{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"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":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"1807.01544","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","created":"2018-07-04","cited_by_count":114},{"id":"1811.04256","title":"Scene Text Detection and Recognition: The Deep Learning Era","created":"2018-11-10","cited_by_count":114},{"id":"2007.09482","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","created":"2020-07-18","cited_by_count":114},{"id":"1801.01671","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","created":"2018-01-05","cited_by_count":109},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94},{"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":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"1703.06520","title":"Detecting Oriented Text in Natural Images by Linking Segments","created":"2017-03-19","cited_by_count":80},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","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":"1910.07954","title":"Convolutional Character Networks","created":"2019-10-17","cited_by_count":61},{"id":"1809.06508","title":"Scene Text Recognition from Two-Dimensional Perspective","created":"2018-09-18","cited_by_count":57},{"id":"1908.09231","title":"Towards Unconstrained End-to-End Text Spotting","created":"2019-08-24","cited_by_count":57},{"id":"2012.04350","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","created":"2020-12-08","cited_by_count":51},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50},{"id":"2106.12326","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","created":"2021-06-23","cited_by_count":46},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45},{"id":"2003.10608","title":"UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World","created":"2020-03-24","cited_by_count":43},{"id":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43},{"id":"2007.09629","title":"Character Region Attention For Text Spotting","created":"2020-07-19","cited_by_count":42},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34},{"id":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23},{"id":"2101.12741","title":"Post-OCR Paragraph Recognition by Graph Convolutional Networks","created":"2021-01-29","cited_by_count":16},{"id":"1712.05404","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","created":"2017-12-14","cited_by_count":12},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11},{"id":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","cited_by_count":6},{"id":"1908.11834","title":"Rethinking Irregular Scene Text Recognition","created":"2019-08-30","cited_by_count":4},{"id":"2002.03509","title":"A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling","created":"2020-02-10","cited_by_count":3}],"next_cursor":null}