{"list":"other","total":56,"rows":[{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68},{"id":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67},{"id":"2005.00642","title":"Spatial Dependency Parsing for Semi-Structured Document Information Extraction","created":"2020-05-01","cited_by_count":65},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39},{"id":"2211.15421","title":"VRDU: A Benchmark for Visually-rich Document Understanding","created":"2022-11-15","cited_by_count":35},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24},{"id":"2110.09915","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","created":"2021-10-19","cited_by_count":23},{"id":"2310.11016","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","created":"2023-10-17","cited_by_count":23},{"id":"2212.09621","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","created":"2022-12-19","cited_by_count":20},{"id":"2303.13095","title":"Modeling Entities as Semantic Points for Visual Information Extraction in the Wild","created":"2023-03-23","cited_by_count":20},{"id":"2106.12940","title":"MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction","created":"2021-06-24","cited_by_count":18},{"id":"2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","created":"2022-06-27","cited_by_count":18},{"id":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18},{"id":"2208.10970","title":"Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis","created":"2022-08-22","cited_by_count":17},{"id":"2305.18721","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","created":"2023-05-30","cited_by_count":17},{"id":"1804.09843","title":"Hierarchical Density Order Embeddings","created":"2018-04-26","cited_by_count":13},{"id":"2205.02411","title":"Relational Representation Learning in Visually-Rich Documents","created":"2022-05-05","cited_by_count":11},{"id":"2204.05819","title":"Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework","created":"2022-03-30","cited_by_count":10},{"id":"2109.01078","title":"Skim-Attention: Learning to Focus via Document Layout","created":"2021-09-02","cited_by_count":7},{"id":"2208.08201","title":"Understanding Long Documents with Different Position-Aware Attentions","created":"2022-08-17","cited_by_count":7},{"id":"2308.07777","title":"Enhancing Visually-Rich Document Understanding via Layout Structure Modeling","created":"2023-08-15","cited_by_count":6},{"id":"2401.02823","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","created":"2024-01-05","cited_by_count":6},{"id":"2305.02577","title":"Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation","created":"2023-05-04","cited_by_count":5},{"id":"2407.06904","title":"Hypergraph based Understanding for Document Semantic Entity Recognition","created":"2024-07-09","cited_by_count":4},{"id":"2402.02379","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","created":"2024-02-04","cited_by_count":3},{"id":"2207.13979","title":"Knowing Where and What: Unified Word Block Pretraining for Document Understanding","created":"2022-07-28","cited_by_count":2},{"id":"2305.13850","title":"Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document","created":"2023-05-23","cited_by_count":2},{"id":"2305.14828","title":"Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation","created":"2023-05-24","cited_by_count":2},{"id":"2305.15057","title":"Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective","created":"2023-05-24","cited_by_count":2},{"id":"2310.14802","title":"DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading","created":"2023-10-23","cited_by_count":2},{"id":"2111.12317","title":"Handling tree-structured text: parsing directory pages","created":"2021-11-24","cited_by_count":1},{"id":"2305.17219","title":"GVdoc: Graph-based Visual Document Classification","created":"2023-05-26","cited_by_count":1},{"id":"2408.01038","title":"UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents","created":"2024-08-02","cited_by_count":1}],"next_cursor":null}