https://github.com/microsoft/GenerativeImage2Text
공식 코드GIT: A Generative Image-to-text Transformer for Vision and Language
Papers with Code 아카이브
Scene Text Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 15
- 보존된 평가 기록
- 190
See Scene Text Detection for leaderboards in this task.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/microsoft/unilm/tree/master/trocr
공식 코드TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
https://github.com/mkoshkina/jersey-number-pipeline
공식 코드A General Framework for Jersey Number Recognition in Sports Video
https://github.com/onealwj/mvlt
공식 코드Masked Vision-Language Transformers for Scene Text Recognition
https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/robust_scanner/README.md
공식 코드RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
https://github.com/openvinotoolkit/training_extensions
공식 코드Why You Should Try the Real Data for the Scene Text Recognition
https://github.com/pay20y/pimnet
공식 코드PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
https://github.com/qqqyd/visu
공식 코드Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
https://github.com/raysonlaroca/rodosol-alpr-dataset
공식 코드On the Cross-dataset Generalization in License Plate Recognition
https://github.com/roatienza/deep-text-recognition-benchmark
공식 코드Vision Transformer for Fast and Efficient Scene Text Recognition
https://github.com/roatienza/straug
공식 코드https://github.com/scut-dlvclab/gpt-4v_ocr
공식 코드Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation
https://github.com/shengtao96/centripetaltext
공식 코드CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
https://github.com/sijieliu518/sgenet
공식 코드Efficient scene text image super-resolution with semantic guidance
https://github.com/simplify23/CDistNet
공식 코드CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
https://github.com/simplify23/MRN
공식 코드MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition
https://github.com/simplify23/tps_pp
공식 코드TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition
https://github.com/thundervvv/rclstr
공식 코드https://github.com/thundervvv/rcmstr
공식 코드Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition
https://github.com/tongkunguan/ccd
공식 코드Self-supervised Character-to-Character Distillation for Text Recognition
https://github.com/tongkunguan/siga
공식 코드Self-supervised Implicit Glyph Attention for Text Recognition
https://github.com/topdu/openocr
공식 코드https://github.com/toyotainfotech/stisr-tcdm
공식 코드Scene Text Image Super-resolution based on Text-conditional Diffusion Models
https://github.com/vdigpku/str-it
공식 코드Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
https://github.com/vdigpku/str_tpsearch
공식 코드Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
https://github.com/wangyuxin87/VisionLAN
공식 코드From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
https://github.com/wenwenyu/MASTER-pytorch
공식 코드MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
https://github.com/wenwenyu/audioocr
공식 코드https://github.com/wp03052/MATRN
공식 코드Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
https://github.com/wzx99/clipocr
공식 코드Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition
https://github.com/xdxie/wordart
공식 코드Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
https://github.com/xfey/mctbench
공식 코드MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark
https://github.com/xieenze/TextSR
공식 코드TextSR: Content-Aware Text Super-Resolution Guided by Recognition
https://github.com/ya0-sun/str-berlin
공식 코드https://github.com/yueruchen/Pedestrian-Synthesis-GAN
공식 코드Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
https://github.com/zhang0jhon/AttentionOCR
공식 코드A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.