Uncertainty-aware coarse-to-fine alignment for text-image person retrieval
Abstract Text-to-image person retrieval, a fine-grained cross-modal retrieval problem, aims to search for person images from an image library that match a given textual caption. Existing text-to-image person retrieval methods usually use fixed-point embedding to express the semantics of the two moda...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-04-01
|
| Series: | Visual Intelligence |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44267-025-00078-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|