Papers › VQA: Visual Question Answering

VQA: Visual Question Answering

3 May 2015ICCV 2015 12arXiv:1505.00468archive 2025-07-28

Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol, Margaret Mitchell, C. Lawrence Zitnick, Dhruv Batra, Devi Parikh

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1505.00468")

Code

Syntology Ran 6 of 7 code samples harvested from 4 repositories linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 5 samples from 4 repositories, 4 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

21 repositories listed; official and paper-mentioned ones first.

SDaydreamer/VisualQA_Project mentioned on GitHubpytorch report
SatyamGaba/visual_question_answering mentioned on GitHubpytorch report
SatyamGaba/vqa mentioned on GitHubpytorch report
abhshkdz/neural-vqa-attention mentioned on GitHubtorch report
chirag26495/DAN_VQA mentioned on GitHubpytorch report
mishajw/vocab_pie mentioned on GitHub report
mkhalil1998/EC601_Group_Project mentioned on GitHubpytorch report
moh833/VQA mentioned on GitHub report
mokhalid-dev/Attention-based-VQA-model mentioned on GitHubpytorch report
ntusteeian/VQA_CNN-LSTM mentioned on GitHubpytorch report
ramprs/grad-cam mentioned on GitHubtorch report
ruxuan666/VQA_program mentioned on GitHubpytorch report
tbmoon/basic_vqa mentioned on GitHubpytorch report
vipulgupta1011/swapmix mentioned on GitHubpytorch report
yanxinyan1/yxy mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 6 ran; 2 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
2ran · fixture could not drive it
1unverified

Licence: 6 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

evaluate_acc luomancs/alternative_answer_set/evaluation/evaluation.py community (archive-listed) ran · honoured contract no licence file found · pointer only · a4063279bd752ead · report
evaluate_metrix1 luomancs/alternative_answer_set/evaluation/evaluation.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 8d3dccfefd226953 · report
extract_answers chirag26495/DAN_VQA/utils/build_vqa_inputs.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 0cf6e2086607dd93 · report
preprocess moh833/VQA/Evaluation/evaluate_VQA_1.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · f3406c3db2da10b5 · report
vqa_processing tbmoon/basic_vqa/utils/build_vqa_inputs.py community (archive-listed) unverified MIT (permissive) · 5c4bf041a6c83301 · report
create_submission identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · d12f1716d21540a8 · report
predict_answers identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 6d3a7a351f38eccd · report

Tasks

Image CaptioningMultiple-choiceVisual Question AnsweringVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

Visual Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract 1.0 multiple choice Dualnet ensemble Percentage correct 71.18 #2 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract 1.0 multiple choice LSTM + global features Percentage correct 69.21 #3 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract 1.0 multiple choice LSTM blind Percentage correct 61.41 #4 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract images 1.0 open ended Dualnet ensemble Percentage correct 69.73 #2 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract images 1.0 open ended LSTM + global features Percentage correct 65.02 #3 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) abstract images 1.0 open ended LSTM blind Percentage correct 57.19 #4 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 multiple choice LSTM Q+I Percentage correct 63.1 #9 of 10 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 open ended LSTM Q+I Percentage correct 58.2 #12 of 14 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 2.0 open ended HDU-USYD-UNCC Percentage correct 68.16 #1 of 4 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 2.0 open ended DLAIT Percentage correct 68.07 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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