Multi-task hierarchical convolutional network for visual-semantic cross-modal retrieval.
Zhong JiZhigang LinHaoran WangYanwei PangXuelong LiPublished in: Pattern Recognit. (2024)
Keyphrases
- cross modal
- multi task
- multi modal
- visual similarity
- multimedia retrieval
- learning tasks
- multimedia databases
- image retrieval
- semantic concepts
- feature selection
- visual data
- multi class
- transfer learning
- semantic similarity
- visual information
- learning problems
- coarse to fine
- semantic information
- visual concepts
- information retrieval
- low level features
- visual content
- machine learning
- action recognition
- similarity measure