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/juangamella/aicp

공식 코드

Active Invariant Causal Prediction: Experiment Selection through Stability

https://github.com/juliakreutzer/joeynmt

공식 코드

Self-Regulated Interactive Sequence-to-Sequence Learning

https://github.com/julietljy/bal

공식 코드

BAL: Balancing Diversity and Novelty for Active Learning

https://github.com/jungomi/character-queries

공식 코드

Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation

https://github.com/juntaoluo/erukaexp

공식 코드

Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning

https://github.com/justherozen/freeal

공식 코드

FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models

https://github.com/jvpoulos/Attention-OCR

공식 코드

Character-Based Handwritten Text Transcription with Attention Networks

https://github.com/jwcalder/mstar-active-learning

공식 코드

Graph-based Active Learning for Semi-supervised Classification of SAR Data

https://github.com/jwwthu/MNIST-MIX

공식 코드

MNIST-MIX: A Multi-language Handwritten Digit Recognition Dataset

https://github.com/kadarsh22/disentanglement_based_active_learning

공식 코드

Disentanglement based Active Learning

https://github.com/kaist-dmlab/mqnet

공식 코드

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning

https://github.com/kaist-dmlab/pcb

공식 코드

Active Prompt Learning in Vision Language Models

https://github.com/kaist-dmlab/taufe

공식 코드

Prioritizing Informative Features and Examples for Deep Learning from Noisy Data

https://github.com/kalra20/RISAN-Robust-Instance-Specific-Abstain-Network

공식 코드

RISAN: Robust Instance Specific Abstention Network

https://github.com/kartikgill/easter2

공식 코드

Easter2.0: Improving convolutional models for handwritten text recognition

https://github.com/kartta-labs/project

공식 코드

An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map Images

https://github.com/kasuba-badri-vishal/dhrishtikon

공식 코드

DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images

https://github.com/kerembozgann/adaptive-epsilon-pal

공식 코드

Beyond Grids: Multi-objective Bayesian Optimization With Adaptive Discretization

https://github.com/kerrydrx/evidentialada

공식 코드

Evidential Uncertainty Quantification: A Variance-Based Perspective

https://github.com/khtae8250/SliceTuner

공식 코드

Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models

https://github.com/khtae8250/falcon

공식 코드

Falcon: Fair Active Learning using Multi-armed Bandits

https://github.com/kjetil-lye/ismo_airfoil

공식 코드

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

https://github.com/kjetil-lye/ismo_heat

공식 코드

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

https://github.com/kjetil-lye/ismo_validation

공식 코드

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

https://github.com/kjetil-lye/iterative_surrogate_optimization

공식 코드

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

https://github.com/kkalais/stochlwta-ml

공식 코드

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning

https://github.com/kli58/ROIAL

공식 코드

ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes

https://github.com/kmalialis/actisiamese

공식 코드

Nonstationary data stream classification with online active learning and siamese neural networks

https://github.com/kmalialis/augmented_queues

공식 코드

Data augmentation on-the-fly and active learning in data stream classification

https://github.com/koraykarabina/impacx_onhw

공식 코드

Improving Accuracy and Explainability of Online Handwriting Recognition

https://github.com/koushik-n/Active-Learning-Plant-Phenotyping

공식 코드

How useful is Active Learning for Image-based Plant Phenotyping?

https://github.com/kritisingh24/active_learning_nmt

공식 코드

Active Learning for Neural Machine Translation

https://github.com/kschwethelm/dpal

공식 코드

Differentially Private Active Learning: Balancing Effective Data Selection and Privacy

https://github.com/ksenia-konyushkova/LAL

공식 코드

Learning Active Learning from Data

https://github.com/ksenia-konyushkova/LAL-RL

공식 코드

Discovering General-Purpose Active Learning Strategies

https://github.com/ksreenivasan/OOD_Federated_Learning

공식 코드

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

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