REVIEW 16 cited by
PP-OCR: A Practical Ultra Lightweight OCR System
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The Optical Character Recognition (OCR) systems have been widely used in various of application scenarios, such as office automation (OA) systems, factory automations, online educations, map productions etc. However, OCR is still a challenging task due to the various of text appearances and the demand of computational efficiency. In this paper, we propose a practical ultra lightweight OCR system, i.e., PP-OCR. The overall model size of the PP-OCR is only 3.5M for recognizing 6622 Chinese characters and 2.8M for recognizing 63 alphanumeric symbols, respectively. We introduce a bag of strategies to either enhance the model ability or reduce the model size. The corresponding ablation experiments with the real data are also provided. Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17.9M images are used). Besides, the proposed PP-OCR are also verified in several other language recognition tasks, including French, Korean, Japanese and German. All of the above mentioned models are open-sourced and the codes are available in the GitHub repository, i.e., https://github.com/PaddlePaddle/PaddleOCR.
Forward citations
Cited by 16 Pith papers
-
Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
General-purpose VLMs systematically rewrite perturbed words back to the original — up to 4.5 WER points on English — with rewriting tied to representation similarity and word length.
-
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
A budgeted evidence-seeking agent that selects a small set of OCR, speech, and key-frame clues outperforms full-video and exhaustive-input baselines for video misinformation detection.
-
GUI-AC: Enhancing Continual Learning in GUI Agents
GUI-AC stabilizes RFT for non-stationary GUI data by down-weighting noisy advantages and relaxing clipping bounds via a grounding certainty term.
-
VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding
A multilingual, multi-page document retrieval benchmark with 35K+ QA pairs shows MLLM retrievers lead but still fail on tables and low-resource languages.
-
MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning
A new one-million-sample multimodal agent tuning dataset with GPT-4o-generated rationales, reflection, and tool/RAG calls is shown to improve fine-tuned models, though training/eval benchmark overlap is not addressed.
-
Region-based Cluster Discrimination for Visual Representation Learning
RICE improves vision encoders by applying cluster discrimination at the region level and unifying object and OCR classification targets in one pretraining framework.
-
DREAM: Document Reconstruction via End-to-end Autoregressive Model
A single model, DREAM, jointly predicts layout elements, coordinates, and transcriptions for document reconstruction, along with a new metric (DSM) and benchmark (DocRec1K).
-
Uncertainty-Aware Complex Scientific Table Data Extraction
Applying conformal prediction to TSR+OCR outputs flags incorrect table cells; the paper reports 53% labor savings and a 30-point accuracy gain, but the flagging threshold is fitted to the test data.
-
MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models
A synthetic music sheet QA dataset and a LoRA-fine-tuned Phi-3 model show large accuracy gains on OMR and chord tasks, but only within the synthetic distribution.
-
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
VRAG-RL uses GRPO reinforcement learning with visual cropping actions and a retrieval-aware reward to improve vision-language RAG agents on document benchmarks.
-
Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications
A survey of instruction-based image editing plus a new 21-task benchmark, CDD-IIE, on which ten open models are scored by human experts.
-
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
A 1B end-to-end VLM reports 83.2 on OlmOCR-Bench after excluding the headers/footers category, plus a new image-localization benchmark.
-
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
A lightweight vision-language transformer with a weakly supervised perspective-correction module reaches about 99% accuracy on modified CCPD license plate benchmarks.
-
GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding
Modeling GUI elements as Gaussian distributions instead of binary targets yields 92.0% (ScreenSpot), 93.3% (ScreenSpot-v2), and 47.5% (ScreenSpot-Pro) for a 7B model, outperforming UI-TARS-72B by a relative 24.7% on t...
-
Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis
For cropped street words, a 15M-parameter CNN OCR model matches or beats much larger VLMs under synthetic weather, while Qwen2.5-VL 3B is the best full-scene VLM.
-
A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions
A survey of Vietnamese document analysis and recognition that catalogs methods, datasets, and open challenges without introducing new experimental results.
Discussion (0). Sign in to comment.