CUHK-PEDES
ImagesTextsUnknownIntroduced 2017-02-19
The CUHK-PEDES dataset is a caption-annotated pedestrian dataset. It contains 40,206 images over 13,003 persons. Images are collected from five existing person re-identification datasets, CUHK03, Market-1501, SSM, VIPER, and CUHK01 while each image is annotated with 2 text descriptions by crowd-sourcing workers. Sentences incorporate rich details about person appearances, actions, poses.
Source: MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination Image Source: https://www.researchgate.net/figure/Image-samples-in-three-datasets-For-MSCOCO-and-Flickr30k-dataset-we-view-every-image_fig2_321095980
Benchmarks
Cross-Modal Information Retrieval/Text-to-image MedrCross-Modal Retrieval/Text-to-image MedrImage Retrieval with Multi-Modal Query/Text-to-image MedrText based Person Retrieval/R@1Text based Person Retrieval/R@5Text based Person Retrieval/R@10Text based Person Retrieval/mAPText based Person Retrieval/Rank-1Text 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