1 code implementation • CVPR 2023 • Ding Jiang, Mang Ye
To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision.
Ranked #3 on
Text based Person Retrieval
on RSTPReid
(using extra training data)
1 code implementation • CVPR 2023 • Cuiqun Chen, Mang Ye, Ding Jiang
Person re-identification (ReID) with descriptive query (text or sketch) provides an important supplement for general image-image paradigms, which is usually studied in a single cross-modality matching manner, e. g., text-to-image or sketch-to-photo.