MétaCan
Menu
Back to cohort
Record W4407304464 · doi:10.1109/access.2025.3540388

BVQA: Connecting Language and Vision Through Multimodal Attention for Open-Ended Question Answering

2025· article· en· W4407304464 on OpenAlexafffund
Eftekhar Hossain, Khaleda Akhter Sathi, Md. Azad Hossain, M. Ali Akber Dewan

Bibliographic record

VenueIEEE Access · 2025
Typearticle
Languageen
FieldComputer Science
TopicSpeech and dialogue systems
Canadian institutionsAthabasca University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceQuestion answeringNatural language processingClosed-ended questionArtificial intelligenceHuman–computer interactionLinguisticsPhilosophy

Abstract

fetched live from OpenAlex

Visual Question Answering (VQA) is a challenging problem of Artificial Intelligence (AI) that requires an understanding of natural language and computer vision to respond to inquiries based on visual content within images. Research on VQA has gained immense traction due to its wide range of applications in aiding visually impaired individuals, enhancing human-computer interaction, facilitating content-based image retrieval systems, etc. While there has been extensive research on VQA, most were predominantly focused on English, often overlooking the complexity associated with low-resource languages, especially in Bengali. To facilitate research in this arena, we have developed a large scale Bengali Visual Question Answering (BVQA) dataset by harnessing the in-context learning abilities of the Large Language Model (LLM). Our BVQA dataset encompasses around 17,800 diverse open-ended QA Pairs generated from the human-annotated captions of ≈3,500 images. Replicating existing VQA systems for a low-resource language poses significant challenges due to the complex nature of their architectures and adaptations for particular languages. To overcome this challenge, we proposed Multimodal CRoss-Attention Network (MCRAN), a novel framework that leverages pretrained transformer architectures to encode the visual and textual information. Furthermore, our method utilizes a multi-head attention mechanism to generate three distinct vision-language representations and fuses them using a sophisticated gating mechanism to answer the query regarding an image. Extensive experiments on BVQA dataset show that the proposed method outperformed the existing baseline across various answer categories. The benchmark and source code is available athttps://github.com/eftekhar-hossain/Bengali-VQA.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.007
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.021
Threshold uncertainty score0.042

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.007
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0010.004
Open science0.0030.003
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0080.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.030
GPT teacher head0.387
Teacher spread0.357 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueIEEE AccessSame topicSpeech and dialogue systemsFrench-language works237,207