Word for Person: Zero-shot Composed Person Retrieval

The Zero-shot Composed Person Retrieval (ZS-CPR) is introduced, which leverages existing domain-related data to resolve the CPR problem without reliance on expensive annotations, and a two-stage learning framework, Word4Per, where a lightweight Textual Inversion Network (TINet) and a text-based person retrieval model based on fine-tuned Contrastive Language-Image Pre-training (CLIP) network are learned without utilizing any CPR data.