If you notice any result or the public code that has not been included in this table, please connect [email protected] without hesitation to add the method. You are welcomed.
| Methods | Rank@1 | Rank@5 | Map | Year | Reference |
|---|---|---|---|---|---|
| QD-DLF | 88.50% | 94.46% | 61.83% | TITS2019 | "Vehicle Re-Identification Using Quadruple Directional Deep Learning Features", Zhu, J., Zeng, H., Huang, J., Liao, S., Lei, Z., Cai, C., & Zheng, L pdf |
| Hard-View-EALN | 84.39% | 94.05% | 57.44% | TIP2019 | "Embedding Adversarial Learning for Vehicle Re-Identification." Lou, Yihang, et al paper |
| RAM | 88.6% | 94.0% | 61.5% | ICME2018 | "Ram: a region-aware deep model for vehicle re-identification." Liu, Xiaobin, et al paper |
| Appearance + ABLN-Ft-16 Color + Model + Re-Ranking | 89.27% | 94.76% | 61.11% | ICIP2018 | "Multi-Attribute Driven Vehicle Re-Identification with Spatial-Temporal Re-Ranking." Jiang, Na, et al paper |
| GS-TRE loss W/ mean VGGM | 96.24% | 98.97% | 59.47% | TMM2018 | "Group-sensitive triplet embedding for vehicle reidentification." Bai, Yan, et al paper |
| GAN+LSRO | 87.70% | 93.92% | 58.23% | ICPR2018 | "Joint Semi-supervised Learning and Re-ranking for Vehicle Re-identification." Wu, Fangyu, et al paper |
| GAN+LSRO+reranking | 88.62% | 94.52% | 64.78% | ICPR2018 | "Joint Semi-supervised Learning and Re-ranking for Vehicle Re-identification." Wu, Fangyu, et al paper |
| JFSDL | 82.90% | 91.60% | 53.53% | IEEE Access2018 | "Joint feature and similarity deep learning for vehicle re-identification." Zhu, Jianqing, et al paper |
| SDC-CNN | 83.49% | 92.55% | 53.45% | ICPR2018 | "A shortly and densely connected convolutional neural network for vehicle re-identification." Zhu, Jianqing, et al paper |
| NuFACT | 76.76% | 91.42% | 48.47% | TMM2018 | "PROVID: Progressive and multimodal vehicle reidentification for large-scale urban surveillance." Liu, X., Liu, W., Mei, T., & Ma, H paper |
| PROVID | 81.56% | 95.11% | 53.42% | TMM2018 | "PROVID: Progressive and multimodal vehicle reidentification for large-scale urban surveillance." Liu, X., Liu, W., Mei, T., & Ma, H paper |
| VAMI+STR | 85.92% | 91.84% | 61.32% | CVPR2018 | "Viewpoint-aware attentive multi-view inference for vehicle re-identification", Y Zhou, L Shao, A Dhabi paper |
| VAMI | 77.03% | 90.82% | 50.13% | CVPR2018 | "Viewpoint-aware attentive multi-view inference for vehicle re-identification", Y Zhou, L Shao, A Dhabi paper |
| SCCN-Ft+CLBL-8-Ft | 60.83% | 78.55% | 25.12% | TIP2018 | "Vehicle re-identification by deep hidden multi-view inference." Zhou, Yi, Li Liu, and Ling Shao paper |
| ABLN-Ft-16 | 60.49% | 77.33% | 24.92% | WACV2018 | "Vehicle re-identification by adversarial bi-directional LSTM network." Zhou, Yi, and Ling Shao paper |
| Siamese-CNN+Path-LSTM | 83.49% | 90.04% | 58.27% | ICCV2017 | "Learning deep neural networks for vehicle re-id with visual-spatio-temporal path proposals." Shen, Y., Xiao, T., Li, H., Yi, S., & Wang, X pdf |
| OIFE | 65.92% | 87.66% | 48.00% | ICCV 2017 | "Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification." Wang, Zhongdao, et al paper |
| OIFE+ST | 68.3% | 89.7% | 51.42% | ICCV 2017 | "Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification." Wang, Zhongdao, et al paper |
| Combining Network | 60.19% | 77.40% | 33.78% | ICIP2017 | "Multi-modal metric learning for vehicle re-identification in traffic surveillance environment." Tang, Yi, et al paper |
| XVGAN | 60.20% | 77.03% | 24.65% | BMVC2017 | "Cross-view gan based vehicle generation for re-identification." Zhou, Y., and L. Shao |
| FACT + Plate-SNN + STR | 61.44% | 78.78% | 27.77% | ECCV2016 | "A deep learning-based approach to progressive vehicle re-identification for urban surveillance." Liu, Xinchen, et al paper |
| FACT | 59.65% | 75.27% | 19.92% | ICME2016 | "Large-scale vehicle re-identification in urban surveillance videos." Liu, Xinchen, et al paper |
| VGG-CNN-M-1024 | 44.10% | 62.63% | 12.76% | CVPR2016 | "Deep relative distance learning: Tell the difference between similar vehicles." Liu, Hongye, et al paper |
| BOW-CN | 33.91% | 53.69% | 12.20% | ICCV2015 | "Scalable person re-identification: A benchmark." Zheng, Liang, et al paper |
| LOMO | 25.33% | 46.48% | 9.64% | CVPR2015 | "Person re-identification by local maximal occurrence representation and metric learning."Liao, Shengcai, et al paper |
| BOW-SFIT | 1.91% | 4.53% | 1.51% | CVPR2014 | "Bayes merging of multiple vocabularies for scalable image retrieval" Zheng, Liang, et al paper |
| % | % | % |