AI RESEARCH
DAPL: Integration of Positive and Negative Descriptions in Text-Based Person Search
arXiv CS.CV
•
ArXi:2405.07459v3 Announce Type: replace Text-based person search (TBPS) aims to retrieve specific images of individuals from large datasets using textual descriptions. Existing TBPS methods focus primarily on identifying explicit positive attributes, often neglecting the critical role of negative descriptions. This oversight can lead to false positives, where images that should be excluded based on negative descriptions are incorrectly included, due to partial alignment with the positive criteria.