Learning Feature Aggregation in Temporal Domain for Re-Identification
It addresses the problem of improving re-identification accuracy for computer vision applications, but is incremental as it builds on existing feature aggregation techniques.
The paper tackles feature aggregation in temporal domain for person and vehicle re-identification by proposing a method that weights feature vectors and trains end-to-end with a Siamese network, resulting in outperforming existing methods on both tasks and introducing a new dataset CarsReId74k with 17,681 unique vehicles and 277,236 positive pairs.
Person re-identification is a standard and established problem in the computer vision community. In recent years, vehicle re-identification is also getting more attention. In this paper, we focus on both these tasks and propose a method for aggregation of features in temporal domain as it is common to have multiple observations of the same object. The aggregation is based on weighting different elements of the feature vectors by different weights and it is trained in an end-to-end manner by a Siamese network. The experimental results show that our method outperforms other existing methods for feature aggregation in temporal domain on both vehicle and person re-identification tasks. Furthermore, to push research in vehicle re-identification further, we introduce a novel dataset CarsReId74k. The dataset is not limited to frontal/rear viewpoints. It contains 17,681 unique vehicles, 73,976 observed tracks, and 277,236 positive pairs. The dataset was captured by 66 cameras from various angles.