MS2GAH: Multi-label semantic supervised graph attention hashing for robust cross-modal retrieval.
Youxiang DuanNing ChenPeiying ZhangNeeraj KumarLunjie ChangWu WenPublished in: Pattern Recognit. (2022)
Keyphrases
- cross modal
- multi label
- visual similarity
- multi modal
- image annotation
- automatic image annotation
- multimedia retrieval
- semantic concepts
- multi label classification
- text categorization
- image classification
- image retrieval
- graph cuts
- multimedia databases
- class labels
- binary classification
- visual concepts
- semantic similarity
- supervised learning
- learning tasks
- text classification
- learning algorithm
- retrieval systems
- image data
- feature selection
- information retrieval
- semi supervised
- high level
- machine learning
- semantic gap
- structured data
- low level
- natural language