{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"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":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"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":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"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":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"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":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2203.15118","title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","created":"2022-03-28","cited_by_count":73},{"id":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70},{"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":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46},{"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":"2112.13547","title":"PRIME: A few primitives can boost robustness to common corruptions","created":"2021-12-27","cited_by_count":40},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40},{"id":"2201.06494","title":"AugLy: Data Augmentations for Robustness","created":"2022-01-17","cited_by_count":34},{"id":"2303.17096","title":"ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing","created":"2023-03-30","cited_by_count":30},{"id":"2004.08686","title":"A Large Dataset of Historical Japanese Documents with Complex Layouts","created":"2020-04-18","cited_by_count":25},{"id":"2203.16850","title":"Revisiting Document Image Dewarping by Grid Regularization","created":"2022-03-31","cited_by_count":25},{"id":"2201.11438","title":"DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer","created":"2022-01-27","cited_by_count":19},{"id":"2303.11126","title":"Robustifying Token Attention for Vision Transformers","created":"2023-03-20","cited_by_count":19},{"id":"2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","created":"2022-06-27","cited_by_count":18},{"id":"2301.00970","title":"Benchmarking the Robustness of LiDAR Semantic Segmentation Models","created":"2023-01-03","cited_by_count":18},{"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":"2304.08796","title":"Deep Unrestricted Document Image Rectification","created":"2023-04-18","cited_by_count":16},{"id":"1802.06194","title":"HWNet v2: An Efficient Word Image Representation for Handwritten Documents","created":"2018-02-17","cited_by_count":13},{"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":"2305.14962","title":"ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-24","cited_by_count":6},{"id":"2305.06553","title":"WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-11","cited_by_count":5},{"id":"2307.02065","title":"Line Graphics Digitization: A Step Towards Full Automation","created":"2023-07-05","cited_by_count":5},{"id":"2304.12486","title":"Evaluating Adversarial Robustness on Document Image Classification","created":"2023-04-24","cited_by_count":2}],"next_cursor":null}