Datasets › Visual7W
Visual7W
Visual7W is a large-scale visual question answering (QA) dataset, with object-level groundings and multimodal answers. Each question starts with one of the seven Ws, what, where, when, who, why, how and which. It is collected from 47,300 COCO images and it has 327,929 QA pairs, together with 1,311,756 human-generated multiple-choices and 561,459 object groundings from 36,579 categories.
Source: https://github.com/yukezhu/visual7w-toolkit Image Source: http://ai.stanford.edu/~yukez/visual7w/
Benchmarks archive 2025-07-28
All 1 leaderboard 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.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Visual Question Answering (VQA) | Visual7W | CMN Percentage correct 72.53 | Modeling Relationships in Referential Expressions with... | hengyuan-hu/bottom-up-attention-vqa +1 | 4 | Compare |
Papers archive 2025-07-28
4 shown of 4 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 112. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Coarse-to-Fine Reasoning for Visual Question Answering | 2 | 1 | 6 Oct 2021 | ran 4 of 9 samples (5 unverified) |
| Compact Trilinear Interaction for Visual Question Answering | 1 | 1 | 26 Sep 2019 | ran 1 of 5 samples (4 unverified) |
| Modeling Relationships in Referential Expressions with Compositional Modular Networks | 2 | 1 | 30 Nov 2016 | not harvested |
| Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding | 10 | 1 | 6 Jun 2016 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Unknown
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- Visual7W
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