{"total":69,"rows":[{"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,"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":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"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":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"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":"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":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","cited_by_count":40,"area":null},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36,"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":"2112.06558","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning","created":"2021-12-13","cited_by_count":27,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27,"area":null},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"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":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20,"area":null},{"id":"2103.10895","title":"Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark","created":"2021-03-19","cited_by_count":17,"area":null},{"id":"2310.16033","title":"Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs","created":"2023-10-24","cited_by_count":15,"area":"mllm"},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","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":"2203.05179","title":"Towards Open-Set Text Recognition via Label-to-Prototype Learning","created":"2022-03-10","cited_by_count":12,"area":null},{"id":"2211.08954","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","created":"2022-11-16","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":"2311.07306","title":"What Large Language Models Bring to Text-rich VQA?","created":"2023-11-13","cited_by_count":10,"area":null},{"id":"2403.00303","title":"ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting","created":"2024-03-01","cited_by_count":10,"area":null},{"id":"2204.05535","title":"Open-set Text Recognition via Character-Context Decoupling","created":"2022-04-12","cited_by_count":8,"area":null},{"id":"2402.08017","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","created":"2024-02-12","cited_by_count":8,"area":"mllm"},{"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":"2308.16383","title":"Separate and Locate: Rethink the Text in Text-based Visual Question Answering","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7,"area":"inference"},{"id":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","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":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","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":"2103.09354","title":"Digital Peter: Dataset, Competition and Handwriting Recognition Methods","created":"2021-03-16","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":"2211.12950","title":"Look, Read and Ask: Learning to Ask Questions by Reading Text in Images","created":"2022-11-23","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":"2105.07795","title":"STRIDE : Scene Text Recognition In-Device","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2209.06730","title":"MUST-VQA: MUltilingual Scene-text VQA","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2209.14970","title":"3D Rendering Framework for Data Augmentation in Optical Character Recognition","created":"2022-09-27","cited_by_count":3,"area":null},{"id":"2302.01540","title":"DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioning","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2408.05706","title":"Decoder Pre-Training with only Text for Scene Text Recognition","created":"2024-08-11","cited_by_count":3,"area":null},{"id":"2111.02064","title":"Event and Activity Recognition in Video Surveillance for Cyber-Physical Systems","created":"2021-11-03","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":"2306.15782","title":"UTRNet: High-Resolution Urdu Text Recognition In Printed Documents","created":"2023-06-27","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":"2207.06695","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2209.03126","title":"DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention","created":"2022-09-07","cited_by_count":1,"area":null},{"id":"2306.00228","title":"Using Visual Cropping to Enhance Fine-Detail Question Answering of BLIP-Family Models","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2308.00295","title":"Making the V in Text-VQA Matter","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2506.10609","title":"MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2510.01651","title":"LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition","created":"2025-10-02","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":"2605.05900","title":"Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2111.03664","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","created":"2021-11-05","cited_by_count":0,"area":"distill"},{"id":"2111.06075","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","created":"2021-11-11","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":"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":"2211.14450","title":"Text-Aware Dual Routing Network for Visual Question Answering","created":"2022-11-17","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":"2507.11730","title":"Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2511.15807","title":"TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models","created":"2025-11-19","cited_by_count":0,"area":null}],"next_cursor":null}