DualFocus: A Unified Framework for Integrating Positive and Negative Descriptors in Text-based Person Retrieval

arXiv:2405.07459v1 Announce Type: new
Abstract: Text-based person retrieval (TPR) aims to retrieve images of a person from an extensive array of candidates based on a given textual description. The core challenge lies in mapping visual and textual data into a unified latent space. While existing TPR methods concentrate on recognizing explicit and positive characteristics, they often neglect the critical influence of negative descriptors, resulting in potential false positives that fulfill positive criteria but could be excluded by negative descriptors. To …

abstract array arxiv challenge core cs.cv data framework images lies mapping negative person positive retrieval space text textual type visual while