This repository provides a curated list of resources in the research domain of Document Layout Analysis (DLA), updated in my free time.
Methods based on heuristic rules are not included.
"Document Layout Analysis" OR "Document Layout Detection" OR "Page Object Detection" OR "Document Structure Analysis" OR "Document Structure Extraction" OR "Document Reading Order" OR "Document Hierarchy"
- Survey / Competition
- Methodology
- 2.1 Page Object Detection
- 2.2 Document Structure Analysis
- Data
- 3.1 Dataset
- 3.2 Data Synthesis / Data Generation / Data Augmentation
- Datasets and annotations for layout analysis of scientific articles, (UNIFI), 2024-03, IJDAR-2024
- Advancements in Financial Document Structure Extraction: Insights from Five Years of FinTOC (2019-2023), (Outscale, NITK, Lancaster), 2023-12, BigData-2023
- Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis, (UVA, Elsevier), 2023-08, arXiv
- ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents, (IBM), 2023-05, ICDAR-2023
- A Methodological Study of Document Layout Analysis, (XJU), 2022-10, VRHCIAI-2022
- A Survey of Graphical Page Object Detection with Deep Neural Networks, (TU Kaiserslautern, DFKI), 2021-06, Applied-Sciences.2021
- ICDAR 2021 Competition on Scientific Literature Parsing, (IBM, UniMelb, Oracle), 2021-06, ICDAR-2021
- Document Layout Analysis: A Comprehensive Survey, (KFUPM), 2019-10, ACM-Computing-Surveys.2019
- ICDAR2019 Competition on Recognition of Documents with Complex Layouts - RDCL2019, (Salford), 2019-09, ICDAR-2019
- ICDAR2017 Competition on Page Object Detection, (PKU), 2017-11, ICDAR-2017
- ICDAR2017 Competition on Recognition of Documents with Complex Layouts - RDCL2017, (Salford), 2017-11, ICDAR-2017
DREAMDREAM: Document Reconstruction via End-to-end Autoregressive Model, (Tencent), 2025-07, ACM-MM-2025DocSAMDocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning, (CAS, UCAS), 2025-04, CVPR-2025DLAdapterSFDLA: Source-Free Document Layout Analysis, (KIT, ETH Zurich), 2025-03, arXivPP-DocLayoutPP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction, (Baidu), 2025-03, arXivUniHDSAUniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis, (USTC, Microsoft), 2025-03, Pattern-Recognition.2025EDocNetEDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation, (SEU), 2025-02, arXivDoPTADoPTA: Improving Document Layout Analysis using Patch-Text Alignment, (Adobe), 2024-12, arXivDocEDADocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model, (SEU), 2024-12, arXivDocLayout-YOLODocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception, (Shanghai AI Lab), 2024-10, arXivUnSupDLAUnSupDLA: Towards Unsupervised Document Layout Analysis, (TU Kaiserslautern, DFKI), 2024-06, ICDAR-2024-WorkshopDLAFormerDLAFormer: An End-to-End Transformer For Document Layout Analysis, (USTC, Microsoft), 2024-05, ICDAR-2024CREPECREPE: Coordinate-Aware End-to-End Document Parser, (Naver, LINE WORKS), 2024-05, ICDAR-2024- A Hybrid Approach for Document Layout Analysis in Document images, (TU Kaiserslautern, DFKI), 2024-04, ICDAR-2024
M2DocM2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis, (SCUT, Alibaba), 2024-03, AAAI-2024RoDLARoDLA: Benchmarking the Robustness of Document Layout Analysis Models, (KIT, Oxford), 2024-03, CVPR-2024Detect-Order-ConstructDetect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis, (USTC, Microsoft), 2024-01, Pattern-Recognition.2024- The YOLO model that still excels in document layout analysis, (XJU), 2023-11, Signal-Image-and-Video-Processing.2024
DOLNetDataset agnostic document object detection, (IIIT), 2023-10, Pattern-Recognition.2023DSGDSG: An End-to-End Document Structure Generator, (ETH Zurich, LMU Munich), 2023-10, ICDM-2023VGTVision Grid Transformer for Document Layout Analysis, (Alibaba), 2023-08, ICCV-2023- A Hybrid Approach to Document Layout Analysis for Heterogeneous Document Images, (Microsoft, USTC, PKU), 2023-08, ICDAR-2023
