{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"1801.02765","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","created":"2018-01-09","cited_by_count":119},{"id":"1807.01544","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","created":"2018-07-04","cited_by_count":114},{"id":"1908.05900","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","created":"2019-08-16","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":"1803.05265","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","created":"2018-03-14","cited_by_count":88},{"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":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80},{"id":"2003.07493","title":"Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection","created":"2020-03-17","cited_by_count":77},{"id":"2004.04940","title":"ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection","created":"2020-04-10","cited_by_count":69},{"id":"2106.13488","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","created":"2021-06-25","cited_by_count":67},{"id":"1904.06535","title":"Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes","created":"2019-04-13","cited_by_count":66},{"id":"1911.09550","title":"All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting","created":"2019-11-21","cited_by_count":66},{"id":"2105.00405","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","created":"2021-05-02","cited_by_count":65},{"id":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63},{"id":"1910.07954","title":"Convolutional Character Networks","created":"2019-10-17","cited_by_count":61},{"id":"1912.02379","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","created":"2019-12-05","cited_by_count":61},{"id":"1707.03985","title":"Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks","created":"2017-07-13","cited_by_count":56},{"id":"2004.13278","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","created":"2020-04-28","cited_by_count":55},{"id":"2012.04350","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","created":"2020-12-08","cited_by_count":51},{"id":"1803.03474","title":"An end-to-end TextSpotter with Explicit Alignment and Attention","created":"2018-03-09","cited_by_count":50},{"id":"1812.01393","title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","created":"2018-12-04","cited_by_count":50},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47},{"id":"1905.05980","title":"Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation","created":"2019-05-15","cited_by_count":45},{"id":"1807.03021","title":"Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes","created":"2018-07-09","cited_by_count":44},{"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":"1907.09653","title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition","created":"2019-07-23","cited_by_count":37},{"id":"1901.02596","title":"MSR: Multi-Scale Shape Regression for Scene Text Detection","created":"2019-01-09","cited_by_count":35},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33},{"id":"1807.03547","title":"Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping","created":"2018-07-10","cited_by_count":20},{"id":"1909.07808","title":"Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning","created":"2019-09-17","cited_by_count":20},{"id":"1907.06007","title":"SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds","created":"2019-07-13","cited_by_count":15},{"id":"2009.01766","title":"Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild","created":"2020-09-03","cited_by_count":15},{"id":"1710.04826","title":"WeText: Scene Text Detection under Weak Supervision","created":"2017-10-13","cited_by_count":13},{"id":"2103.00785","title":"Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links","created":"2021-03-01","cited_by_count":5}],"next_cursor":null}