paper-with-me

ITCPR dataset

Image-Text Composed Person Retrieval dataset

홈페이지 · 논문 1편

The ITCPR dataset is a comprehensive collection specifically designed for the Zero-Shot Composed Person Retrieval (ZS-CPR) task. It consists of a total of 2,225 annotated triplets, derived from three distinct datasets: Celeb-reID, PRCC, and LAST.

ImagesTexts English

벤치마크

Zero-shot Composed Person Retrieval on ITCPR dataset 결과 6개