GLAMA Graphical Approach to Document Layout Analysis, (Kensho, Meta, Google), 2023-08, ICDAR-2023HiMHiM: hierarchical multimodal network for document layout analysis, (QUST, ASU), 2023-07, Applied-Intelligence.2023DRFNDRFN: A unified framework for complex document layout analysis, (ECNU, Fudan, Videt), 2023-05, Information-Processing-&-Management.2023TransDLANetM6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis, (SCUT, Huawei, IntSig), 2023-05, CVPR-2023WeLayoutWeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents, (Tencent), 2023-05, arXivSwinDocSegmenterSwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation, (UAB, ISI), 2023-05, ICDAR-2023SelfDocSegSelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation, (ISI, UAB, IITK), 2023-05, ICDAR-2023StrucTexTv2StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training, (Baidu), 2023-03, ICLR-2023HSCA-NetHSCA-Net: A Hybrid Spatial-Channel Attention Network in Multiscale Feature Pyramid for Document Layout Analysis, (QUST, PITT), 2022-12, Journal-of-Artificial-Intelligence-and-Technology.2023- Rethinking Learnable Proposals for Graphical Object Detection in Scanned Document Images, (TU Kaiserslautern, DFKI, LUT), 2022-10, Applied-Sciences.2020
TRDLUTransformer-Based Approach for Document Layout Understanding, (KSU), 2022-10, ICIP-2022PP-StructureV2PP-StructureV2: A Stronger Document Analysis System, (Baidu), 2022-10, arXiv- Lateral Feature Enhancement Network for Page Object Detection, (QUST), 2022-08, TIM.2022
Doc-GCNDoc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis, (Sydney, UWA), 2022-08, COLING-2022- Investigating Attention Mechanism for Page Object Detection in Document Images, (TU Kaiserslautern, DFKI, LTU), 2022-07, Applied-Sciences.2022
DSAPExploiting Spatial Attention and Contextual Information for Document Image Segmentation, (XMU, Northumbria, SZU), 2022-05, PAKDD-2022LayoutLMv3LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking, (SYSU, Microsoft), 2022-04, ACM-MM-2022SRRVSRRV: A Novel Document Object Detector Based on Spatial-Related Relation and Vision, (QUST), 2022-04, IEEE-Transactions-on-Multimedia.2022DiTDiT: Self-supervised Pre-training for Document Image Transformer, (SJTU, Microsoft), 2022-03, ACM-MM-2022DocBedDocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts, (Amazon), 2022-02, IAAI-2022DocSegTrDocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer, (UAB, ISI), 2022-01, arXivUDocUnified Pretraining Framework for Document Understanding, (Adobe), 2021-12, NeurIPS-2021L-E3NetDocument Layout Analysis with Aesthetic-Guided Image Augmentation, (Fudan, ECNU, Videt), 2021-11, arXiv- Deep Learning in Time-Frequency Domain for Document Layout Analysis, (UDLA, DETRI, UNICAMP, Analog Devices, ESPE), 2021-11, IEEE-Access.2021
E3NetDocument image layout analysis via explicit edge embedding network, (ECNU, Videt), 2021-10, Information-Sciences.2021- A Page Object Detection Method Based on Mask R-CNN, (QUST, ASU, HIT), 2021-10, IEEE-Access.2021
VTLayoutVTLayout: Fusion of Visual and Text Features for Document Layout Analysis, (UCAS, CAS), 2021-08, PRICAI-2021FS-PARNFew-shot prototype alignment regularization network for document image layout segementation, (UESTC, YZU, Kyudai, Afanti, QDU), 2021-07, Pattern-Recognition.2021- End-to-end dilated convolution network for document image semantic segmentation, (QUST, ASU), 2021-07, Journal-of-Central-South-University.2021
- Beyond document object detection: instance-level segmentation of complex layouts, (UAB, ISI), 2021-07, IJDAR.2021
SelfDocSelfDoc: Self-Supervised Document Representation Learning, (Brandeis, Adobe), 2021-06, CVPR-2021VSRVSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations, (Hikvision, ZJU), 2021-05, ICDAR-2021- Document Layout Analysis with an Enhanced Object Detector, (TU Kaiserslautern, DFKI), 2021-04, IPRIA-2021
LAMPRETLAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding, (UCLA, Google), 2021-04, arXivDRFNDocument Layout Analysis via Dynamic Residual Feature Fusion, (ECNU, Videt), 2021-04, ICME-2021- Probabilistic homogeneity for document image segmentation, (VUB), 2021-01, Pattern-Recognition.2021
