Learning Hierarchical Semantic Correspondences for Cross-Modal Image-Text Retrieval.
Sheng ZengChanghong LiuJun ZhouYong ChenAiwen JiangHanxi LiPublished in: ICMR (2022)
Keyphrases
- text retrieval
- image retrieval
- cross modal
- perceptual information
- image features
- image classification
- multimedia retrieval
- visual recognition
- image data
- image content
- information retrieval
- image regions
- semantic gap
- document retrieval
- image representation
- feature extraction
- learning algorithm
- query expansion
- multimedia databases
- feature vectors
- similarity measure
- multimedia information retrieval
- visual similarity
- multimedia