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/oatml/causal-bald

공식 코드

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

https://github.com/ofa-sys/ofa

공식 코드

Transferring General Multimodal Pretrained Models to Text Recognition

https://github.com/olivesgatech/RoSE

공식 코드

Targeting Negative Flips in Active Learning using Validation Sets

https://github.com/olivesgatech/clinical-trial-active-learning

공식 코드

Clinical Trial Active Learning

https://github.com/olivesgatech/focal_dataset

공식 코드

FOCAL: A Cost-Aware Video Dataset for Active Learning

https://github.com/olivesgatech/gauss

공식 코드

Gaussian Switch Sampling: A Second Order Approach to Active Learning

https://github.com/olivesgatech/introspective-learning

공식 코드

Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

https://github.com/olivesgatech/man-recon

공식 코드

Man-recon: manifold learning for reconstruction with deep autoencoder for smart seismic interpretation

https://github.com/omegafragger/DDU

공식 코드

Deep Deterministic Uncertainty: A Simple Baseline

https://github.com/open-mmlab/mmocr

공식 코드

MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding

https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/robust_scanner/README.md

공식 코드

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

https://github.com/openai/moderation-api-release

공식 코드

A Holistic Approach to Undesired Content Detection in the Real World

https://github.com/openai/prm800k

공식 코드

Let's Verify Step by Step

https://github.com/opendatalab/OHR-Bench

공식 코드

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

https://github.com/opendatalab/PDF-Extract-Kit

공식 코드

MinerU: An Open-Source Solution for Precise Document Content Extraction

https://github.com/opendatalab/mineru

공식 코드

MinerU: An Open-Source Solution for Precise Document Content Extraction

https://github.com/opendatalab/pm4bench

공식 코드

PM4Bench: A Parallel Multilingual Multi-Modal Multi-task Benchmark for Large Vision Language Model

https://github.com/opengvlab/internvl

공식 코드

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

https://github.com/openmatch/activerag

공식 코드

ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents

https://github.com/ortonwang/pcdal

공식 코드

PCDAL: A Perturbation Consistency-Driven Active Learning Approach for Medical Image Segmentation and Classification

https://github.com/osimeoni/RethinkingDeepActiveLearning

공식 코드

Rethinking deep active learning: Using unlabeled data at model training

https://github.com/ozansener/active_learning_coreset

공식 코드

Active Learning for Convolutional Neural Networks: A Core-Set Approach

https://github.com/paarandika/Gradient-Approx-to-improve-OCR

공식 코드

Unknown-box Approximation to Improve Optical Character Recognition Performance

https://github.com/park-jay/slavery-discourse

공식 코드

A Data-driven Investigation of Euphemistic Language: Comparing the usage of "slave" and "servant" in 19th century US newspapers

https://github.com/parmoo/cfr-materials

공식 코드

A framework for fully autonomous design of materials via multiobjective optimization and active learning: challenges and next steps

https://github.com/pathak22/exploration-by-disagreement

공식 코드

Self-Supervised Exploration via Disagreement

https://github.com/patrickzh/deepcore

공식 코드

DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

https://github.com/peiyunh/alpf

공식 코드

Active Learning with Partial Feedback

https://github.com/peluz/victor-visual-text

공식 코드

Sequence-aware multimodal page classification of Brazilian legal documents

https://github.com/pgiouroukis/dual

공식 코드

DUAL: Diversity and Uncertainty Active Learning for Text Summarization

https://github.com/philip-schrodt/ngec

공식 코드

Creating Custom Event Data Without Dictionaries: A Bag-of-Tricks

https://github.com/philipp-kohl/active-learning-evaluation-framework

공식 코드

ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP

https://github.com/philipp-kohl/scoping-review-active-learning-er

공식 코드

Scoping Review of Active Learning Strategies and their Evaluation Environments for Entity Recognition Tasks

https://github.com/pieter-jacobs/bachelor-thesis

공식 코드

Active learning for reducing labeling effort in text classification tasks

https://github.com/pieterblok/boxal

공식 코드

Improved detection of discarded fish species through BoxAL active learning

https://github.com/pieterblok/maskal

공식 코드

Active learning with MaskAL reduces annotation effort for training Mask R-CNN

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