M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis.
Ning ZhangHiuyi ChengJiayu ChenZongyuan JiangJun HuangYang XueLianwen JinPublished in: AAAI (2024)
Keyphrases
- multi modal fusion
- document collections
- database
- retrieval systems
- document classification
- text documents
- document images
- web documents
- document clustering
- information retrieval systems
- multi class
- information extraction
- document retrieval
- facial features
- keywords
- structured documents
- multimedia documents
- image sequences