{"list":"other","total":59,"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":"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"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":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"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":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"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":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140},{"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":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"1907.10719","title":"LayoutVAE: Stochastic Scene Layout Generation From a Label Set","created":"2019-07-24","cited_by_count":119},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106},{"id":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"2212.10562","title":"Character-Aware Models Improve Visual Text Rendering","created":"2022-12-20","cited_by_count":92},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"2403.09622","title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering","created":"2024-03-14","cited_by_count":81},{"id":"2003.02567","title":"GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images","created":"2020-03-05","cited_by_count":68},{"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":"2205.00303","title":"Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs","created":"2022-04-30","cited_by_count":59},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48},{"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":"2406.10208","title":"Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering","created":"2024-06-14","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":"2206.00169","title":"Discovering the Hidden Vocabulary of DALLE-2","created":"2022-06-01","cited_by_count":43},{"id":"2306.09086","title":"Relation-Aware Diffusion Model for Controllable Poster Layout Generation","created":"2023-06-15","cited_by_count":37},{"id":"2404.00995","title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation","created":"2024-04-01","cited_by_count":35},{"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":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22},{"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":"2407.11502","title":"How Control Information Influences Multilingual Text Image Generation and Editing?","created":"2024-07-16","cited_by_count":9},{"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}