Super Visual Semantic Embedding for Cross-Modal Image-Text Retrieval.
Zhixian ZengJianjun CaoGuoquan JiangNianfeng WengYuxin XuZibo NiePublished in: CSAE (2021)
Keyphrases
- cross modal
- text retrieval
- image retrieval
- multimedia retrieval
- visual similarity
- visual data
- image content
- perceptual information
- multi modal
- low level
- image data
- image features
- visual features
- document retrieval
- image annotation
- low level features
- image representation
- visual concepts
- multimedia information retrieval
- semantic similarity
- information retrieval
- image classification
- high level
- image database
- query expansion
- visual information
- image collections
- image search
- document collections
- retrieval systems
- content based retrieval
- relevance feedback
- image regions
- image set
- multimedia data
- semantic gap
- semantic information
- feature space
- video sequences
- similarity measure