Papers › Hierarchical Question-Image Co-Attention for Visual Question Answering

Hierarchical Question-Image Co-Attention for Visual Question Answering

31 May 2016NeurIPS 2016 12arXiv:1606.00061archive 2025-07-28

Jiasen Lu, Jianwei Yang, Dhruv Batra, Devi Parikh

A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling "where to look" or visual attention, it is equally important to model "what words to listen to" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a novel 1-dimensional convolution neural networks (CNN). Our model improves the state-of-the-art on the VQA dataset from 60.3% to 60.5%, and from 61.6% to 63.3% on the COCO-QA dataset. By using ResNet, the performance is further improved to 62.1% for VQA and 65.4% for COCO-QA.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1606.00061")

Code

Syntology Ran 1 of 7 code samples harvested from 3 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jiasenlu/HieCoAttenVQA officialmentioned in papermentioned on GitHubtorch report
SkyOL5/VQA-CoAttention mentioned on GitHubpytorch report
WillSuen/VQA mentioned on GitHubtf report
arya46/VQA_HieCoAtt mentioned on GitHubtfMIT report
karunraju/VQA mentioned on GitHubpytorch report
miohana/vqa mentioned on GitHubtfMIT report
phisad/keras-hicoatt mentioned on GitHubtfGPL-3.0 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; 1 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
6unverified

Licence: 1 of the 7 samples is 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

collate_lines karunraju/VQA/coatt/coattention_experiment_runner.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 8f94f0e75a42bcfa · report
build_model arya46/VQA_HieCoAtt/models/arch.py community (archive-listed) unverified MIT (permissive) · 841acde4f63da42b · report
image_feature_extractor arya46/VQA_HieCoAtt/utils/helper_functions.py community (archive-listed) unverified MIT (permissive) · 89d2b73b092fedd6 · report
image_feature_extractor miohana/vqa/utils/helper_functions.py community (archive-listed) unverified MIT (permissive) · ab1d505a48053f78 · report
predict_answers arya46/VQA_HieCoAtt/utils/helper_functions.py community (archive-listed) unverified MIT (permissive) · 7d9a7d3d8353ba1a · report
predict_function arya46/VQA_HieCoAtt/utils/load_pickles.py community (archive-listed) unverified MIT (permissive) · 4a692c10164ea21a · report
process_sentence arya46/VQA_HieCoAtt/utils/helper_functions.py community (archive-listed) unverified MIT (permissive) · fe06a6a886106510 · report

Tasks

Visual DialogVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Dialog VisDial v0.9 val HieCoAtt-QI MRR 57.88 #9 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val HieCoAtt-QI Mean Rank 5.84 #9 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val HieCoAtt-QI R@1 43.51 #9 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val HieCoAtt-QI R@10 83.96 #9 of 18 Archive leaderboard report
Visual Dialog VisDial v0.9 val HieCoAtt-QI R@5 74.49 #9 of 18 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 multiple choice HQI+ResNet Percentage correct 66.1 #7 of 10 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 open ended HQI+ResNet Percentage correct 62.1 #6 of 14 Archive leaderboard report
Visual Question Answering (VQA) VQA v1 test-dev HieCoAtt (ResNet) Accuracy 61.8 #5 of 7 Archive leaderboard report
Visual Question Answering (VQA) VQA v1 test-std HieCoAtt (ResNet) Accuracy 62.1 #3 of 6 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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