Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval.
Zhenghao LiuChenyan XiongYuanhuiyi LvZhiyuan LiuGe YuPublished in: ICLR (2023)
Keyphrases
- multi modal
- cross modal
- video search
- image retrieval
- information retrieval systems
- auto annotation
- audio visual
- information retrieval
- retrieval systems
- image database
- relevance feedback
- active learning
- mutual information
- image annotation
- multi modality
- image processing
- visual recognition
- multimedia information retrieval