Learning Text-image Joint Embedding for Efficient Cross-modal Retrieval with Deep Feature Engineering.
Zhongwei XieLing LiuYanzhao WuLuo ZhongLin LiPublished in: ACM Trans. Inf. Syst. (2022)
Keyphrases
- cross modal
- image retrieval
- feature engineering
- perceptual information
- learning algorithm
- visual recognition
- learning process
- image classification
- visual similarity
- multi modal
- image data
- image features
- multimedia retrieval
- image content
- information retrieval
- data sets
- multimedia databases
- visual data
- text retrieval
- high dimensional
- image annotation
- test collection
- text classification
- image database