Deep robust multilevel semantic hashing for multi-label cross-modal retrieval.
Ge SongXiaoyang TanJun ZhaoMing YangPublished in: Pattern Recognit. (2021)
Keyphrases
- cross modal
- multi label
- visual similarity
- multi modal
- image annotation
- text categorization
- multi label classification
- multimedia retrieval
- automatic image annotation
- semantic concepts
- image retrieval
- graph cuts
- multimedia databases
- image classification
- semantic similarity
- text classification
- learning tasks
- binary classification
- visual concepts
- class labels
- natural language
- semantic information
- machine learning
- image segmentation
- semantic gap
- retrieval systems
- visual data
- visual content
- image content
- visual features
- markov random field
- relevance feedback
- semi supervised
- multimedia
- information retrieval