Papers with Code 아카이브

Optical Character Recognition (OCR)

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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)

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/dakot/probal

공식 코드

Toward Optimal Probabilistic Active Learning Using a Bayesian Approach

https://github.com/dali92002/DE-GAN

공식 코드

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

https://github.com/dali92002/htrbymatching

공식 코드

Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition

https://github.com/damo-nlp-sg/multimodal_textbook

공식 코드

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

https://github.com/dancewithDianTong/COMBOO

공식 코드

Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

https://github.com/danielsun94/conversational_diagnosis

공식 코드

Conversational Disease Diagnosis via External Planner-Controlled Large Language Models

https://github.com/danielt17/Deep-Neural-Trees-Simulation-Environment

공식 코드

Stealing Black-Box Functionality Using The Deep Neural Tree Architecture

https://github.com/danikiyasseh/SoCal

공식 코드

SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals

https://github.com/danikiyasseh/SoQal

공식 코드

SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals

https://github.com/data61/aboleth

공식 코드

Noise Contrastive Priors for Functional Uncertainty

https://github.com/dataiku-research/openal

공식 코드

OpenAL: Evaluation and Interpretation of Active Learning Strategies

https://github.com/dataiku-research/paper_ial_2021

공식 코드

Sample Noise Impact on Active Learning

https://github.com/dataiku-research/sample_noise_impact_on_active_learning

공식 코드

Sample Noise Impact on Active Learning

https://github.com/datascienceuibk/chroniclingamericaqa

공식 코드

ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages

https://github.com/datascienceuibk/multiocr-qa

공식 코드

MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts

https://github.com/datvo06/MSAU

공식 코드

End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net

https://github.com/davidjurgens/potato

공식 코드

POTATO: The Portable Text Annotation Tool

https://github.com/davidtw999/bemps

공식 코드

Diversity Enhanced Active Learning with Strictly Proper Scoring Rules

https://github.com/davidzhangyuanhan/bamboo

공식 코드

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

https://github.com/dbmdz/clef-hipe

공식 코드

hmBERT: Historical Multilingual Language Models for Named Entity Recognition

https://github.com/dbrainio/cyrillichandwritingpoc

공식 코드

Data Generation for Post-OCR correction of Cyrillic handwriting

https://github.com/dcgm/biblio-dataset

공식 코드

BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction

https://github.com/dcgm/softctc

공식 코드

SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels

https://github.com/decile-team/distil

공식 코드

SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios

https://github.com/deep-scribe/handwriting-recognition

공식 코드

Motion-Based Handwriting Recognition and Word Reconstruction

https://github.com/deeplearnxmu/mc_tit

공식 코드

Exploring Better Text Image Translation with Multimodal Codebook

https://github.com/deepmicroscopy/adaptiveregionselection

공식 코드

Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation

https://github.com/deepmind/dm_nevis

공식 코드

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

https://github.com/deepmind/neural_testbed

공식 코드

Fine-Tuning Language Models via Epistemic Neural Networks

https://github.com/deepseek-ai/deepseek-vl

공식 코드

DeepSeek-VL: Towards Real-World Vision-Language Understanding

https://github.com/dell-research-harvard/effocr

공식 코드

Efficient OCR for Building a Diverse Digital History

https://github.com/dell-research-harvard/quantifying-character-similarity

공식 코드

Quantifying Character Similarity with Vision Transformers

https://github.com/dholzmueller/bmdal_reg

공식 코드

A Framework and Benchmark for Deep Batch Active Learning for Regression

https://github.com/dhuseljic/dal-toolbox

공식 코드

Efficient Bayesian Updates for Deep Learning via Laplace Approximations

https://github.com/diku-dk/credanno

공식 코드

cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule Diagnosis

https://github.com/divelab/atta

공식 코드

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.