English
Related papers

Related papers: Lightweight and Production-Ready PDF Visual Elemen…

200 papers

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Aman Ulla

Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension, offering a significant leap forward. These breakthroughs have proven particularly instrumental in addressing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Yiran Li , Junpeng Wang , Prince Aboagye , Michael Yeh , Yan Zheng , Liang Wang , Wei Zhang , Kwan-Liu Ma

Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Junxiao Xue , Quan Deng , Tingqi Hu , Meicong Si , Xinyi Yin , Yunyun Shi , Xuecheng Wu

Retrieval-augmented generation (RAG) systems have predominantly focused on text-based retrieval, limiting their effectiveness in handling visually-rich documents that encompass text, images, tables, and charts. To bridge this gap, we…

Information Retrieval · Computer Science 2025-05-07 Mingjun Xu , Zehui Wang , Hengxing Cai , Renxin Zhong

Retrieval-Augmented Generation (RAG) systems fail when documents evolve through versioning-a ubiquitous characteristic of technical documentation. Existing approaches achieve only 58-64% accuracy on version-sensitive questions, retrieving…

Information Retrieval · Computer Science 2025-10-10 Daniel Huwiler , Kurt Stockinger , Jonathan Fürst

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 (DocRAG) methods…

Information Retrieval · Computer Science 2025-11-10 Kuicai Dong , Yujing Chang , Shijie Huang , Yasheng Wang , Ruiming Tang , Yong Liu

Object-aware reasoning in vision-language tasks poses significant challenges for current models, particularly in handling unseen objects, reducing hallucinations, and capturing fine-grained relationships in complex visual scenes. To address…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Antonio Carlos Rivera , Anthony Moore , Steven Robinson

Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Wang Zhu , Alekh Agarwal , Mandar Joshi , Robin Jia , Jesse Thomason , Kristina Toutanova

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 parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Cheng Cui , Ting Sun , Suyin Liang , Tingquan Gao , Zelun Zhang , Jiaxuan Liu , Xueqing Wang , Changda Zhou , Hongen Liu , Manhui Lin , Yue Zhang , Yubo Zhang , Jing Zhang , Jun Zhang , Xing Wei , Yi Liu , Dianhai Yu , Yanjun Ma

Document layout analysis involves understanding the arrangement of elements within a document. This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings. The…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Tahira Shehzadi , Didier Stricker , Muhammad Zeshan Afzal

Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning. However, applying it to specific domains like legal…

Computation and Language · Computer Science 2026-05-28 Zerui Chen , Qinggang Zhang , Zhishang Xiang , Zhimin Wei , Linfeng Gao , Xiao Huang , Zhihong Zhang , Jinsong Su

Documents are visually rich structures that convey information through text, but also figures, page layouts, tables, or even fonts. Since modern retrieval systems mainly rely on the textual information they extract from document pages to…

Information Retrieval · Computer Science 2025-03-03 Manuel Faysse , Hugues Sibille , Tony Wu , Bilel Omrani , Gautier Viaud , Céline Hudelot , Pierre Colombo

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Jaemin Son , Sujin Choi , Inyong Yun

Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for…

Computation and Language · Computer Science 2026-02-03 Jacob Si , Mike Qu , Michelle Lee , Marek Rei , Yingzhen Li

In this work, we propose the use of "aligned visual captions" as a mechanism for integrating information contained within videos into retrieval augmented generation (RAG) based chat assistant systems. These captions are able to describe the…

Artificial Intelligence · Computer Science 2024-05-29 Kevin Dela Rosa

Retrieving images from natural language descriptions is a core task at the intersection of computer vision and natural language processing, with wide-ranging applications in search engines, media archiving, and digital content management.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Dao Sy Duy Minh , Huynh Trung Kiet , Nguyen Lam Phu Quy , Phu-Hoa Pham , Tran Chi Nguyen

Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Taewhan Kim , Soeun Lee , Si-Woo Kim , Dong-Jin Kim

Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented -- focusing on either text or images in…

Computation and Language · Computer Science 2026-01-06 Xiangyu Peng , Can Qin , Zeyuan Chen , Ran Xu , Caiming Xiong , Chien-Sheng Wu

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