TL;DR
This paper introduces Keypoint Promptable ReID (KPR), a new approach for occluded person re-identification that uses semantic keypoints to resolve multi-person ambiguity, supported by a new dataset and annotations, outperforming previous methods.
Contribution
The paper proposes a novel prompt-based ReID formulation using keypoints and introduces a new dataset with keypoint annotations for occluded scenarios.
Findings
KPR outperforms previous state-of-the-art methods on occluded ReID tasks.
The new dataset enables effective training and evaluation of keypoint-based ReID methods.
Using keypoints reduces multi-person ambiguity in occluded ReID scenarios.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsSparse Evolutionary Training
