3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting.
Xuri GeSongpei XuFuhai ChenJie WangGuoxin WangShan AnJoemon M. JosePublished in: CoRR (2024)
Keyphrases
- sentence retrieval
- image data
- low level
- image retrieval
- spatial relations
- image content
- image features
- image classification
- high level
- visual data
- visual features
- visual information
- image regions
- machine translation
- question answering
- video data
- retrieval systems
- information retrieval
- information retrieval systems
- feature space
- similarity measure
- feature selection