{"total":245,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2203.06486","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","created":"2022-03-12","cited_by_count":169,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"area":null},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94,"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":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77,"area":null},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70,"area":null},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70,"area":null},{"id":"2405.17933","title":"ToonCrafter: Generative Cartoon Interpolation","created":"2024-05-28","cited_by_count":68,"area":null},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66,"area":null},{"id":"2105.00405","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","created":"2021-05-02","cited_by_count":65,"area":null},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65,"area":null},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58,"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":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50,"area":null},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47,"area":null},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45,"area":null},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44,"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":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34,"area":null},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33,"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":"2210.11248","title":"OCR-VQGAN: Taming Text-within-Image Generation","created":"2022-10-19","cited_by_count":31,"area":null},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"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":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28,"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":"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":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"area":null},{"id":"2407.16670","title":"FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process","created":"2024-07-23","cited_by_count":25,"area":null},{"id":"2110.01890","title":"De-rendering Stylized Texts","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2109.03426","title":"Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection","created":"2021-09-08","cited_by_count":23,"area":null},{"id":"2203.10539","title":"End-to-End Video Text Spotting with Transformer","created":"2022-03-20","cited_by_count":22,"area":null},{"id":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2104.11493","title":"Stroke-Based Scene Text Erasing Using Synthetic Data for Training","created":"2021-04-23","cited_by_count":20,"area":null},{"id":"2307.01946","title":"ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization","created":"2023-07-04","cited_by_count":20,"area":null},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19,"area":null},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"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":"2207.10273","title":"Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context","created":"2022-07-21","cited_by_count":18,"area":null},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2110.12663","title":"Industrial Scene Text Detection with Refined Feature-attentive Network","created":"2021-10-25","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":"2208.12419","title":"Arbitrary Shape Text Detection via Segmentation with Probability Maps","created":"2022-08-26","cited_by_count":15,"area":null},{"id":"2108.01343","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","created":"2021-08-03","cited_by_count":14,"area":null},{"id":"2107.05945","title":"CentripetalText: An Efficient Text Instance Representation for Scene Text Detection","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2206.13381","title":"TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask","created":"2022-06-27","cited_by_count":13,"area":null},{"id":"2210.07489","title":"The Surprisingly Straightforward Scene Text Removal Method With Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2306.09593","title":"FETNet: Feature Erasing and Transferring Network for Scene Text Removal","created":"2023-06-16","cited_by_count":12,"area":null},{"id":"2306.12106","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","created":"2023-06-21","cited_by_count":12,"area":null},{"id":"2308.07202","title":"Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning","created":"2023-08-14","cited_by_count":12,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2209.03016","title":"Text Growing on Leaf","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2405.13896","title":"A General Framework for Jersey Number Recognition in Sports Video","created":"2024-05-22","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":"2205.11016","title":"MolMiner: You only look once for chemical structure recognition","created":"2022-05-23","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":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2111.02394","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","created":"2021-11-03","cited_by_count":9,"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":"2207.11469","title":"Progressive Scene Text Erasing with Self-Supervision","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2301.08898","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","created":"2023-01-21","cited_by_count":9,"area":null},{"id":"2306.07842","title":"PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2308.10408","title":"Turning a CLIP Model into a Scene Text Spotter","created":"2023-08-21","cited_by_count":9,"area":null},{"id":"2312.05286","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2507.18264","title":"Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil","created":"2025-07-24","cited_by_count":9,"area":null},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2207.14807","title":"PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2209.03268","title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2305.14725","title":"AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2402.03082","title":"Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2412.10255","title":"AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era","created":"2024-12-13","cited_by_count":8,"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":"2205.03562","title":"Graph Fusion Network for Multi-Oriented Object Detection","created":"2022-05-07","cited_by_count":7,"area":null},{"id":"2209.03014","title":"Zoom Text Detector","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2305.19957","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2411.18159","title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2109.03794","title":"Digitize-PID: Automatic Digitization of Piping and Instrumentation Diagrams","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2207.12955","title":"Contextual Text Block Detection towards Scene Text Understanding","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2212.02340","title":"CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2308.02905","title":"FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework","created":"2023-08-05","cited_by_count":6,"area":null},{"id":"2502.14780","title":"ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting","created":"2025-02-20","cited_by_count":6,"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":"2104.04903","title":"BiP-Net: Bidirectional Perspective Strategy based Arbitrary-Shaped Text Detection Network","created":"2021-04-11","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":"2209.02397","title":"A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data","created":"2022-09-06","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":"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":"2308.15624","title":"Detection of Mild Cognitive Impairment Using Facial Features in Video Conversations","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2403.03719","title":"Multimodal Transformer for Comics Text-Cloze","created":"2024-03-06","cited_by_count":5,"area":null},{"id":"2411.13929","title":"From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2501.17441","title":"Towards Making Flowchart Images Machine Interpretable","created":"2025-01-29","cited_by_count":5,"area":null}],"next_cursor":"100"}