MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter.
Zhiyuan LiuSihang LiYanchen LuoHao FeiYixin CaoKenji KawaguchiXiang WangTat-Seng ChuaPublished in: CoRR (2023)
Keyphrases
- language modeling
- cross modal
- multi modal
- uni modal
- language model
- retrieval model
- information retrieval
- query expansion
- probabilistic model
- n gram
- text classification
- document retrieval
- multimedia retrieval
- information retrieval systems
- high dimensional
- image classification
- visual data
- relevance model
- image retrieval