# EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA

Source: [EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA](<https://www.sota2.com/research/paper/68fa6d041e209131cea3758a>)

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

Data updated: 2025-10-26T00:24:36.116Z

Authors: Arka Ujjal Dey, Ernest Valveny, Gaurav Harit

Published: 2021-08-22T13:21:58.000Z

## Abstract

The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use of external knowledge to augment our understanding of the scene text. We design a framework to extract, validate, and reason with knowledge using a standard multimodal transformer for vision language understanding tasks. Through empirical evidence and qualitative results, we demonstrate how external knowledge can highlight instance-only cues and thus help deal with training data bias, improve answer entity type correctness, and detect multiword named entities. We generate results comparable to the state-of-the-art on three publicly available datasets, under the constraints of similar upstream OCR systems and training data.

## 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/2108.09717>)

[PDF](<https://arxiv.org/pdf/2108.09717.pdf>)
