VPULab CityFlow-ReID Evaluation Framework
This Evaluation Framework allows researchs to keep on evaluating the performance of their approaches and the ones from the State-of-the-Art over the CitiFlow-ReID dataset. As this dataset has not public ground truth annotations, AI City Challenge provided an on-line evaluation server during the challenge, which is no more available.
Results
Results in Table show that the correlation between our evaluation framework and that of the official challenge.
The code is public available in VPULab-CityFlow-ReID-Evaluation-Framework.
Related Publication: Moral, P., García-Martín, Á., Martínez, J.M. et al. Enhancing vehicle re-identification via synthetic training datasets and re-ranking based on video-clips information. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-14511-0
Acknowledgement: This work is part of the preliminary tasks related to the Harvesting Visual Data (HVD) project (PID2021-125051OB-I00) funded by the Ministerio de Ciencia e Innovación of the Spanish Government.
Paula Moral
Video Processing and Understanding Lab PhD Researcher.
Álvaro García-Martín
Video Processing and Understanding Lab Staff.
José M. Martínez
Video Processing and Understanding Lab Staff.