Papers with Code 아카이브
Document Layout Analysis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 6
- 보존된 평가 기록
- 30
"Document Layout Analysis is performed to determine physical structure of a document, that is, to determine document components. These document components can consist of single connected components-regions [...] of pixels that are adjacent to form single regions [...] , or group of text lines. A text line is a group of characters, symbols, and words that are adjacent, “relatively close” to each other and through which a straight line can be drawn (usually with horizontal or vertical orientation)." L. O'Gorman, "The document spectrum for page layout analysis," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1162-1173, Nov. 1993.
Image credit: PubLayNet: largest dataset ever for document layout analysis
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ds-kiel/mcucoder
공식 코드MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices
https://github.com/dsaragih/diffuse-gen
공식 코드Using Diffusion Models to Generate Synthetic Labelled Data for Medical Image Segmentation
https://github.com/dsevero/linear-autoregressive-similarity-index
공식 코드The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
https://github.com/fab-jul/imgcomp-cvpr
공식 코드https://github.com/facebookresearch/deit
공식 코드Training data-efficient image transformers & distillation through attention
https://github.com/fengyurenpingsheng/Learned-image-compression-with-GLLMM
공식 코드https://github.com/finger-monkey/ReID_Adversarial_Defense
공식 코드A Person Re-identification Data Augmentation Method with Adversarial Defense Effect
https://github.com/google-research-datasets/hiertext
공식 코드Towards End-to-End Unified Scene Text Detection and Layout Analysis
https://github.com/guanlongzhao/single-image-dehazing
공식 코드https://github.com/hikopensource/davar-lab-ocr
공식 코드VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
https://github.com/hitachi-nlp/appjsonify
공식 코드appjsonify: An Academic Paper PDF-to-JSON Conversion Toolkit
https://github.com/hjkimk/text-role-classification
공식 코드Text Role Classification in Scientific Charts Using Multimodal Transformers
https://github.com/ibm-aur-nlp/PubLayNet
공식 코드PubLayNet: largest dataset ever for document layout analysis
https://github.com/icdar21-mapseg/icdar21-mapseg-eval
공식 코드https://github.com/ideal-iqa/iqa-eval
공식 코드A study on the adequacy of common IQA measures for medical images
https://github.com/imsb-uke/bias-transfer-microscopy
공식 코드Deep learning-based bias transfer for overcoming laboratory differences of microscopic images
https://github.com/jianhuapei/ldm-enabled-semcom-system
공식 코드https://github.com/juglab/microssim
공식 코드MicroSSIM: Improved Structural Similarity for Comparing Microscopy Data
https://github.com/liuzhening111/bisic
공식 코드Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model
https://github.com/lquirosd/P2PaLA
공식 코드https://github.com/maitysubhajit/selfdocseg
공식 코드SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
https://github.com/makbari7/DSSLIC
공식 코드DSSLIC: Deep Semantic Segmentation-based Layered Image Compression
https://github.com/mdv3101/CDeCNet
공식 코드CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images
https://github.com/microsoft/comphrdoc
공식 코드https://github.com/microsoft/unilm
공식 코드LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/microsoft/unilm/tree/master/beit
공식 코드https://github.com/microsoft/unilm/tree/master/dit
공식 코드DiT: Self-supervised Pre-training for Document Image Transformer
https://github.com/microsoft/unilm/tree/master/layoutlmv3
공식 코드LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
https://github.com/moha23/LF-DAAE
공식 코드Learning-Based Practical Light Field Image Compression Using A Disparity-Aware Model
https://github.com/monniert/docExtractor
공식 코드docExtractor: An off-the-shelf historical document element extraction
https://github.com/njuvision/nic
공식 코드Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling
https://github.com/opendatalab/DocLayout-YOLO
공식 코드https://github.com/paddlepaddle/paddlex
공식 코드PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction
https://github.com/pd162/roi-matching
공식 코드Class-Agnostic Region-of-Interest Matching in Document Images
https://github.com/raphaelBarman/dhSegment
공식 코드Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.