# PAT: Parallel Attention Transformer for Visual Question Answering in Vietnamese

Source: [PAT: Parallel Attention Transformer for Visual Question Answering in Vietnamese](<https://www.sota2.com/research/paper/68fa70061e209131cea48a9a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:32:16.690Z

Authors: Nghia Hieu Nguyen, Kiet Van Nguyen

Published: 2023-07-17T05:05:15.000Z

## Abstract

We present in this paper a novel scheme for multimodal learning named the Parallel Attention mechanism. In addition, to take into account the advantages of grammar and context in Vietnamese, we propose the Hierarchical Linguistic Features Extractor instead of using an LSTM network to extract linguistic features. Based on these two novel modules, we introduce the Parallel Attention Transformer (PAT), achieving the best accuracy compared to all baselines on the benchmark ViVQA dataset and other SOTA methods including SAAA and MCAN.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.08247>)

[PDF](<https://arxiv.org/pdf/2307.08247.pdf>)