{"total":88,"rows":[{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429,"area":null},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324,"area":null},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143,"area":null},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2109.03144","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"id":"2308.12234","title":"MolGrapher: Graph-based Visual Recognition of Chemical Structures","created":"2023-08-23","cited_by_count":24,"area":null},{"id":"2503.06470","title":"Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems","created":"2025-03-09","cited_by_count":23,"area":null},{"id":"2602.20903","title":"TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering","created":"2026-02-24","cited_by_count":15,"area":null},{"id":"2303.05325","title":"BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset","created":"2023-03-09","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":"2507.20025","title":"Region-based Cluster Discrimination for Visual Representation Learning","created":"2025-07-26","cited_by_count":13,"area":null},{"id":"2102.09127","title":"Efficient Online ML API Selection for Multi-Label Classification Tasks","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2301.10165","title":"Lexi: Self-Supervised Learning of the UI Language","created":"2023-01-23","cited_by_count":10,"area":null},{"id":"2410.05267","title":"Grounding Partially-Defined Events in Multimodal Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2204.12743","title":"Self-Supervised Text Erasing with Controllable Image Synthesis","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2309.00378","title":"Long-Term Ad Memorability: Understanding & Generating Memorable Ads","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2404.04624","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","created":"2024-04-06","cited_by_count":9,"area":null},{"id":"2507.15085","title":"OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities","created":"2025-07-20","cited_by_count":9,"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":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2307.04643","title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","created":"2023-07-07","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":"2108.06949","title":"Data Augmentation for Scene Text Recognition","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2210.07903","title":"Text Detection Forgot About Document OCR","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2301.02363","title":"Text2Poster: Laying out Stylized Texts on Retrieved Images","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","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":"2410.21414","title":"CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2502.18148","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.13483","title":"EmoMeta: A Multimodal Dataset for Fine-grained Emotion Classification in Chinese Metaphors","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2109.12212","title":"An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2307.04245","title":"A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2505.01435","title":"AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2605.16740","title":"TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.01050","title":"TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images","created":"2026-05-31","cited_by_count":3,"area":null},{"id":"2207.06694","title":"Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2405.08427","title":"Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2407.06950","title":"Spanish TrOCR: Leveraging Transfer Learning for Language Adaptation","created":"2024-07-09","cited_by_count":2,"area":null},{"id":"2409.04117","title":"Confidence-Aware Document OCR Error Detection","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2504.16723","title":"Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.03570","title":"Evaluating OCR performance on food packaging labels in South Africa","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2601.16113","title":"synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.11044","title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2608.19637","title":"TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2403.07553","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2409.05125","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2409.10016","title":"AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2503.17735","title":"RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2504.18948","title":"Use of Metric Learning for the Recognition of Handwritten Digits, and its Application to Increase the Outreach of Voice-based Communication Platforms","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2505.06918","title":"Uni-AIMS: AI-Powered Microscopy Image Analysis","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2510.03160","title":"SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2605.18818","title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.24602","title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.30762","title":"ChessQueries: Toward Better Chess Board Recognition","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.03445","title":"OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2102.02971","title":"Metaknowledge Extraction Based on Multi-Modal Documents","created":"2021-02-05","cited_by_count":0,"area":null},{"id":"2108.09215","title":"Video Ads Content Structuring by Combining Scene Confidence Prediction and Tagging","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2207.03960","title":"Detection of Furigana Text in Images","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2209.05911","title":"Computer vision based vehicle tracking as a complementary and scalable approach to RFID tagging","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2301.05099","title":"Improving Inference Performance of Machine Learning with the Divide-and-Conquer Principle","created":"2023-01-12","cited_by_count":0,"area":null},{"id":"2407.01987","title":"AHMsys: An Automated HVAC Modeling System for BIM Project","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2407.06354","title":"High-Throughput Phenotyping using Computer Vision and Machine Learning","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2407.12836","title":"OSPC: Artificial VLM Features for Hateful Meme Detection","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2504.05770","title":"A Lightweight Multi-Module Fusion Approach for Korean Character Recognition","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2506.05061","title":"A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions","created":"2025-06-05","cited_by_count":0,"area":null},{"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":"2507.17335","title":"TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.16295","title":"Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2604.10077","title":"DocRevive: A Unified Pipeline for Document Text Restoration","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.17500","title":"Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.22754","title":"HalalBench: A Multilingual OCR Benchmark for Food Packaging Ingredient Extraction","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.23095","title":"INSIGHT: Indoor Scene Intelligence from Geometric-Semantic Hierarchy Transfer for Public~Safety","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.05018","title":"Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiatives","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.28406","title":"Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.15299","title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.25642","title":"Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.27923","title":"PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10244","title":"Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.17538","title":"From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.33450","title":"Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39649","title":"FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound Degradation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.11286","title":"When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.11685","title":"HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.17448","title":"TableVision: Recovering Verified Structure from Historical Tables","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}