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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Vector Quantized Semantic Communication System
Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis
Evaluating the Quality and Diversity of DCGAN-based Generatively Synthesized Diabetic Retinopathy Imagery
Scalable Video Coding for Humans and Machines
Evaluating the Practicality of Learned Image Compression
Universal Learned Image Compression With Low Computational Cost
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
PO-ELIC: Perception-Oriented Efficient Learned Image Coding
Q-LIC: Quantizing Learned Image Compression with Channel Splitting
Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission
Learning to Remove Clutter in Real-World GPR Images Using Hybrid Data
Unified Pretraining Framework for Document Understanding
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Neural Graph Matching for Modification Similarity Applied to Electronic Document Comparison
Towards End-to-End Unified Scene Text Detection and Layout Analysis
DiT: Self-supervised Pre-training for Document Image Transformer
Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
Improved Wavelets for Image Compression from Unitary Circuits
DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts
ADC-Net: An Open-Source Deep Learning Network for Automated Dispersion Compensation in Optical Coherence Tomography
DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer
Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder
Cross-Domain Document Layout Analysis Using Document Style Guide
Signal Reconstruction from Quantized Noisy Samples of the Discrete Fourier Transform
Learning True Rate-Distortion-Optimization for End-To-End Image Compression
DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression
A New Image Codec Paradigm for Human and Machine Uses
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression
Data Augmentation For Medical MR Image Using Generative Adversarial Networks
Learning-Based Video Coding with Joint Deep Compression and Enhancement
Document Layout Analysis with Aesthetic-Guided Image Augmentation
Temporal Context Mining for Learned Video Compression
DeepWiVe: Deep-Learning-Aided Wireless Video Transmission
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.