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/DVLP-CMATERJU/RectiNet
공식 코드A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping
https://github.com/GuoLusjtu/DVC
공식 코드https://github.com/InterDigitalInc/CompressAI
공식 코드CompressAI: a PyTorch library and evaluation platform for end-to-end compression research
https://github.com/JasonZHM/CAE-ADMM
공식 코드CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders
https://github.com/JasonZHM/CAEP
공식 코드CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders
https://github.com/JianpingLin/M-LVC_CVPR2020
공식 코드M-LVC: Multiple Frames Prediction for Learned Video Compression
https://github.com/JooyoungLeeETRI/CA_Entropy_Model
공식 코드Context-adaptive Entropy Model for End-to-end Optimized Image Compression
https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression
공식 코드End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression
https://github.com/Meixu-Chen/MOVI-Codec
공식 코드https://github.com/NormXU/Layout2Graph
공식 코드PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis
https://github.com/RenYang-home/HLVC
공식 코드Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement
https://github.com/RenYang-home/OpenDVC
공식 코드OpenDVC: An Open Source Implementation of the DVC Video Compression Method
https://github.com/RenYang-home/RLVC
공식 코드Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
https://github.com/Stillrot/RGINP
공식 코드https://github.com/YannickStruempler/LearnedJPEG
공식 코드Learning to Improve Image Compression without Changing the Standard Decoder
https://github.com/ZhengxueCheng/Learned-Image-Compression-with-GMM-and-Attention
공식 코드Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
https://github.com/ach-1914/ladlenet
공식 코드https://github.com/adlnlp/doc_gcn
공식 코드Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis
https://github.com/ailab-unifi/cte-dataset
공식 코드https://github.com/alibabaresearch/advancedliteratemachinery
공식 코드https://github.com/andreagemelli/doc2graph
공식 코드Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
https://github.com/anon-user-for-web/badlad
공식 코드BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset
https://github.com/anranwu-richpo/dcqa
공식 코드https://github.com/bidalab/paldb
공식 코드Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs
https://github.com/biswassanket/docsegtr
공식 코드DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer
https://github.com/biswassanket/synth_doc_generation
공식 코드DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis
https://github.com/bowenl0218/bpgan-signal-compression
공식 코드Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization
https://github.com/bowenl0218/mmvc_video_codec
공식 코드https://github.com/curto2/c
공식 코드High-Resolution Deep Convolutional Generative Adversarial Networks
https://github.com/cycloneboy/pdf_table
공식 코드PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction
https://github.com/dell-research-harvard/HJDataset
공식 코드A Large Dataset of Historical Japanese Documents with Complex Layouts
https://github.com/dhlab-epfl/dhSegment
공식 코드dhSegment: A generic deep-learning approach for document segmentation
https://github.com/dhlab-epfl/dhSegment-text
공식 코드Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers
https://github.com/dhlab-epfl/dhSegment-text-torch
공식 코드Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers
https://github.com/dleninja/adcnet
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.