CUHK-PEDES

Introduced by Li et al. in Person Search with Natural Language Description

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

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Text based Person Retrieval	CUHK-PEDES	MARS
Text-based Person Retrieval with Noisy Correspondence	CUHK-PEDES	RDE
Pedestrian Image Caption	CUHK-PEDES	Hulk
Cross-Modal Retrieval	CUHK-PEDES	Dual Path