question and (2) predict whether a visual question cannot be answered.

Source: https://vizwiz.org/tasks-and-datasets/vqa/ Image Source: https://vizwiz.org/tasks-and-datasets/vqa/

Benchmarks archive 2025-07-28

All 7 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 12 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): Visual Question Answering (VQA) · VizWiz 2020 VQA (8 judged, 1 placed), Visual Question Answering · VizWiz (5 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Image Captioning VizWiz 2020 test-dev IBM Research AI CIDEr 80.67 — — 50 Compare
Visual Question Answering (VQA) VizWiz 2020 VQA PaLI overall 73.3 PaLI: A Jointly-Scaled Multilingual Language-Image Model google-research/big_vision 16 Compare
Image Captioning VizWiz 2020 test IBM Research AI CIDEr 81.04 — — 13 Compare
Visual Question Answering (VQA) VizWiz 2018 LXR955, No Ensemble overall 55.4 LXMERT: Learning Cross-Modality Encoder Representations... huggingface/transformers +8 10 Compare
Visual Question Answering (VQA) VizWiz 2020 Answerability CLIP-Ensemble average_precision 84.13 Less Is More: Linear Layers on CLIP Features as Powerful... — 6 Compare
Visual Question Answering VizWiz Emu-I * Accuracy 38.1 Emu: Generative Pretraining in Multimodality baaivision/emu +1 1 Compare
Visual Question Answering (VQA) VizWiz 2018 Answerability ensemble_two_best average_precision 82.78 — — 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 7 · with a code link: 5 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 7 with a benchmark row: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 7 of 7 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 260. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization 1 1 5 Feb 2024 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (5 pointer-only for licence)
Emu: Generative Pretraining in Multimodality 2 1 11 Jul 2023 official: harvested for another paper · 0 ran · 2 unverified
PaLI: A Jointly-Scaled Multilingual Language-Image Model 1 1 14 Sep 2022 official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model 0 4 10 Jun 2022 not harvested
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering 0 1 4 Sep 2019 not harvested
LXMERT: Learning Cross-Modality Encoder Representations from Transformers 9 1 20 Aug 2019 community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (3 pointer-only for licence)
Towards VQA Models That Can Read 7 1 18 Apr 2019 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • VizWiz Answer Differences 2019
  • VizWiz 2020 VQA
  • VizWiz 2020 test-dev
  • VizWiz 2020 test
  • VizWiz 2020 Answerability
  • VizWiz 2018 Answerability
  • VizWiz 2018
  • VizWiz

8 variant names, 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