BINYASBINYAS: a complex document layout analysis system, (GKCIET, Jadavpur), 2020-11, Multimedia-Tools-and-Applications.2021- Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks, (KSU), 2020-10, ICPR-2020
- Page Segmentation Using Convolutional Neural Network and Graphical Model, (CAS, UCAS), 2020-08, DAS-2020
- Document Structure Extraction using Prior based High Resolution Hierarchical Semantic Segmentation, (Adobe), 2019-11, ECCV-2020
DocParserDocParser: Hierarchical Structure Parsing of Document Renderings, (ETH Zurich), 2019-11, AAAI-2021- Instance Aware Document Image Segmentation using Label Pyramid Networks and Deep Watershed Transformation, (CAS, UCAS, Tencent, univ-lr), 2019-09, ICDAR-2019
- Page Segmentation using a Convolutional Neural Network with Trainable Co-Occurrence Features, (Kyudai, SIT), 2019-09, ICDAR-2019
- Page Object Detection from PDF Document Images by Deep Structured Prediction and Supervised Clustering, (CAS, UCAS), 2018-08, ICPR-2018
DeepLayoutDeepLayout: A Semantic Segmentation Approach to Page Layout Analysis, (PKU), 2018-07, ICIC-2018dhSegmentdhSegment: A generic deep-learning approach for document segmentation, (EPFL), 2018-04, ICFHR-2018- Ensemble of Deep Object Detectors for Page Object Detection, (VNU-HCM), 2018-01, IMCOM-2018
- Multi-Scale Multi-Task FCN for Semantic Page Segmentation and Table Detection, (PSU, Adobe), 2017-11, ICDAR-2017
- CNN Based Page Object Detection in Document Images, (PKU), 2017-11, ICDAR-2017
- Fast CNN-Based Document Layout Analysis, (IBM), 2017-10, ICCV-Workshop-2017
MFCNLearning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network, (PSU, Adobe), 2017-06, CVPR-2017
DREAMDREAM: Document Reconstruction via End-to-end Autoregressive Model, (Tencent), 2025-07, ACM-MM-2025SCANSCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation, (NEC), 2025-05, arXivXY-Cut++XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark, (TJU), 2025-04, arXivUniHDSAUniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis, (USTC, Microsoft), 2025-03, Pattern-Recognition.2025DRGGGraph-based Document Structure Analysis, (KIT), 2025-02, ICLR-2025- Reading order detection in visually-rich documents with multi-modal layout-aware relation prediction, (ZJU, Hikvision), 2024-06, Pattern-Recognition.2024
DLAFormerDLAFormer: An End-to-End Transformer For Document Layout Analysis, (USTC, Microsoft), 2024-05, ICDAR-2024- Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction, (Allen AI, HUJI, BIU), 2024-02, ACL-2024
Detect-Order-ConstructDetect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis, (USTC, Microsoft), 2024-01, Pattern-Recognition.2024DSGDSG: An End-to-End Document Structure Generator, (ETH Zurich, LMU Munich), 2023-10, ICDM-2023- A Hybrid Approach to Document Layout Analysis for Heterogeneous Document Images, (Microsoft, USTC, PKU), 2023-08, ICDAR-2023
- Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation, (Google), 2023-05, ICDAR-2023
DSPSHRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures, (USTC, iFLYTEK), 2023-02, AAAI-2023LayerDocLayerDoc: Layer-wise Extraction of Spatial Hierarchical Structure in Visually-Rich Documents, (UMD, Adobe), 2023-01, WACV-2023MTDMultimodal Tree Decoder for Table of Contents Extraction in Document Images, (USTC, iFLYTEK), 2022-08, ICPR-2022XYLayoutLMXYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding, (SJTU, Ant Group), 2022-03, CVPR-2022- Reading order detection on handwritten documents, (UPV), 2022-02, Neural-Computing-and-Applications.2022
LayoutReaderLayoutReader: Pre-training of Text and Layout for Reading Order Detection, (UC San Diego, Microsoft), 2021-08, EMNLP-2021HELDExtracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application, (CAS, UCAS, Tencent, Peng Cheng Lab), 2021-05, Journal-of-Computer-Science-and-Technology.2022LAMPRETLAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding, (UCLA, Google), 2021-04, arXiv- An End-to-End OCR Text Re-organization Sequence Learning for Rich-Text Detail Image Comprehension, (ZJU, Alibaba), 2020-11, ECCV-2020
DocStructDocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding, (Sensetime), 2020-10, EMNLP-2020DocParserDocParser: Hierarchical Structure Parsing of Document Renderings, (ETH Zurich), 2019-11, AAAI-2021- Table-Of-Contents generation on contemporary documents, (Fortia), 2019-09, ICDAR-2019
DocRec1KDREAM: Document Reconstruction via End-to-end Autoregressive Model, (Tencent), 2025-07, ACM-MM-2025DocBench-100XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark, (TJU), 2025-04, arXivAnnoPageAnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorization, (VUTBR, MZK, NKP, CAS), 2025-03, arXivSFDLASFDLA: Source-Free Document Layout Analysis, (KIT, ETH Zurich), 2025-03, arXivGraphDocGraph-based Document Structure Analysis, (KIT), 2025-02, ICLR-2025OmniDocBenchOmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations, (Shanghai AI Lab, Abaka AI, 2077AI), 2024-12, CVPR-2025LADaS 2.0Diachronic Document Dataset for Semantic Layout Analysis, (Inria, PSL, IHEID, UNIGE), 2024-11, arXivREADocREADoc: A Unified Benchmark for Realistic Document Structured Extraction, (CAS, UCAS), 2024-09, arXivSciPostLayoutSciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters, (OMRON SINIC X, Waseda), 2024-07, BMVC-2024Comp-HRDocDetect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis, (USTC, Microsoft), 2024-01, Pattern-Recognition.2024ADOPDADOPD: A Large-Scale Document Page Decomposition Dataset, (Adobe, OSU, UC Merced, JHU), 2024-01, ICLR-2024E-PeriodicaDSG: An End-to-End Document Structure Generator, (ETH Zurich, LMU Munich), 2023-10, ICDM-2023D4LAVision Grid Transformer for Document Layout Analysis, (Alibaba), 2023-08, ICCV-2023CDSSEDRFN: A unified framework for complex document layout analysis, (ECNU, Fudan, Videt), 2023-05, Information-Processing-&-Management.2023M6DocM6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis, (SCUT, Huawei, IntSig), 2023-05, CVPR-2023ETD-ODv2A New Annotation Method and Dataset for Layout Analysis of Long Documents, (Virginia Tech), 2023-04, WWW-2023BaDLADBaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset, (Bengali.AI, SUST, BRACU, Vanderbilt, Rice, RPI), 2023-03, ICDAR-2023HRDocHRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures, (USTC, iFLYTEK), 2023-02, AAAI-2023TexBiGA Dataset for Analysing Complex Document Layouts in the Digital Humanities and Its Evaluation with Krippendorff’s Alpha, (uni-weimar), 2022-09, DAGM-GCPR-2022HierDocMultimodal Tree Decoder for Table of Contents Extraction in Document Images, (USTC, iFLYTEK), 2022-08, ICPR-2022DocLayNetDocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis, (IBM), 2022-06, SIGKDD-2022NewsNet7DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts, (Amazon), 2022-02, IAAI-2022DADSegmentation for document layout analysis: not dead yet, (USask, Living Sky), 2022-01, IJDAR.2022FPDDocument Layout Analysis with Aesthetic-Guided Image Augmentation, (Fudan, ECNU, Videt), 2021-11, arXivSciBankDeep Learning in Time-Frequency Domain for Document Layout Analysis, (UDLA, DETRI, UNICAMP, Analog Devices, ESPE), 2021-11, IEEE-Access.2021ReadingBankLayoutReader: Pre-training of Text and Layout for Reading Order Detection, (UC San Diego, Microsoft), 2021-08, EMNLP-2021DocBankDocBank: A Benchmark Dataset for Document Layout Analysis, (BUAA, Microsoft), 2020-06, COLING-2020arXivdocsDocParser: Hierarchical Structure Parsing of Document Renderings, (ETH Zurich), 2019-11, AAAI-2021article-regionsVisual Detection with Context for Document Layout Analysis, (BNL), 2019-11, EMNLP-IJCNLP-2019PubLayNetPubLayNet: largest dataset ever for document layout analysis, (IBM), 2019-08, ICDAR-2019ICDAR2017_PODICDAR2017 Competition on Page Object Detection, (PKU), 2017-11, ICDAR-2017DSSE-200Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network, (PSU, Adobe), 2017-06, CVPR-2017
LED BenchmarkLED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis, (CNU), 2025-07, arXivDocSynth-300KDocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception, (Shanghai AI Lab), 2024-10, arXiv- RoDLA: Benchmarking the Robustness of Document Layout Analysis Models, (KIT, Oxford), 2024-03, CVPR-2024
