Asymmetric cross-modal hashing with high-level semantic similarity.
Fan YangYufeng LiuXiaojian DingFumin MaJie CaoPublished in: Pattern Recognit. (2022)
Keyphrases
- cross modal
- semantic similarity
- visual similarity
- high level
- semantic information
- semantic concepts
- low level
- multi modal
- co occurrence
- similarity measure
- wordnet
- low level features
- visual features
- multimedia retrieval
- semantic representations
- image retrieval
- automatic image annotation
- visual recognition
- visual data
- visual information
- video sequences
- multimedia
- similarity search
- contextual information
- higher level
- natural language processing
- multimedia data
- background knowledge
- image search
- visual content
- keywords
- text classification