victorjoos's picture
Add metadata
8b062e9 verified
metadata
thumbnail: >-
  https://github.com/VlSomers/keypoint_promptable_reidentification/blob/main/assets/keypoint_promptable_reid.jpg
tags:
  - reid

KPR: Keypoint Promptable Re-Identification

[Paper] [GitHub] [Demo] [Video] [Poster] [BPBreID] [TrackLab]

arXiv Hippocratic License HL3-LAW-MEDIA-MIL-SOC-SV

๐Ÿ”ฅ SOTA ReID model, with optional keypoint prompts, that is robust to multi-person occlusions ๐Ÿ”ฅ

โœ… Plug-and-play with any pose estimator or through manual keypoint selection

๐Ÿš€ Release of the Occluded-PoseTrack-ReID dataset with manual keypoint annotations + keypoints annotations for four existing ReID benchmarks

KPR can be easily integrated into any codebase to perform person retrieval, person search, multi-person (pose) tracking, multi-view multi-skeleton matching for 3D pose, ...

SOTA performance with the SOLIDER human-centric foundation model as backbone.

Keypoint Promptable Re-Identification, ECCV24

Vladimir Somers, Alexandre Alahi, Christophe De Vleeschouwer

arxiv 2407.18112