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.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
데이터셋
68개논문
mAP: 17.2Rank-1: 41.4
Rank-1: 84.9mAP: 76.7
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
Rank-1: 91.2mAP: 86.7
Rank-1: 94.13
Rank-1: 87.5mAP: 81.3
Rank-1: 88.35mAP: 79.09
mAP: 15.8Rank-1: 29.9
Rank-1: 88.2mAP: 80
mAP: 86.0Rank-1: 81.5
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.
하위 태스크
UP
Unsupervised Person Re-Identification
GP
Generalizable Person Re-identification
SP
Self-Supervised Person Re-Identification
CP
Cross-Modal Person Re-Identification
CP
Cloth-Changing Person Re-Identification
CC
Clothes Changing Person Re-Identification
DT
Direct Transfer Person Re-identification
FL
Federated Lifelong Person ReID
IP
Image-To-Video Person Re-Identification
LP
Large-Scale Person Re-Identification
OP
Occluded Person Re-Identification
SP
Semi-Supervised Person Re-Identification