Deep Similarity Preserving and Attention-based Hashing for Cross-Modal Retrieval.
Shubai ChenSong WuYu ChenYuan YuanPublished in: SEKE (2021)
Keyphrases
- cross modal
- visual similarity
- multi modal
- multimedia retrieval
- image retrieval
- multimedia databases
- similarity measure
- semantic similarity
- visual recognition
- visual features
- data structure
- visual data
- visual content
- perceptual information
- web images
- dissimilarity measure
- image annotation
- visual information
- automatic image annotation
- similarity search
- contextual information
- wordnet
- video sequences
- keywords