GUI Agents

• OmniParser for Pure Vision Based GUI Agent (08 Arxiv)

• UI-Hawk: Unleashing the Screen Stream Understanding for GUI Agents (08 Arxiv)

Text Recognition

• PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer (ECCV2024)

• Self-supervised Character-to-Character Distillation for Text Recognition (ICCV 2023)

• MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition (ICCV 2023)

• Revisiting Scene Text Recognition: A Data Perspective (ICCV 2023)

• Self-Supervised Implicit Glyph Attention for Text Recognition (CVPR 2023)

• Relational Contrastive Learning for Scene Text Recognition (ACMMM 2023)

• TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition (IJCAI 2023)

• Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition (IJCAI 2023)

• Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition (ACMMM 2022)

• Chinese Character Recognition with Augmented Character Profile Matching (ACMMM 2022)
  

• Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

• Task Grouping for Multilingual Text Recognition (Workshops) (ECCV 2022 Workshops)

• Multi-modal Text Recognition Networks: Interactive Enhancements Between Visual and Semantic Features (ECCV 2022)

• On Calibration of Scene-Text Recognition Models (Workshops) (ECCV 2022 Workshops)

• Pure Transformer with Integrated Experts for Scene Text Recognition (ECCV 2022)

• Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning (ECCV 2022)

• Multi-granularity Prediction for Scene Text Recognition (ECCV 2022)

• Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition (ECCV 2022)

• Background-Insensitive Scene Text Recognition with Text Semantic Segmentation (ECCV 2022)

• SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition (ECCV 2022)

• Levenshtein OCR (ECCV 2022)

• SVTR: Scene Text Recognition with a Single Visual Model (IJCAI 2022)

• Open-Set Text Recognition via Character-Context Decoupling (CVPR 2022)

• Knowledge Mining with Scene Text for Fine-Grained Recognition (CVPR 2022)

• Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition (AAAI 2022)

• Perceiving Stroke-Semantic Context: Hierarchical Contrastive Learning for Robust Scene Text Recognition (AAAI 2022)

• Context-Based Contrastive Learning for Scene Text Recognition (AAAI 2022)

• Sequence-to-Sequence Contrastive Learning for Text Recognition (CVPR 2021)

• What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels (CVPR 2021)

• MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition (CVPR 2021)

• Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition (CVPR 2021)

• Dictionary-Guided Scene Text Recognition (CVPR 2021)

• Primitive Representation Learning for Scene Text Recognition (CVPR 2021)

Controllable Text Generation

• How To Create SOTA Image Generation with Text: Recraft’s ML Team Insights

• Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering (ECCV2024)

• Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering (ECCV2024)

• ANYTEXT: MULTILINGUAL VISUAL TEXT GENERATION AND EDITING (ICLR2024)

• Character-Aware Models Improve Visual Text Rendering (ACL2023)

• TextDiffuser: Diffusion Models as Text Painters (NeurIPS2023)

• GlyphControl: Glyph Conditional Control for Visual Text Generation (NeurIPS2023)

• Layout-Agnostic Scene Text Image Synthesis with Diffusion Models (CVPR2024)

• CustomText: Customized Textual Image Generation using Diffusion Models (CVPR2024)

• TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering (Arxiv)

• Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation (Arxiv)

• Typographic Text Generation with Off-the-Shelf Diffusion Model (Arxiv)

• High Fidelity Scene Text Synthesis (Arxiv)

• UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models (Arxiv)

• GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (Arxiv)

• ARTIST: Improving the Generation of Text-rich Images by Disentanglement (Arxiv)

Multi-modal Large Language Model

• On Pre-training of Multimodal Language Models Customized for Chart Understanding (06 Arxiv)

• PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling (10 Arxiv)

• MPLUG-DOCOWL2: HIGH-RESOLUTION COMPRESSING FOR OCR-FREE MULTI-PAGE DOCUMENT UNDERSTANDING (09 Arxiv)

• LayTextLLM: A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (06 Arxiv)

• RegionGPT: Towards Region Understanding Vision Language Model (05 Arxiv)

• Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding (NeurIPS 2024)

• Honeybee: Locality-enhanced Projector for Multimodal LLM (CVPR24)

• Continuous or Discrete, That Is the Question: A Survey on Large MultiModal Models from the Perspective of Input-Output Space Extension (11 Arxiv)

• MobileVLM V2: Faster and Stronger Baseline for Vision Language Model (01 Arxiv)

• InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD (04 Arxiv)

• Mini-Monkey: Alleviate the Sawtooth Effect by Multi-Scale Adaptive Cropping (08 Arxiv)

• InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks (CVPR2024)

• TRINS: Towards Multimodal Language Models that Can Read (CVPR2024)

• UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (EMNLP2023)

• On Pre-training of Multimodal Language Models Customized for Chart Understanding (Arxiv)

• LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models (Arxiv)

• Multimodal Table Understanding (Arxiv)

• Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding (Arxiv)

• LayTextLLM: A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (Arxiv)

• MoAI: Mixture of All Intelligence for Large Language and Vision Models (Arxiv)

• Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning (Arxiv)

• TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document (Arxiv)

• DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding (Arxiv)

• Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models (Arxiv)

• Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding (Arxiv)

• TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models (Arxiv)

• mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (Arxiv)

• DOCLLM: A LAYOUT-AWARE GENERATIVE LANGUAGE MODEL FOR MULTIMODAL DOCUMENT UNDERSTANDING (12-2023 Arxiv)

Text Detection

• Bridging Synthetic and Real Worlds for Pre-training Scene Text Detector (ECCV2024)

• LORE: Logical Location Regression Network for Table Structure Recognition (AAAI2024)

• LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI2024)

• CPN: Complementary Proposal Network for Unconstrained Text Detection (AAAI2024)