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.
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information
GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise
NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts
UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection
Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop
TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale
Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation
An information-matching approach to optimal experimental design and active learning
Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning
Exploiting Contextual Uncertainty of Visual Data for Efficient Training of Deep Models
HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction
Unlocking the Archives: Using Large Language Models to Transcribe Handwritten Historical Documents
Machine Learning-Accelerated Multi-Objective Design of Fractured Geothermal Systems
Handwriting Recognition in Historical Documents with Multimodal LLM
Cost-Aware Query Policies in Active Learning for Efficient Autonomous Robotic Exploration
SpiroActive: Active Learning for Efficient Data Acquisition for Spirometry
Structured Analysis and Comparison of Alphabets in Historical Handwritten Ciphers
Are VLMs Really Blind
Active Learning for Vision-Language Models
DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers
Machine Unlearning using Forgetting Neural Networks
Toxicity of the Commons: Curating Open-Source Pre-Training Data
Evaluation of uncertainty estimations for Gaussian process regression based machine learning interatomic potentials
Annotation Efficiency: Identifying Hard Samples via Blocked Sparse Linear Bandits
Efficient Biological Data Acquisition through Inference Set Design
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
Integrating Canonical Neural Units and Multi-Scale Training for Handwritten Text Recognition
Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation
Towards Visual Text Design Transfer Across Languages
Exploring the Universe with SNAD: Anomaly Detection in Astronomy
Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learning
regAL: Python Package for Active Learning of Regression Problems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.