Prototype-guided Cross-modal Completion and Alignment for Incomplete Text-based Person Re-identification

no code implementations • 29 Sep 2023 • Tiantian Gong, Guodong Du, Junsheng Wang, Yongkang Ding, Liyan Zhang

Therefore, we propose the cross-modal nearest neighbor construction strategy for missing data by computing the cross-modal similarity between existing images and texts, which provides key guidance for the completion of missing modal features.

Person Re-Identification