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/yuchuang1205/pal

공식 코드

From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision

https://github.com/yueyu1030/actune

공식 코드

AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models

https://github.com/yuhuigao/fg-bench

공식 코드

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study

https://github.com/yujielu10/seeker

공식 코드

From Text to Pixel: Advancing Long-Context Understanding in MLLMs

https://github.com/yuliang-liu/monkey

공식 코드

TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document

https://github.com/yuliang-liu/multimodalocr

공식 코드

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

https://github.com/yuqiChen94/Active_fuzzer

공식 코드

Active Fuzzing for Testing and Securing Cyber-Physical Systems

https://github.com/yusenzhang826/aim

공식 코드

AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications

https://github.com/yushu-li/hiltta

공식 코드

Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection

https://github.com/yuta-hi/bayesian_unet

공식 코드

Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling

https://github.com/yutingli0606/htr-vt

공식 코드

HTR-VT: Handwritten Text Recognition with Vision Transformer

https://github.com/yuweihao/mm-vet

공식 코드

MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities

https://github.com/yuzhe630/adder-DSE

공식 코드

Cross-layer Optimization for High Speed Adders: A Pareto Driven Machine Learning Approach

https://github.com/ywher/ss-ada

공식 코드

SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic Segmentation

https://github.com/yyysbysb/al_obs_neurips19

공식 코드

The Label Complexity of Active Learning from Observational Data

https://github.com/yzhihao/mcscset

공식 코드

MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction

https://github.com/zacps/al-stopping-conditions

공식 코드

Hitting the Target: Stopping Active Learning at the Cost-Based Optimum

https://github.com/zalanborsos/bilevel_coresets

공식 코드

Semi-supervised Batch Active Learning via Bilevel Optimization

https://github.com/zeyademam/active_learning

공식 코드

Active Learning at the ImageNet Scale

https://github.com/zhang-fengzhuo/active-lathe

공식 코드

Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees

https://github.com/zhangrenyuuchicago/balance

공식 코드

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

https://github.com/zhangxulu1996/gal4personalization

공식 코드

Generative Active Learning for Image Synthesis Personalization

https://github.com/zhangyan-ucas/TEA

공식 코드

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues

https://github.com/zhangyuanhan-ai/bamboo

공식 코드

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

https://github.com/zhenyutang2023/data_selection

공식 코드

Exploring Data Redundancy in Real-world Image Classification through Data Selection

https://github.com/zhesna/EMMA

공식 코드

Mindful Active Learning

https://github.com/zhiqic/chartreader

공식 코드

ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules

https://github.com/zhishenyang/scientific_figure_captioning_dataset

공식 코드

SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning

https://github.com/zhongzhuoyao/HCCR-GoogLeNet

공식 코드

High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps

https://github.com/zi-w/Kitchen2D

공식 코드

Active model learning and diverse action sampling for task and motion planning

https://github.com/ziatdinovmax/ActiveChannelLearning

공식 코드

Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learning

https://github.com/ziatdinovmax/neurobayes

공식 코드

Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data

https://github.com/zirak-ai/pashtoocr

공식 코드

PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language

https://github.com/zixy17/limeqo

공식 코드

Low Rank Learning for Offline Query Optimization

https://github.com/zjw700/mus-cdb

공식 코드

MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection

https://github.com/zn1010/peace

공식 코드

PEaCE: A Chemistry-Oriented Dataset for Optical Character Recognition on Scientific Documents

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