{"total":18,"rows":[{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2404.11339","title":"Best Practices for a Handwritten Text Recognition System","created":"2024-04-17","cited_by_count":17,"area":null},{"id":"2104.01552","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","created":"2021-04-04","cited_by_count":15,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"area":null},{"id":"2408.00644","title":"Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning","created":"2024-08-01","cited_by_count":9,"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":"2408.00441","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2202.06080","title":"Recognition-free Question Answering on Handwritten Document Collections","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2303.03127","title":"ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2411.10261","title":"Partial Scene Text Retrieval","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2105.15093","title":"Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2209.10441","title":"A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2106.05144","title":"Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2308.03515","title":"Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoring","created":"2023-08-07","cited_by_count":1,"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":"2609.07159","title":"Unsupervised Domain Adaptation for Symbol Spotting in Historical Encrypted Manuscripts","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.34490","title":"HPMD: A Historical Persian Manuscript Dataset for Word Spotting with Line-Level Annotation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}