Occluded Person Re-Identification (ReID) is a metric learning task that involves matching occluded individuals based on their appearance. While many studies have tackled occlusions caused by objects, multi-person occlusions remain less explored. In this work, we identify and address a critical challenge overlooked by previous occluded ReID methods: the Multi-Person Ambiguity (MPA) arising when multiple individuals are visible in the same bounding box, making it impossible to determine the intended ReID target among the candidates. Inspired by recent work on prompting in vision, we introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints indicating the intended target. Since promptable re-identification is an unexplored paradigm, existing ReID datasets lack the pixel-level annotations necessary for prompting. To bridge this gap and foster further research on this topic, we introduce Occluded-PoseTrack ReID, a novel ReID dataset with keypoints labels, that features strong inter-person occlusions. Furthermore, we release custom keypoint labels for four popular ReID benchmarks. Experiments on person retrieval, but also on pose tracking, demonstrate that our method systematically surpasses previous state-of-the-art approaches on various occluded scenarios. Our code, dataset and annotations are available at https://github.com/VlSomers/keypoint_promptable_reidentification.

翻译：遮挡行人重识别是一项基于外观匹配遮挡个体的度量学习任务。尽管已有大量研究致力于解决物体遮挡问题，但多人遮挡场景仍较少被探索。本文发现并解决了先前遮挡重识别方法忽视的关键挑战：当多个个体同时出现在同一检测框内时产生的多人歧义问题，该问题导致无法在候选目标中确定待识别的特定个体。受近期视觉提示研究的启发，我们提出关键点可提示重识别——一种新颖的重识别问题范式，通过语义关键点集合显式补充输入检测框以指示目标个体。由于可提示重识别是尚未探索的新范式，现有重识别数据集缺乏提示所需的像素级标注。为填补这一空白并推动该方向研究，我们构建了Occluded-PoseTrack ReID数据集，这是一个包含关键点标注且具有显著人际遮挡特性的新型重识别数据集。此外，我们为四个主流重识别基准数据集发布了定制关键点标注。在行人检索与姿态跟踪任务上的实验表明，我们的方法在各种遮挡场景下均系统性地超越了现有最优方法。代码、数据集及标注已开源：https://github.com/VlSomers/keypoint_promptable_reidentification。