{"total":112,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279,"area":null},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203,"area":null},{"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,"area":null},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"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,"area":null},{"id":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81,"area":null},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70,"area":null},{"id":"2203.01601","title":"Syntax-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-03-03","cited_by_count":68,"area":null},{"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,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45,"area":null},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45,"area":null},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41,"area":null},{"id":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","cited_by_count":40,"area":null},{"id":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40,"area":null},{"id":"2111.11011","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","created":"2021-11-22","cited_by_count":36,"area":null},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36,"area":null},{"id":"2207.11934","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","created":"2022-07-25","cited_by_count":33,"area":null},{"id":"2105.04286","title":"Primitive Representation Learning for Scene Text Recognition","created":"2021-05-10","cited_by_count":28,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25,"area":null},{"id":"2107.12090","title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","created":"2021-07-26","cited_by_count":24,"area":null},{"id":"2201.00267","title":"On the Cross-dataset Generalization in License Plate Recognition","created":"2022-01-02","cited_by_count":22,"area":null},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2210.05391","title":"PP-StructureV2: A Stronger Document Analysis System","created":"2022-10-11","cited_by_count":20,"area":null},{"id":"2103.15992","title":"A Multiplexed Network for End-to-End, Multilingual OCR","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2104.02894","title":"Facial Attribute Transformers for Precise and Robust Makeup Transfer","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2303.07012","title":"AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation","created":"2023-03-13","cited_by_count":17,"area":null},{"id":"2203.04814","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2207.14801","title":"Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach","created":"2022-07-29","cited_by_count":15,"area":null},{"id":"2111.09162","title":"It's About Time: Analog Clock Reading in the Wild","created":"2021-11-17","cited_by_count":14,"area":null},{"id":"2209.00641","title":"Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition","created":"2022-08-31","cited_by_count":14,"area":null},{"id":"2207.04675","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","created":"2022-07-11","cited_by_count":13,"area":null},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2107.12081","title":"Towards the Unseen: Iterative Text Recognition by Distilling from Errors","created":"2021-07-26","cited_by_count":12,"area":null},{"id":"2203.05179","title":"Towards Open-Set Text Recognition via Label-to-Prototype Learning","created":"2022-03-10","cited_by_count":12,"area":null},{"id":"2312.11923","title":"IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2107.11041","title":"RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles","created":"2021-07-23","cited_by_count":10,"area":null},{"id":"2309.04331","title":"Leveraging Model Fusion for Improved License Plate Recognition","created":"2023-09-08","cited_by_count":10,"area":null},{"id":"2402.13643","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","created":"2024-02-21","cited_by_count":10,"area":null},{"id":"2305.05322","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2401.03637","title":"Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2108.10840","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","created":"2021-08-24","cited_by_count":7,"area":null},{"id":"2203.05122","title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","created":"2022-03-10","cited_by_count":7,"area":null},{"id":"2204.07714","title":"Pushing the Performance Limit of Scene Text Recognizer without Human Annotation","created":"2022-04-16","cited_by_count":7,"area":null},{"id":"2207.08417","title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2601.07671","title":"Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2106.06960","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2021-06-13","cited_by_count":6,"area":null},{"id":"2308.00508","title":"Relational Contrastive Learning for Scene Text Recognition","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2102.10884","title":"Revisiting Classification Perspective on Scene Text Recognition","created":"2021-02-22","cited_by_count":5,"area":null},{"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,"area":null},{"id":"2103.04635","title":"FEDS -- Filtered Edit Distance Surrogate","created":"2021-03-08","cited_by_count":5,"area":null},{"id":"2103.09354","title":"Digital Peter: Dataset, Competition and Handwriting Recognition Methods","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2105.08383","title":"I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition","created":"2021-05-18","cited_by_count":5,"area":null},{"id":"2106.05920","title":"Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2107.02827","title":"Plot2Spectra: an Automatic Spectra Extraction Tool","created":"2021-07-06","cited_by_count":5,"area":null},{"id":"2108.06949","title":"Data Augmentation for Scene Text Recognition","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2209.13139","title":"Searching a High-Performance Feature Extractor for Text Recognition Network","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2305.05166","title":"E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2104.12076","title":"Parallel Scale-wise Attention Network for Effective Scene Text Recognition","created":"2021-04-25","cited_by_count":4,"area":null},{"id":"2105.07795","title":"STRIDE : Scene Text Recognition In-Device","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2212.14674","title":"A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2409.11656","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2210.07423","title":"Task Grouping for Multilingual Text Recognition","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2201.02850","title":"Image-based Automatic Dial Meter Reading in Unconstrained Scenarios","created":"2022-01-08","cited_by_count":2,"area":null},{"id":"2202.11949","title":"SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition","created":"2022-02-24","cited_by_count":2,"area":null},{"id":"2203.12165","title":"Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2303.06078","title":"An End-to-End Neural Network for Image-to-Audio Transformation","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2306.15782","title":"UTRNet: High-Resolution Urdu Text Recognition In Printed Documents","created":"2023-06-27","cited_by_count":2,"area":null},{"id":"2501.09052","title":"Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks","created":"2025-01-15","cited_by_count":2,"area":null},{"id":"2602.13812","title":"DTBench: A Synthetic Benchmark for Document-to-Table Extraction","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2111.12276","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2204.02630","title":"IterVM: Iterative Vision Modeling Module for Scene Text Recognition","created":"2022-04-06","cited_by_count":1,"area":null},{"id":"2207.06695","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2209.01914","title":"Scene Text Recognition with Single-Point Decoding Network","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2306.03482","title":"Looking and Listening: Audio Guided Text Recognition","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2402.17134","title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2407.09965","title":"Learning Online Scale Transformation for Talking Head Video Generation","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2602.10138","title":"Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2101.01310","title":"Research on Fast Text Recognition Method for Financial Ticket Image","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2106.05611","title":"Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2109.01034","title":"Scene Text recognition with Full Normalization","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2109.01880","title":"Deep learning facilitates fully automated brain image registration of optoacoustic tomography and magnetic resonance imaging","created":"2021-09-04","cited_by_count":0,"area":null},{"id":"2201.00132","title":"SAFL: A Self-Attention Scene Text Recognizer with Focal Loss","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2203.06696","title":"Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching","created":"2022-03-13","cited_by_count":0,"area":null},{"id":"2205.05507","title":"TextMatcher: Cross-Attentional Neural Network to Compare Image and Text","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2210.02576","title":"Reading Chinese in Natural Scenes with a Bag-of-Radicals Prior","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2210.10836","title":"Scene Text Recognition with Semantics","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2211.05624","title":"Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2303.09347","title":"CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.04524","title":"Scene Text Recognition with Image-Text Matching-guided Dictionary","created":"2023-05-08","cited_by_count":0,"area":null}],"next_cursor":"100"}