{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2308.15070","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","created":"2023-08-29","cited_by_count":257},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"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},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","cited_by_count":131},{"id":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"1603.03915","title":"Robust Scene Text Recognition with Automatic Rectification","created":"2016-03-12","cited_by_count":121},{"id":"1811.04256","title":"Scene Text Detection and Recognition: The Deep Learning Era","created":"2018-11-10","cited_by_count":114},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"1912.09421","title":"Neural Design Network: Graphic Layout Generation with Constraints","created":"2019-12-19","cited_by_count":83},{"id":"2003.10557","title":"ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation","created":"2020-03-23","cited_by_count":69},{"id":"2003.02567","title":"GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images","created":"2020-03-05","cited_by_count":68},{"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},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58},{"id":"2312.12142","title":"FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning","created":"2023-12-19","cited_by_count":48},{"id":"1807.03021","title":"Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes","created":"2018-07-09","cited_by_count":44},{"id":"2003.10608","title":"UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World","created":"2020-03-24","cited_by_count":43},{"id":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","cited_by_count":43},{"id":"2205.00146","title":"Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator","created":"2022-04-30","cited_by_count":32},{"id":"2312.02433","title":"Lenna: Language Enhanced Reasoning Detection Assistant","created":"2023-12-05","cited_by_count":29},{"id":"2202.11456","title":"SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text","created":"2022-02-23","cited_by_count":26},{"id":"2011.06704","title":"Diffusion models for Handwriting Generation","created":"2020-11-13","cited_by_count":25},{"id":"2303.16576","title":"WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models","created":"2023-03-29","cited_by_count":23},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23},{"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},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13},{"id":"2305.15660","title":"Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition","created":"2023-05-25","cited_by_count":10},{"id":"2402.13643","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","created":"2024-02-21","cited_by_count":10},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","cited_by_count":7},{"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}],"next_cursor":null}