paper-with-me

홈 › Papers

Hierarchical multimodal transformers for Multi-Page DocVQA

2022-12-07 · Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny

Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.

📄 PDF Abstract BibTeX arXiv:2212.05935

Code (1)

rubenpt91/MP-DocVQA-Framework 공식 구현 pytorch

Tasks

DecoderQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

2024-11-07 · Jaemin Cho, Debanjan Mahata, Ozan Irsoy, Yujie He 외

Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rel…

document understandingOptical Character RecognitionOptical Character Recognition (OCR)Question Answering+4

SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement

2025-06-16 · Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu 외

Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tab…

document understandingQuestion AnsweringRAGRe-Ranking+3

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning

2026-08-04 · Le Xiang, Zhicheng Guan, Hong Chen, Xiaocong Lin 외 arxiv

Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages. Existing app…

Visual Question Answering

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

2025-05-22 · Kuicai Dong, Yujing Chang, Shijie Huang, Yasheng Wang 외

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (D…

BenchmarkingEvidence SelectionQuestion AnsweringRetrieval+2

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

2026-03-24 · Mincheol Kwon, Minseung Lee, Seonga Choi, Miso Choi 외 arxiv

Large Vision-Language Models (LVLMs) have shown strong performance across various multimodal tasks by leveraging the reasoning capabilities of Large Language Models (LLMs). However, processing visually complex and inform…