{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"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":"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":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"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":"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":"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":"1908.05900","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","created":"2019-08-16","cited_by_count":114},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"1801.01671","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","created":"2018-01-05","cited_by_count":109},{"id":"1912.10205","title":"Decoupled Attention Network for Text Recognition","created":"2019-12-21","cited_by_count":102},{"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":"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":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81},{"id":"1703.06520","title":"Detecting Oriented Text in Natural Images by Linking Segments","created":"2017-03-19","cited_by_count":80},{"id":"1603.03101","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","created":"2016-03-09","cited_by_count":74},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2203.01601","title":"Syntax-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-03-03","cited_by_count":68},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"1910.07954","title":"Convolutional Character Networks","created":"2019-10-17","cited_by_count":61},{"id":"1908.09231","title":"Towards Unconstrained End-to-End Text Spotting","created":"2019-08-24","cited_by_count":57},{"id":"2002.01276","title":"GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition","created":"2020-02-04","cited_by_count":52},{"id":"2012.04350","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","created":"2020-12-08","cited_by_count":51},{"id":"2106.12326","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","created":"2021-06-23","cited_by_count":46},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45},{"id":"2003.06606","title":"Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition","created":"2020-03-14","cited_by_count":36},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33},{"id":"1811.01396","title":"Handwriting Recognition in Low-resource Scripts using Adversarial Learning","created":"2018-11-04","cited_by_count":32},{"id":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29},{"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":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11},{"id":"2209.06717","title":"Out-of-Vocabulary Challenge Report","created":"2022-09-14","cited_by_count":11},{"id":"2402.13643","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","created":"2024-02-21","cited_by_count":10},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","cited_by_count":7}],"next_cursor":null}