ICFG-PEDES
Identity-Centric and Fine-Grained Person Description Dataset
ImagesTextsplease email to chxding@scut.edu.cn to obtain the databaseIntroduced 2021-07-01
One large-scale database for Text-to-Image Person Re-identification, i.e., Text-based Person Retrieval.
Compared with existing databases, ICFG-PEDES has three key advantages. First, its textual descriptions are identity-centric and fine-grained. Second, the images included in ICFG-PEDES are more challenging, containing more appearance variability due to the presence of complex backgrounds and variable illumination. Third, the scale of ICFG-PEDES is larger.
Benchmarks
Image Retrieval/rank-1Text based Person Retrieval/R@1Text based Person Retrieval/Rank-1Text based Person Retrieval/R@5Text based Person Retrieval/R@10Text based Person Retrieval/mAPText based Person Retrieval/mINPText based Person Retrieval/Rank-10Text based Person Retrieval/Rank-5Text-based Person Retrieval with Noisy Correspondence/Rank 1Text-based Person Retrieval with Noisy Correspondence/Rank-10Text-based Person Retrieval with Noisy Correspondence/Rank-5Text-based Person Retrieval with Noisy Correspondence/mAPText-based Person Retrieval with Noisy Correspondence/mINP