Unifying Vision, Text, and Layout for Universal Document Processing.
Zineng TangZiyi YangGuoxin WangYuwei FangYang LiuChenguang ZhuMichael ZengCha ZhangMohit BansalPublished in: CVPR (2023)
Keyphrases
- document processing
- digital libraries
- document images
- information retrieval
- document analysis
- information extraction
- text processing
- multimedia documents
- computer vision
- textual documents
- vision system
- document clustering
- data model
- text mining
- information retrieval systems
- data mining
- image segmentation
- keywords
- metadata
- text collections