{"total":167,"rows":[{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"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":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"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":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"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":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63,"area":null},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"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":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"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":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","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":"2412.09604","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","created":"2024-12-12","cited_by_count":42,"area":null},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41,"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":"2212.01982","title":"Exploring Stroke-Level Modifications for Scene Text Editing","created":"2022-12-05","cited_by_count":37,"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":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2305.03347","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","created":"2023-05-05","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":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","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":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2203.10492","title":"SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization","created":"2022-03-20","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":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","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":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18,"area":null},{"id":"2207.11169","title":"Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark","created":"2022-07-22","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":"2104.01552","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","created":"2021-04-04","cited_by_count":15,"area":null},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"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":"2206.13381","title":"TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask","created":"2022-06-27","cited_by_count":13,"area":null},{"id":"2207.04675","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","created":"2022-07-11","cited_by_count":13,"area":null},{"id":"2305.01443","title":"Scalable Mask Annotation for Video Text Spotting","created":"2023-05-02","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":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","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":"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":"2405.13896","title":"A General Framework for Jersey Number Recognition in Sports Video","created":"2024-05-22","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":"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":"2109.04699","title":"EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling","created":"2021-09-10","cited_by_count":10,"area":null},{"id":"2112.06104","title":"Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection","created":"2021-12-12","cited_by_count":10,"area":null},{"id":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2305.03327","title":"FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation","created":"2023-05-05","cited_by_count":10,"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":"2110.04488","title":"Demystifying the Transferability of Adversarial Attacks in Computer Networks","created":"2021-10-09","cited_by_count":9,"area":null},{"id":"2304.04376","title":"ICDAR 2023 Video Text Reading Competition for Dense and Small Text","created":"2023-04-10","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2210.06924","title":"Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2305.10029","title":"TextSLAM: Visual SLAM with Semantic Planar Text Features","created":"2023-05-17","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":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2506.00721","title":"Common Inpainted Objects In-N-Out of Context","created":"2025-05-31","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2512.16270","title":"TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2207.08417","title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning","created":"2022-07-18","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":"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":"2312.01938","title":"DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text","created":"2023-11-29","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":"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":"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":"2205.08257","title":"Detection Masking for Improved OCR on Noisy Documents","created":"2022-05-17","cited_by_count":5,"area":null},{"id":"2309.08919","title":"Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution","created":"2023-09-16","cited_by_count":5,"area":null},{"id":"2402.01697","title":"APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT","created":"2024-01-24","cited_by_count":5,"area":null},{"id":"2408.00106","title":"WAS: Dataset and Methods for Artistic Text Segmentation","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2506.09082","title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2510.20803","title":"ARGenSeg: Image Segmentation with Autoregressive Image Generation Model","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2112.14976","title":"Contrastive Learning of Semantic and Visual Representations for Text Tracking","created":"2021-12-30","cited_by_count":4,"area":null},{"id":"2212.04116","title":"OCR-RTPS: An OCR-based real-time positioning system for the valet parking","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2304.10097","title":"Scene Style Text Editing","created":"2023-04-20","cited_by_count":4,"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":"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":"2410.18277","title":"KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2405.00260","title":"CREPE: Coordinate-Aware End-to-End Document Parser","created":"2024-05-01","cited_by_count":3,"area":null}],"next_cursor":"100"}