# Learning Feature Aggregation in Temporal Domain for Re-Identification

## TL;DR

This paper introduces a novel feature aggregation method in the temporal domain for person and vehicle re-identification, utilizing end-to-end training with a Siamese network, and presents a new large-scale vehicle re-identification dataset.

## Contribution

It proposes a new temporal feature aggregation technique trained end-to-end and introduces the CarsReId74k dataset for vehicle re-identification research.

## Key findings

- Our method outperforms existing feature aggregation techniques.
- The CarsReId74k dataset provides diverse vehicle observations from multiple angles.
- The approach improves re-identification accuracy on both person and vehicle datasets.

## Abstract

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.