Papers with Code 아카이브
Optical Character Recognition (OCR)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 6
- 보존된 평가 기록
- 20
Optical Character Recognition or Optical Character Reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo, license plates in cars...) or from subtitle text superimposed on an image (for example: from a television broadcast)
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learning atomic forces from uncertainty-calibrated adversarial attacks
MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts
Distributionally Robust Active Learning for Gaussian Process Regression
Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data
Active Learning for Conditional Inverse Design with Crystal Generation and Foundation Atomic Models
Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI
Active Learning Classification from a Signal Separation Perspective
AutoTandemML: Active Learning Enhanced Tandem Neural Networks for Inverse Design Problems
Visual Zero-Shot E-Commerce Product Attribute Value Extraction
Harnessing PDF Data for Improving Japanese Large Multimodal Models
Generating $π$-Functional Molecules Using STGG+ with Active Learning
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models
Physics-Informed Gaussian Process Classification for Constraint-Aware Alloy Design
From Selection to Generation: A Survey of LLM-based Active Learning
Southern Newswire Corpus: A Large-Scale Dataset of Mid-Century Wire Articles Beyond the Front Page
Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
Co-designing Large Language Model Tools for Project-Based Learning with K12 Educators
ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classification
Multifidelity Simulation-based Inference for Computationally Expensive Simulators
Handwritten Text Recognition: A Survey
Towards a Foundation Model for Physics-Informed Neural Networks: Multi-PDE Learning with Active Sampling
Educating a Responsible AI Workforce: Piloting a Curricular Module on AI Policy in a Graduate Machine Learning Course
Adapting Multilingual Embedding Models to Historical Luxembourgish
Col-OLHTR: A Novel Framework for Multimodal Online Handwritten Text Recognition
A physics-based data-driven model for CO$_2$ gas diffusion electrodes to drive automated laboratories
Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
Probabilistic Artificial Intelligence
AL-PINN: Active Learning-Driven Physics-Informed Neural Networks for Efficient Sample Selection in Solving Partial Differential Equations
Automatic quantification of breast cancer biomarkers from multiple 18F-FDG PET image segmentation
Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents
DenseReviewer: A Screening Prioritisation Tool for Systematic Review based on Dense Retrieval
Mining Unstructured Medical Texts With Conformal Active Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.