LACETowards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints, (Buffalo, Adobe, MBZUAI), 2024-02, ICLR-2024RanLayNetRanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization, (IIIT, VIT, JNU, NII), 2024-01, MMAsia-2023- WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents, (Tencent), 2023-05, arXiv
- A New Annotation Method and Dataset for Layout Analysis of Long Documents, (Virginia Tech), 2023-04, WWW-2023
- Automatic generation of scientific papers for data augmentation in document layout analysis, (UNIFI), 2023-03, Pattern-Recognition-Letters.2023
LayoutDiffusionLayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models, (SJTU, Microsoft), 2023-03, ICCV-2023- Diffusion-based Document Layout Generation, (Purdue, Microsoft), 2023-03, ICDAR-2023
LayoutDMLayoutDM: Discrete Diffusion Model for Controllable Layout Generation, (CyberAgent, Waseda), 2023-03, CVPR-2023LDGMUnifying Layout Generation with a Decoupled Diffusion Model, (XJTU, Microsoft, Tsinghua), 2023-03, CVPR-2023PLayPLay: Parametrically Conditioned Layout Generation using Latent Diffusion, (Google), 2023-01, ICML-2023LayoutFormer++LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction, (XJTU, Microsoft, SJTU, BUAA), 2022-08, CVPR-2023- Coarse-to-Fine Generative Modeling for Graphic Layouts, (XJTU, Microsoft), 2022-06, AAAI-2022
DL-DSGCross-Domain Document Layout Analysis Using Document Style Guide, (Fudan, ECNU, Videt), 2022-01, Expert-Systems-with-Applications.2024BLTBLT: Bidirectional Layout Transformer for Controllable Layout Generation, (CMU, Google), 2021-12, ECCV-2022- Synthetic Document Generator for Annotation-free Layout Recognition, (JPMorgan), 2021-11, Pattern-Recognition.2022
- Document image layout analysis via explicit edge embedding network, (ECNU, Videt), 2021-10, Information-Sciences.2021
- A Page Object Detection Method Based on Mask R-CNN, (QUST, ASU, HIT), 2021-10, IEEE-Access.2021
CanvasEmbCanvasEmb: Learning Layout Representation with Large-scale Pre-training for Graphic Design, (NUS, Microsoft, Meituan), 2021-10, ACM-MM-2021LayoutMCLDiverse Multimedia Layout Generation with Multi Choice Learning, (UNSW, CSIRO), 2021-10, ACM-MM-2021- Constrained Graphic Layout Generation via Latent Optimization, (Waseda, CyberAgent), 2021-08, ACM-MM-2021
CanvasVAECanvasVAE: Learning to Generate Vector Graphic Documents, (CyberAgent), 2021-08, ICCV-2021DocSynthDocSynth: A Layout Guided Approach for Controllable Document Image Synthesis, (UAB, ISI), 2021-07, ICDAR-2021LayoutGANLayoutGAN: Synthesizing Graphic Layouts With Vector-Wireframe Adversarial Networks, (BIT, Adobe), 2021-07, IEEE-Transactions-on-Pattern-Analysis-and-Machine-Intelligence.2021DDRDocument Domain Randomization for Deep Learning Document Layout Extraction, (OSU, Uni Vie, Inria, Uni Stuttgart, Nottingham, ODU, PSU), 2021-05, ICDAR-2021RUITERUITE: Refining UI Layout Aesthetics Using Transformer Encoder, (RWTH), 2021-04, IUI-2021VTNVariational Transformer Networks for Layout Generation, (Google, ETH Zurich, TUM), 2021-04, CVPR-2021LayoutTransformerLayoutTransformer: Layout Generation and Completion with Self-attention, (UMD, UC San Diego, Amazon), 2020-06, ICCV-2021- Cross-Domain Document Object Detection: Benchmark Suite and Method, (NEU, Adobe), 2020-03, CVPR-2020
NDNNeural Design Network: Graphic Layout Generation with Constraints, (Google, UC Merced, Yonsei, Georgia Tech), 2019-12, ECCV-2020READREAD: Recursive Autoencoders for Document Layout Generation, (SFU, TAU, Amazon, Cornell), 2019-09, CVPR-2020-Workshop- Content-aware generative modeling of graphic design layouts, (CityUHK), 2019-07, ACM-Transactions-on-Graphics.2019
LayoutGANLayoutGAN: Generating Graphic Layouts with Wireframe Discriminators, (BIT, Adobe), 2019-01, ICLR-2019- Multi-Scale Multi-Task FCN for Semantic Page Segmentation and Table Detection, (PSU, Adobe), 2017-11, ICDAR-2017
- Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network, (PSU, Adobe), 2017-06, CVPR-2017