A Unified Visual Prompt Tuning Framework with Mixture-of-Experts for Multimodal Information Extraction.
Bo XuShizhou HuangMing DuHongya WangHui SongYanghua XiaoXin LinPublished in: DASFAA (3) (2023)
Keyphrases
- information extraction
- main contribution
- multi modal
- bayesian framework
- web mining
- low level
- visual representation
- database
- precision and recall
- semi structured
- visual information
- gaussian mixture model
- theoretical framework
- mixture model
- text mining
- probabilistic model
- database systems
- multimedia
- data mining
- neural network
- data sets