StyleText is a new large-scale dataset and benchmark for stylized scene text inpainting, constructed via an automated pipeline and paired with a FluxFill+LoRA baseline that improves OCR accuracy.
hub Baseline reference
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
Baseline reference. 62% of citing Pith papers use this work as a benchmark or comparison.
20
Pith papers citing it
Baseline
62% of classified citations
abstract
This paper describes the COCO-Text dataset. In recent years large-scale datasets like SUN and Imagenet drove the advancement of scene understanding and object recognition. The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images. The dataset is based on the MS COCO dataset, which contains images of complex everyday scenes. The images were not collected with text in mind and thus contain a broad variety of text instances. To reflect the diversity of text in natural scenes, we annotate text with (a) location in terms of a bounding box, (b) fine-grained classification into machine printed text and handwritten text, (c) classification into legible and illegible text, (d) script of the text and (e) transcriptions of legible text. The dataset contains over 173k text annotations in over 63k images. We provide a statistical analysis of the accuracy of our annotations. In addition, we present an analysis of three leading state-of-the-art photo Optical Character Recognition (OCR) approaches on our dataset. While scene text detection and recognition enjoys strong advances in recent years, we identify significant shortcomings motivating future work.
hub tools
citation-role summary
dataset 5
background 3
citation-polarity summary
representative citing papers
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
Introduces a new dataset and three-tier competition for visual question answering that requires reading scene text to answer questions about images.
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
OCRBench provides the largest evaluation suite yet for OCR capabilities in large multimodal models, revealing gaps in multilingual, handwritten, and mathematical text handling.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
Evaluation of MLLMs on assistive scenarios with a new egocentric benchmark called NetraLink provides a diagnostic of model strengths and limitations in object recognition, scene text, and multilingual understanding.
Releases three object-centric datasets with 256x256 standardized crops and annotations to support constrained-data image generation and augmentation.
Survey proposing a taxonomy for document parsing into pipeline-based systems and VLM-driven unified models, reviewing components, metrics, benchmarks, and challenges.
The RRC-MLT-2019 report describes an expanded multi-lingual scene text challenge with new tasks, a 20k-image real dataset, synthetic data, and competition outcomes from 60 submissions.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
citing papers explorer
-
StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting
StyleText is a new large-scale dataset and benchmark for stylized scene text inpainting, constructed via an automated pipeline and paired with a FluxFill+LoRA baseline that improves OCR accuracy.
-
AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
-
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
-
ICDAR 2019 Competition on Scene Text Visual Question Answering
Introduces a new dataset and three-tier competition for visual question answering that requires reading scene text to answer questions about images.
-
Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
-
Amplifying Membership Signal Through Chained Regeneration
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
-
OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
OCRBench provides the largest evaluation suite yet for OCR capabilities in large multimodal models, revealing gaps in multilingual, handwritten, and mathematical text handling.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
-
Common Inpainted Objects In-N-Out of Context
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.
-
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
-
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
-
Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications
Evaluation of MLLMs on assistive scenarios with a new egocentric benchmark called NetraLink provides a diagnostic of model strengths and limitations in object recognition, scene text, and multilingual understanding.
-
Object-Centric Dataset Resources for Constrained-Data Image Generation and Augmentation
Releases three object-centric datasets with 256x256 standardized crops and annotations to support constrained-data image generation and augmentation.
-
Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
Survey proposing a taxonomy for document parsing into pipeline-based systems and VLM-driven unified models, reviewing components, metrics, benchmarks, and challenges.
-
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
The RRC-MLT-2019 report describes an expanded multi-lingual scene text challenge with new tasks, a 20k-image real dataset, synthetic data, and competition outcomes from 60 submissions.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
- DataComp-VLM: Improved Open Datasets for Vision-Language Models