{"list":"other","total":118,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"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":"1904.00523","title":"Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model","created":"2019-04-01","cited_by_count":403},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"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":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","cited_by_count":131},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2212.10562","title":"Character-Aware Models Improve Visual Text Rendering","created":"2022-12-20","cited_by_count":92},{"id":"1908.03047","title":"Editing Text in the Wild","created":"2019-08-08","cited_by_count":82},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73},{"id":"2003.10557","title":"ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation","created":"2020-03-23","cited_by_count":69},{"id":"1812.05840","title":"Spatial Fusion GAN for Image Synthesis","created":"2018-12-14","cited_by_count":68},{"id":"2005.03341","title":"Scene Text Image Super-Resolution in the Wild","created":"2020-05-07","cited_by_count":63},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55},{"id":"2003.08152","title":"SwapText: Image Based Texts Transfer in Scenes","created":"2020-03-18","cited_by_count":50},{"id":"2106.08385","title":"TextStyleBrush: Transfer of Text Aesthetics from a Single Example","created":"2021-06-15","cited_by_count":49},{"id":"1903.01192","title":"STEFANN: Scene Text Editor using Font Adaptive Neural Network","created":"2019-03-04","cited_by_count":47},{"id":"2011.14021","title":"Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach","created":"2020-11-27","cited_by_count":45},{"id":"2304.05568","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","created":"2023-04-12","cited_by_count":45},{"id":"2305.10825","title":"DiffUTE: Universal Text Editing Diffusion Model","created":"2023-05-18","cited_by_count":45},{"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":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43},{"id":"1609.01326","title":"UnrealCV: Connecting Computer Vision to Unreal Engine","created":"2016-09-05","cited_by_count":41},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41},{"id":"2110.12942","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","created":"2021-10-25","cited_by_count":39},{"id":"1909.09470","title":"Document Rectification and Illumination Correction using a Patch-based CNN","created":"2019-09-20","cited_by_count":38},{"id":"2106.15368","title":"Text Prior Guided Scene Text Image Super-resolution","created":"2021-06-29","cited_by_count":37},{"id":"2212.01982","title":"Exploring Stroke-Level Modifications for Scene Text Editing","created":"2022-12-05","cited_by_count":37},{"id":"2305.03892","title":"DocDiff: Document Enhancement via Residual Diffusion Models","created":"2023-05-06","cited_by_count":37},{"id":"2203.09388","title":"A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution","created":"2022-03-17","cited_by_count":35},{"id":"1903.04092","title":"MTRNet: A Generic Scene Text Eraser","created":"2019-03-11","cited_by_count":29},{"id":"2112.08171","title":"Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution","created":"2021-12-13","cited_by_count":28},{"id":"1812.00723","title":"EnsNet: Ensconce Text in the Wild","created":"2018-12-03","cited_by_count":27},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27},{"id":"2210.08161","title":"Geometric Representation Learning for Document Image Rectification","created":"2022-10-15","cited_by_count":27},{"id":"1705.02772","title":"Scene Text Eraser","created":"2017-05-08","cited_by_count":26},{"id":"1909.07113","title":"TextSR: Content-Aware Text Super-Resolution Guided by Recognition","created":"2019-09-16","cited_by_count":26},{"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},{"id":"2204.14044","title":"C3-STISR: Scene Text Image Super-resolution with Triple Clues","created":"2022-04-29","cited_by_count":26},{"id":"2110.14968","title":"DocScanner: Robust Document Image Rectification with Progressive Learning","created":"2021-10-28","cited_by_count":25},{"id":"2203.16850","title":"Revisiting Document Image Dewarping by Grid Regularization","created":"2022-03-31","cited_by_count":25},{"id":"1912.07183","title":"MTRNet++: One-stage Mask-based Scene Text Eraser","created":"2019-12-16","cited_by_count":24},{"id":"2109.07756","title":"Dense Semantic Contrast for Self-Supervised Visual Representation Learning","created":"2021-09-16","cited_by_count":24},{"id":"2303.14726","title":"Learning Generative Structure Prior for Blind Text Image Super-resolution","created":"2023-03-26","cited_by_count":24},{"id":"2203.09910","title":"Fourier Document Restoration for Robust Document Dewarping and Recognition","created":"2022-03-18","cited_by_count":23},{"id":"2104.06815","title":"Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network","created":"2021-04-14","cited_by_count":21},{"id":"2104.11493","title":"Stroke-Based Scene Text Erasing Using Synthetic Data for Training","created":"2021-04-23","cited_by_count":20},{"id":"1506.02211","title":"Boosting Optical Character Recognition: A Super-Resolution Approach","created":"2015-06-07","cited_by_count":19},{"id":"2011.09768","title":"Scene text removal via cascaded text stroke detection and erasing","created":"2020-11-19","cited_by_count":18},{"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":"2308.03262","title":"A Benchmark for Chinese-English Scene Text Image Super-resolution","created":"2023-08-07","cited_by_count":17},{"id":"2207.11515","title":"Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild","created":"2022-07-23","cited_by_count":16},{"id":"2304.08796","title":"Deep Unrestricted Document Image Rectification","created":"2023-04-18","cited_by_count":16},{"id":"2210.08216","title":"UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior","created":"2022-10-15","cited_by_count":15},{"id":"2302.10414","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","created":"2023-02-21","cited_by_count":15},{"id":"2311.09759","title":"Scene Text Image Super-resolution based on Text-conditional Diffusion Models","created":"2023-11-16","cited_by_count":15},{"id":"1901.09193","title":"Scene Text Synthesis for Efficient and Effective Deep Network Training","created":"2019-01-26","cited_by_count":14},{"id":"1911.09026","title":"Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation","created":"2019-11-19","cited_by_count":14},{"id":"2106.13029","title":"PERT: A Progressively Region-based Network for Scene Text Removal","created":"2021-06-24","cited_by_count":13},{"id":"2109.02762","title":"STRIVE: Scene Text Replacement In Videos","created":"2021-09-06","cited_by_count":13},{"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},{"id":"2306.09593","title":"FETNet: Feature Erasing and Transferring Network for Scene Text Removal","created":"2023-06-16","cited_by_count":12},{"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},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12},{"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}],"next_cursor":"100"}