English
Related papers

Related papers: Beyond Bag-of-Patches: Learning Global Layout via …

200 papers

Retrieval-Augmented Generation (RAG) systems have been popular for generative applications, powering language models by injecting external knowledge. Companies have been trying to leverage their large catalog of documents (e.g. PDFs,…

With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional…

Computation and Language · Computer Science 2026-03-24 Yibo Yan , Jiahao Huo , Guanbo Feng , Mingdong Ou , Yi Cao , Xin Zou , Shuliang Liu , Yuanhuiyi Lyu , Yu Huang , Jungang Li , Kening Zheng , Xu Zheng , Philip S. Yu , James Kwok , Xuming Hu

Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure to ensure retrieval efficacy while maintaining computational efficiency. Existing VDR models struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Fengbin Zhu , Zijing Cai , Yuzhe Wang , Pengyang Shao , Wenjie Wang , Fuli Feng , Richang Hong , Tat-Seng Chua

Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually…

Information Retrieval · Computer Science 2025-09-30 Zhongbin Xie , Thomas Lukasiewicz

Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities. The visual cues offered by their complex layouts play a…

Computation and Language · Computer Science 2024-01-03 Dongsheng Wang , Natraj Raman , Mathieu Sibue , Zhiqiang Ma , Petr Babkin , Simerjot Kaur , Yulong Pei , Armineh Nourbakhsh , Xiaomo Liu

Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Souhail Bakkali , Sanket Biswas , Zuheng Ming , Mickaël Coustaty , Marçal Rusiñol , Oriol Ramos Terrades , Josep Lladós

Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting…

Computation and Language · Computer Science 2025-06-23 Yihao Ding , Soyeon Caren Han , Jean Lee , Eduard Hovy

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Fuyuan Liu , Dianyu Yu , He Ren , Nayu Liu , Xiaomian Kang , Delai Qiu , Fa Zhang , Genpeng Zhen , Shengping Liu , Jiaen Liang , Wei Huang , Yining Wang , Junnan Zhu

Visual document understanding (VDU) is a challenging task for large vision language models (LVLMs), requiring the integration of visual perception, text recognition, and reasoning over structured layouts. Although recent LVLMs have shown…

Computation and Language · Computer Science 2026-04-07 Haruka Kawasaki , Ryota Tanaka , Kyosuke Nishida

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Teng Wang , Lingquan Meng , Lei Cheng , Changyin Sun

Document centric RAG pipelines usually begin with OCR, followed by brittle heuristics for chunking, table parsing, and layout reconstruction. These text first workflows are costly to maintain, sensitive to small layout shifts, and often…

Information Retrieval · Computer Science 2026-01-07 Anup Roy , Rishabh Gyanendra Upadhyay , Animesh Rameshbhai Panara , Robin Mills , Aidan Millar

We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding (VDU). The VDU domain entails understanding documents (beyond mere OCR predictions) e.g., extracting information from a form, VQA for documents and other…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Srikar Appalaraju , Peng Tang , Qi Dong , Nishant Sankaran , Yichu Zhou , R. Manmatha

Visually-rich Document Understanding (VrDU) has attracted much research attention over the past years. Pre-trained models on a large number of document images with transformer-based backbones have led to significant performance gains in…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Yi Tu , Ya Guo , Huan Chen , Jinyang Tang

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision…

Information Retrieval · Computer Science 2021-05-20 Shi Yu , Zhenghao Liu , Chenyan Xiong , Tao Feng , Zhiyuan Liu

The robustness of a model for real-world deployment is decided by how well it performs on unseen data and distinguishes between in-domain and out-of-domain samples. Visual document classifiers have shown impressive performance on…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Fnu Mohbat , Mohammed J. Zaki , Catherine Finegan-Dollak , Ashish Verma

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

Computation and Language · Computer Science 2022-05-06 Xin Li , Yan Zheng , Yiqing Hu , Haoyu Cao , Yunfei Wu , Deqiang Jiang , Yinsong Liu , Bo Ren

Traditional information extraction systems face challenges with text only language models as it does not consider infographics (visual elements of information) such as tables, charts, images etc. often used to convey complex information to…

Information Retrieval · Computer Science 2025-07-17 Rachna Saxena , Abhijeet Kumar , Suresh Shanmugam

Recent approaches for visually-rich document understanding (VrDU) uses manually annotated semantic groups, where a semantic group encompasses all semantically relevant but not obviously grouped words. As OCR tools are unable to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Zhouqiang Jiang , Bowen Wang , Junhao Chen , Yuta Nakashima

Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Previous works typically formulated layout reading order as a…

Computation and Language · Computer Science 2024-10-01 Chong Zhang , Yi Tu , Yixi Zhao , Chenshu Yuan , Huan Chen , Yue Zhang , Mingxu Chai , Ya Guo , Huijia Zhu , Qi Zhang , Tao Gui

Visually rich documents (VRDs) challenge retrieval-augmented generation (RAG) with layout-dependent semantics, brittle OCR, and evidence spread across complex figures and structured tables. This survey examines how Multimodal Large Language…

Information Retrieval · Computer Science 2026-01-08 Xiantao Zhang