Temporal Knowledge Propagation for Image-to-Video Person Re-identification

TL;DR

This paper introduces Temporal Knowledge Propagation (TKP), a novel method that transfers temporal information from videos to still images to improve image-to-video person re-identification, significantly outperforming existing methods.

Contribution

The paper proposes a new TKP approach that propagates temporal knowledge from videos to images, addressing information asymmetry in image-to-video Re-ID tasks.

Findings

Outperforms state-of-the-art on two datasets

Effectively transfers temporal knowledge to improve image features

Enhances discriminative power of features for Re-ID

Abstract

In many scenarios of Person Re-identification (Re-ID), the gallery set consists of lots of surveillance videos and the query is just an image, thus Re-ID has to be conducted between image and videos. Compared with videos, still person images lack temporal information. Besides, the information asymmetry between image and video features increases the difficulty in matching images and videos. To solve this problem, we propose a novel Temporal Knowledge Propagation (TKP) method which propagates the temporal knowledge learned by the video representation network to the image representation network. Specifically, given the input videos, we enforce the image representation network to fit the outputs of video representation network in a shared feature space. With back propagation, temporal knowledge can be transferred to enhance the image features and the information asymmetry problem can be alleviated. With additional classification and integrated triplet losses, our model can learn expressive and discriminative image and video features for image-to-video re-identification. Extensive experiments demonstrate the effectiveness of our method and the overall results on two widely used datasets surpass the state-of-the-art methods by a large margin. Code is available at: https://github.com/guxinqian/TKP