{"total":97,"rows":[{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"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":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173,"area":"mllm"},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88,"area":null},{"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,"area":"mllm"},{"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,"area":null},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58,"area":"diffusion"},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53,"area":null},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53,"area":null},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45,"area":null},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"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":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","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":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34,"area":null},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34,"area":null},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"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":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24,"area":null},{"id":"2411.15858","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","created":"2024-11-24","cited_by_count":24,"area":null},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2305.05140","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","created":"2023-05-09","cited_by_count":18,"area":null},{"id":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16,"area":null},{"id":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16,"area":"mllm"},{"id":"2302.10414","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14,"area":"distill"},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"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":"2209.06717","title":"Out-of-Vocabulary Challenge Report","created":"2022-09-14","cited_by_count":11,"area":null},{"id":"2407.12317","title":"Out of Length Text Recognition with Sub-String Matching","created":"2024-07-17","cited_by_count":11,"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":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9,"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":"2308.03729","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models","created":"2023-08-07","cited_by_count":9,"area":"mllm"},{"id":"2308.08806","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","created":"2023-08-17","cited_by_count":8,"area":"distill"},{"id":"2405.05841","title":"Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2305.14758","title":"MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition","created":"2023-05-24","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":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2308.00508","title":"Relational Contrastive Learning for Scene Text Recognition","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2503.18746","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2507.02790","title":"From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding","created":"2025-07-03","cited_by_count":6,"area":null},{"id":"2112.00948","title":"Visual-Semantic Transformer for Scene Text Recognition","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2401.07641","title":"SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2401.10110","title":"SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2305.16172","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2310.08009","title":"Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2311.17955","title":"PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2404.12734","title":"Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer","created":"2024-04-19","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":"2409.17095","title":"General Detection-based Text Line Recognition","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2512.01422","title":"MDiff4STR: Mask Diffusion Model for Scene Text Recognition","created":"2025-12-01","cited_by_count":4,"area":"diffusion"},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2308.02770","title":"One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer","created":"2023-08-05","cited_by_count":3,"area":null},{"id":"2309.01081","title":"Orientation-Independent Chinese Text Recognition in Scene Images","created":"2023-09-03","cited_by_count":3,"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":"2402.15806","title":"Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2411.15585","title":"Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2511.23071","title":"Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding","created":"2025-11-28","cited_by_count":2,"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":"2211.04785","title":"Masked Vision-Language Transformers for Scene Text Recognition","created":"2022-11-09","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":"2307.16253","title":"Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction","created":"2023-07-30","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":"2407.05562","title":"Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2602.04030","title":"TiCLS : Tightly Coupled Language Text Spotter","created":"2026-02-03","cited_by_count":1,"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},{"id":"2305.05602","title":"Collaborative Chinese Text Recognition with Personalized Federated Learning","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2307.16410","title":"HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2401.09823","title":"Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layer","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2401.10041","title":"CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2403.07518","title":"Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2405.09125","title":"HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2408.02036","title":"LEGO: Self-Supervised Representation Learning for Scene Text Images","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2409.14483","title":"One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2410.18374","title":"Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2411.11219","title":"Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2412.10446","title":"Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2503.16184","title":"Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation","created":"2025-03-20","cited_by_count":0,"area":"distill"},{"id":"2505.04175","title":"DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation","created":"2025-05-07","cited_by_count":0,"area":"rag"},{"id":"2505.06855","title":"Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies","created":"2025-05-11","cited_by_count":0,"area":null},{"id":"2508.01153","title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.15557","title":"ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.08133","title":"OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2603.13886","title":"Multi-Modal Character Localization and Extraction for Chinese Text Recognition","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.14885","title":"Masked Next-Scale Prediction for Self-supervised Scene Text Recognition","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.10684","title":"Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.34781","title":"When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context","created":"2026-09-28","cited_by_count":0,"area":"mllm"}],"next_cursor":null}