Multi-Modal Transformer With Global-Local Alignment for Composed Query Image Retrieval.
Yahui XuYi BinJiwei WeiYang YangGuoqing WangHeng Tao ShenPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- multi modal
- relevance feedback
- image retrieval
- video search
- retrieval accuracy
- retrieval method
- retrieval precision
- cross modal
- image annotation
- query expansion
- query processing
- multi modality
- retrieved images
- image database
- audio visual
- high dimensional
- keywords
- semantic concepts
- image representation
- image search
- data sources
- fusing multiple
- sequence databases
- web images
- content based retrieval
- low level features