Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval.
Xuri GeFuhai ChenJoemon M. JoseZhilong JiZhongqin WuXiao LiuPublished in: ACM Multimedia (2021)
Keyphrases
- multi modal
- image features
- sentence retrieval
- uni modal
- image retrieval
- multi modality
- image representation
- image data
- audio visual
- image regions
- image collections
- high dimensional
- image content
- information retrieval
- multiple modalities
- image annotation
- image classification
- machine learning
- medical images
- video search
- low level
- structured data
- novelty detection
- feature extraction
- feature set
- metadata