Unlock Multi-Modal Capability of Dense Retrieval via Visual Module Plugin.
Tianshuo ZhouSen MeiXinze LiZhenghao LiuChenyan XiongZhiyuan LiuYu GuGe YuPublished in: CoRR (2023)
Keyphrases
- multi modal
- cross modal
- video search
- single modality
- multi modality
- auto annotation
- information retrieval
- audio visual
- visual information
- high dimensional
- multiple modalities
- image database
- image annotation
- image processing
- humanoid robot
- semantic concepts
- visual similarity
- information retrieval systems
- image retrieval
- multimedia databases
- visual features
- x ray
- object recognition