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.
Papers
Showing 101–110 of 1488 papers
All datasetsMarket-1501DukeMTMC-reIDMSMT17Occluded-DukeMTMCMarket-1501-CCUHK03 detectedCUHK03 labeledMARSCUHK03LTCCPRCCPRID2011
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | st-ReID(RE, RK) | Rank-1 | 98 | — | Unverified |
| 2 | SSKD(GH) | Rank-1 | 97.36 | — | Unverified |
| 3 | CLIP-ReID+Pose2ID (no RK) | Rank-1 | 97.3 | — | Unverified |
| 4 | SOLIDER +UFFM+AMC | Rank-1 | 97 | — | Unverified |
| 5 | Unsupervised Pre-training (ResNet101+MGN) | Rank-1 | 97 | — | Unverified |
| 6 | RGT&RGPR (RK) | Rank-1 | 96.9 | — | Unverified |
| 7 | SOLIDER | Rank-1 | 96.9 | — | Unverified |
| 8 | LightMBN (RR) | Rank-1 | 96.8 | — | Unverified |
| 9 | Viewpoint-Aware Loss(RK) | Rank-1 | 96.79 | — | Unverified |
| 10 | SOLIDER (RK) | Rank-1 | 96.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DenseIL | mAP | 97.1 | — | Unverified |
| 2 | CTL Model (ResNet50, 256x128) | mAP | 96.1 | — | Unverified |
| 3 | BPBreID (RK) | mAP | 92.9 | — | Unverified |
| 4 | Unsupervised Pre-training (ResNet101+RK) | mAP | 92.77 | — | Unverified |
| 5 | RGT&RGPR (RK) | mAP | 92.7 | — | Unverified |
| 6 | st-ReID(RE, RK,Cam) | mAP | 92.7 | — | Unverified |
| 7 | Viewpoint-Aware Loss(RK) | mAP | 91.8 | — | Unverified |
| 8 | LDS (ResNet50 + RK) | mAP | 91 | — | Unverified |
| 9 | Adaptive L2 Regularization (with re-ranking) | mAP | 90.7 | — | Unverified |
| 10 | FlipReID (with re-ranking) | mAP | 90.7 | — | Unverified |