arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.09717cs.CVcs.MM
收藏

EKTVQA:在文本VQA中普遍使用外部知识来增强场景文本

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

Computer Vision Center, Universitat Aut\` o noma de Barcelona, Bellaterra (Barcelona)

Arka Ujjal Dey, Ernest Valveny, Gaurav Harit

摘要:

Text-VQA的开放式问答任务通常需要阅读和推理图像中很少看到或完全看不到的场景文本内容。我们解决这个zero-shot性质的问题,提出了广泛使用的外部知识,以增加我们的理解场景文本。我们设计了一个框架来提取,验证和推理知识,使用标准的多模态Transformer的视觉语言理解任务。通过实证证据和定性结果,我们展示了外部知识如何突出实例提示,从而帮助处理训练数据偏差,提高答案实体类型的正确性,并检测多词命名实体。我们生成的结果相当于国家的最先进的三个公开可用的数据集,类似的上游OCR系统和训练数据的约束下。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