Rank-1: 91.7mAP: 86.5
Papers with Code · CC BY-SA 4.0
Person Re-Identification
Person Re-Identification is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing 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.
논문
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
Rank-1: 91.2mAP: 86.7
Rank-1: 87.5mAP: 81.3
mAP: 17.2Rank-1: 41.4
Rank-1: 89.8mAP: 76.1Rank-5: 94.7Rank-10: 96.0
Rank-1: 88.2mAP: 80
Rank-1: 84.9mAP: 76.7
Rank-1: 86.2mAP: 74.1Rank-5: 90.5
Rank-1: 84.2mAP: 64
Rank-1: 94.13
Rank-1: 85.60mAP: 67.30
Rank-1: 87.3mAP: 71.8
Rank-1: 86.2mAP: 65.9
Rank-1: 83.8mAP: 67.6
Rank-1: 85.6mAP: 64.8
Rank-1: 86.0mAP: 68.0
Rank-1: 88.35mAP: 79.09
mAP: 15.8Rank-1: 29.9
Rank-1: 84.8mAP: 63.9
Rank-1: 89.5mAP: 75.0
mAP: 86.0Rank-1: 81.5
Rank-1: 86.20mAP: 69.40
mAP: 67.3
Rank-1: 86.6mAP: 68.8