{"list":"other","total":126,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"1901.06767","title":"LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators","created":"2019-01-21","cited_by_count":131},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","cited_by_count":131},{"id":"1811.00751","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","created":"2018-11-02","cited_by_count":130},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"1907.10719","title":"LayoutVAE: Stochastic Scene Layout Generation From a Label Set","created":"2019-07-24","cited_by_count":119},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112},{"id":"1712.00516","title":"Multi-Content GAN for Few-Shot Font Style Transfer","created":"2017-12-01","cited_by_count":100},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"2306.04141","title":"Art and the science of generative AI: A deeper dive","created":"2023-06-07","cited_by_count":95},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92},{"id":"1904.02632","title":"A Learned Representation for Scalable Vector Graphics","created":"2019-04-04","cited_by_count":91},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88},{"id":"1609.03605","title":"Detecting Text in Natural Image with Connectionist Text Proposal Network","created":"2016-09-12","cited_by_count":85},{"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},{"id":"1912.09421","title":"Neural Design Network: Graphic Layout Generation with Constraints","created":"2019-12-19","cited_by_count":83},{"id":"2206.04655","title":"Towards Layer-wise Image Vectorization","created":"2022-06-09","cited_by_count":79},{"id":"2312.16476","title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","created":"2023-12-27","cited_by_count":76},{"id":"2403.19128","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","created":"2024-03-28","cited_by_count":74},{"id":"1605.00075","title":"Deep Colorization","created":"2016-04-30","cited_by_count":70},{"id":"2104.03064","title":"DG-Font: Deformable Generative Networks for Unsupervised Font Generation","created":"2021-04-07","cited_by_count":70},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2009.05284","title":"Attribute-conditioned Layout GAN for Automatic Graphic Design","created":"2020-09-11","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":"2303.01818","title":"Word-As-Image for Semantic Typography","created":"2023-03-03","cited_by_count":63},{"id":"1907.09837","title":"ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution","created":"2019-07-23","cited_by_count":61},{"id":"2303.15937","title":"PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout","created":"2023-03-28","cited_by_count":61},{"id":"2305.02567","title":"LayoutDM: Transformer-based Diffusion Model for Layout Generation","created":"2023-05-04","cited_by_count":57},{"id":"1910.04987","title":"Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning","created":"2019-10-11","cited_by_count":53},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46},{"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":"2007.02190","title":"B\\'ezierSketch: A generative model for scalable vector sketches","created":"2020-07-04","cited_by_count":43},{"id":"2303.05049","title":"Unifying Layout Generation with a Decoupled Diffusion Model","created":"2023-03-09","cited_by_count":41},{"id":"2303.11589","title":"LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models","created":"2023-03-21","cited_by_count":41},{"id":"2312.12232","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","created":"2023-12-19","cited_by_count":41},{"id":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","cited_by_count":41},{"id":"2212.05895","title":"Diff-Font: Diffusion Model for Robust One-Shot Font Generation","created":"2022-12-12","cited_by_count":40},{"id":"2406.08232","title":"OpenCOLE: Towards Reproducible Automatic Graphic Design Generation","created":"2024-06-12","cited_by_count":37},{"id":"1804.04128","title":"Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation","created":"2018-04-11","cited_by_count":35},{"id":"2205.09965","title":"Few-Shot Font Generation by Learning Fine-Grained Local Styles","created":"2022-05-20","cited_by_count":34},{"id":"2212.02122","title":"CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics","created":"2022-12-05","cited_by_count":34},{"id":"2303.17870","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","created":"2023-03-31","cited_by_count":34},{"id":"2405.10317","title":"Text-to-Vector Generation with Neural Path Representation","created":"2024-05-16","cited_by_count":33},{"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":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31},{"id":"2004.03015","title":"Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment","created":"2020-04-06","cited_by_count":28},{"id":"1802.03345","title":"A Two-Stage Method for Text Line Detection in Historical Documents","created":"2018-02-09","cited_by_count":26},{"id":"2303.09604","title":"DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion","created":"2023-03-16","cited_by_count":26},{"id":"2303.14017","title":"CF-Font: Content Fusion for Few-shot Font Generation","created":"2023-03-24","cited_by_count":26},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25},{"id":"2312.04145","title":"Diffusing Colors: Image Colorization with Text Guided Diffusion","created":"2023-12-07","cited_by_count":25},{"id":"1507.03196","title":"DeepFont: Identify Your Font from An Image","created":"2015-07-12","cited_by_count":24},{"id":"1611.09026","title":"Awesome Typography: Statistics-Based Text Effects Transfer","created":"2016-11-28","cited_by_count":24},{"id":"2106.04912","title":"ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis","created":"2021-06-09","cited_by_count":23},{"id":"1708.02660","title":"Learning Visual Importance for Graphic Designs and Data Visualizations","created":"2017-08-08","cited_by_count":22},{"id":"1909.02072","title":"Large-scale Tag-based Font Retrieval with Generative Feature Learning","created":"2019-09-04","cited_by_count":22},{"id":"2303.03755","title":"DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer","created":"2023-03-07","cited_by_count":20},{"id":"2204.02701","title":"Aesthetic Text Logo Synthesis via Content-aware Layout Inferring","created":"2022-04-06","cited_by_count":19},{"id":"2309.09506","title":"LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models","created":"2023-09-18","cited_by_count":19},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19},{"id":"2406.09794","title":"SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis","created":"2024-06-14","cited_by_count":19},{"id":"2311.11591","title":"DesignGPT: Multi-Agent Collaboration in Design","created":"2023-11-20","cited_by_count":17},{"id":"1801.01922","title":"Vectorization of Line Drawings via PolyVector Fields","created":"2018-01-05","cited_by_count":16},{"id":"2409.19051","title":"Multimodal Markup Document Models for Graphic Design Completion","created":"2024-09-27","cited_by_count":16},{"id":"2410.10168","title":"First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending","created":"2024-10-14","cited_by_count":16}],"next_cursor":"100"}