Unsupervised Long Term Person Re-Identification
1 papers with code • 0 benchmarks • 0 datasets
Long-term Person Re-Identification(Clothes-Changing Person Re-ID) is a computer vision task in which the goal is to match a person's identity across different cameras, clothes, and locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, and body shape to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.
Benchmarks
These leaderboards are used to track progress in Unsupervised Long Term Person Re-Identification
Most implemented papers
SiCL: Silhouette-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes Change
In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change.