{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"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":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","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":"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":"1712.00516","title":"Multi-Content GAN for Few-Shot Font Style Transfer","created":"2017-12-01","cited_by_count":100},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"1908.03047","title":"Editing Text in the Wild","created":"2019-08-08","cited_by_count":82},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74},{"id":"1812.05840","title":"Spatial Fusion GAN for Image Synthesis","created":"2018-12-14","cited_by_count":68},{"id":"1711.06454","title":"Separating Style and Content for Generalized Style Transfer","created":"2017-11-17","cited_by_count":64},{"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":"2104.00887","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","created":"2021-04-02","cited_by_count":46},{"id":"1905.01354","title":"Controllable Artistic Text Style Transfer via Shape-Matching GAN","created":"2019-05-03","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":"1907.09653","title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition","created":"2019-07-23","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":"2204.05539","title":"Content and Style Aware Generation of Text-line Images for Handwriting Recognition","created":"2022-04-12","cited_by_count":35},{"id":"2303.15269","title":"Handwritten Text Generation from Visual Archetypes","created":"2023-03-27","cited_by_count":32},{"id":"2210.11248","title":"OCR-VQGAN: Taming Text-within-Image Generation","created":"2022-10-19","cited_by_count":31},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31},{"id":"1611.09026","title":"Awesome Typography: Statistics-Based Text Effects Transfer","created":"2016-11-28","cited_by_count":24},{"id":"2110.01890","title":"De-rendering Stylized Texts","created":"2021-10-05","cited_by_count":24},{"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},{"id":"1612.00215","title":"Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts","created":"2016-12-01","cited_by_count":21},{"id":"1812.06384","title":"TET-GAN: Text Effects Transfer via Stylization and Destylization","created":"2018-12-16","cited_by_count":19},{"id":"2102.00653","title":"Deep Learning-based Forgery Attack on Document Images","created":"2021-02-01","cited_by_count":14},{"id":"2109.02762","title":"STRIVE: Scene Text Replacement In Videos","created":"2021-09-06","cited_by_count":13},{"id":"2106.08710","title":"Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence","created":"2021-06-16","cited_by_count":10},{"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},{"id":"2202.06777","title":"Multi-scale Attention Guided Pose Transfer","created":"2022-02-14","cited_by_count":10},{"id":"1906.01466","title":"Selective Style Transfer for Text","created":"2019-06-04","cited_by_count":8},{"id":"2207.09649","title":"GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation","created":"2022-07-20","cited_by_count":6},{"id":"2203.07705","title":"APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation","created":"2022-03-15","cited_by_count":3}],"next_cursor":null}