PRW

Person Re-identification in the Wild

Dataset Information
Modalities
Videos
Introduced
2016
License
Unknown
Homepage
Official Website
Contents

Overview

PRW is a large-scale dataset for end-to-end pedestrian detection and person recognition in raw video frames. PRW is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized cameras. It contains 932 identities and 11,816 frames in which pedestrians are annotated with their bounding box positions and identities.

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Person Search SPNet Swap Path Network for Robust … 2024-12-06
Person Search SOLIDER Beyond Appearance: a Semantic Controllable … 2023-03-30
Person Search SeqNeXt Gallery Filter Network for Person … 2022-10-24
Person Search GLCNet MovieNet-PS: A Large-Scale Person Search … 2021-12-05
Person Search GLCNet+CBGM MovieNet-PS: A Large-Scale Person Search … 2021-12-05
Person Search ROI-AlignPS Efficient Person Search: An Anchor-Free … 2021-09-01
Person Search AlignPS Anchor-Free Person Search 2021-03-22
Person Search AlignPS+ Anchor-Free Person Search 2021-03-22
Person Search OIM+SeqNet Sequential End-to-end Network for Efficient … 2021-03-18
Person Search NAE+SeqNet+CBGM Sequential End-to-end Network for Efficient … 2021-03-18
Person Search NAE+SeqNet Sequential End-to-end Network for Efficient … 2021-03-18
Person Search OIM+SeqNet+CBGM Sequential End-to-end Network for Efficient … 2021-03-18
Person Search DMRNet Decoupled and Memory-Reinforced Networks: Towards … 2021-02-22

Research Papers

Recent papers with results on this dataset:

External Links: