Papers › Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding

Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding

6 Jun 2016EMNLP 2016 11arXiv:1606.01847archive 2025-07-28

Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, Marcus Rohrbach

Modeling textual or visual information with vector representations trained from large language or visual datasets has been successfully explored in recent years. However, tasks such as visual question answering require combining these vector representations with each other. Approaches to multimodal pooling include element-wise product or sum, as well as concatenation of the visual and textual representations. We hypothesize that these methods are not as expressive as an outer product of the visual and textual vectors. As the outer product is typically infeasible due to its high dimensionality, we instead propose utilizing Multimodal Compact Bilinear pooling (MCB) to efficiently and expressively combine multimodal features. We extensively evaluate MCB on the visual question answering and grounding tasks. We consistently show the benefit of MCB over ablations without MCB. For visual question answering, we present an architecture which uses MCB twice, once for predicting attention over spatial features and again to combine the attended representation with the question representation. This model outperforms the state-of-the-art on the Visual7W dataset and the VQA challenge.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

akirafukui/vqa-mcb officialmentioned in papermentioned on GitHubcaffe2BSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Analyzing the Behavior of Visual Question Answering Models (arXiv:1606.07356; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Adam1679/mutan-article-net mentioned on GitHubpytorchSyntology: not harvested report
Cadene/vqa.pytorch mentioned on GitHubpytorchSyntology: not harvested report
JoonSeongPark/vqa mentioned on GitHubpytorchSyntology: not harvested report
MarcBS/keras mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Deep Features for Discriminative Localization (arXiv:1512.04150; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
arunmallya/simple-vqa mentioned on GitHubtorchSyntology: not harvested report
gabegrand/adversarial-vqa mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and... (arXiv:1906.08430; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jnhwkim/cbp mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
vuhoangminh/vqa_medical mentioned on GitHubpytorchSyntology: not harvested report
yikang-li/iqan mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Phrase GroundingVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Phrase Grounding Flickr30k Entities Test MCB R@1 48.69 #12 of 18 Archive leaderboard report
Phrase Grounding ReferIt MCB Accuracy 28.91 #3 of 3 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 multiple choice MCB 7 att. Percentage correct 70.1 #1 of 10 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 open ended MCB 7 att. Percentage correct 66.5 #1 of 14 Archive leaderboard report
Visual Question Answering (VQA) VQA v1 test-dev MCB (ResNet) Accuracy 64.2 #3 of 7 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev MCB Accuracy 64.7 #45 of 56 Archive leaderboard report
Visual Question Answering (VQA) Visual7W MCB+Att. Percentage correct 62.2 #4 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.

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