Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification.
Zhiwei ZhaoBin LiuYan LuQi ChuNenghai YuPublished in: AAAI (2024)
Keyphrases
- multi modal
- person re identification
- semantic concepts
- multiple modalities
- uni modal
- image retrieval
- multiscale
- image classification
- semantic information
- image features
- image annotation
- input image
- image content
- low level
- image representation
- image collections
- image segmentation
- web images
- feature representation
- high resolution
- low level features
- natural images
- high dimensional
- feature space
- feature points