Top-push Video-based Person Re-identification

TL;DR

This paper introduces a top-push distance learning model for video-based person re-identification, leveraging space-time cues to improve discriminative feature matching and outperform existing methods.

Contribution

The paper proposes a novel top-push distance learning approach that enhances video-based person re-id by focusing on top-rank matching optimization.

Findings

Outperforms state-of-the-art video re-id methods

Effectively distinguishes persons with similar appearances and motions

Utilizes space-time information for robust re-identification

Abstract

Most existing person re-identification (re-id) models focus on matching still person images across disjoint camera views. Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the occlusion, pose and camera-view change, and lighting variation problems. In comparison, video-based re-id methods can utilize extra space-time information, which contains much more rich cues for matching to overcome the mentioned problems. However, we find that when using video-based representation, some inter-class difference can be much more obscure than the one when using still-image based representation, because different people could not only have similar appearance but also have similar motions and actions which are hard to align. To solve this problem, we propose a top-push distance learning model (TDL), in which we integrate a top-push constrain for matching video features of persons. The top-push constraint enforces the optimization on top-rank matching in re-id, so as to make the matching model more effective towards selecting more discriminative features to distinguish different persons. Our experiments show that the proposed video-based re-id framework outperforms the state-of-the-art video-based re-id methods.