Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval.
Dixuan LinYi-Xing PengJingke MengWei-Shi ZhengPublished in: CoRR (2023)
Keyphrases
- cross modal
- image retrieval
- visual similarity
- multi modal
- image features
- image content
- multiscale
- image data
- multimedia retrieval
- web images
- text retrieval
- visual data
- image database
- image classification
- perceptual information
- information retrieval
- image representation
- low level
- visual recognition
- keywords
- object recognition
- relevance feedback
- text mining
- image collections
- image annotation
- information retrieval systems
- text documents
- image set
- content based retrieval
- graph cuts
- document retrieval
- visual concepts
- query processing
- semantic information
- visual features