{"list":"other","total":58,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"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":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"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":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2209.00383","title":"TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut","created":"2022-09-01","cited_by_count":113},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105},{"id":"2004.12629","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","created":"2020-04-27","cited_by_count":98},{"id":"1706.02337","title":"Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network","created":"2017-06-07","cited_by_count":92},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80},{"id":"2106.04550","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","created":"2021-06-08","cited_by_count":76},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2011.13677","title":"Self-EMD: Self-Supervised Object Detection without ImageNet","created":"2020-11-27","cited_by_count":70},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47},{"id":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40},{"id":"2204.05539","title":"Content and Style Aware Generation of Text-line Images for Handwriting Recognition","created":"2022-04-12","cited_by_count":35},{"id":"2004.08686","title":"A Large Dataset of Historical Japanese Documents with Complex Layouts","created":"2020-04-18","cited_by_count":25},{"id":"2008.10831","title":"CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images","created":"2020-08-25","cited_by_count":22},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22},{"id":"2107.02638","title":"DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis","created":"2021-07-06","cited_by_count":17},{"id":"2208.11168","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","created":"2022-08-23","cited_by_count":17},{"id":"2104.10538","title":"Guided Table Structure Recognition through Anchor Optimization","created":"2021-04-21","cited_by_count":15},{"id":"1711.05862","title":"Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines","created":"2017-11-03","cited_by_count":14},{"id":"2305.04609","title":"SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation","created":"2023-05-08","cited_by_count":13},{"id":"2404.01819","title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","created":"2024-04-02","cited_by_count":13},{"id":"2308.02051","title":"A Graphical Approach to Document Layout Analysis","created":"2023-08-03","cited_by_count":8},{"id":"2305.02769","title":"Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer","created":"2023-05-04","cited_by_count":7},{"id":"2306.13526","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","created":"2023-06-23","cited_by_count":7},{"id":"2404.17888","title":"A Hybrid Approach for Document Layout Analysis in Document images","created":"2024-04-27","cited_by_count":6},{"id":"2405.00187","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","created":"2024-04-30","cited_by_count":5},{"id":"2405.04971","title":"End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents","created":"2024-05-08","cited_by_count":4},{"id":"2201.09407","title":"Cross-Domain Document Layout Analysis Using Document Style Guide","created":"2022-01-24","cited_by_count":1}],"next_cursor":null}