University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Cross-domain adversarial feature learning for sketch re-identification

Pang, L., Wang, Y., Song, Yi-Zhe, Huang, T. and Tian, Y. (2018) Cross-domain adversarial feature learning for sketch re-identification In: 26th ACM international conference on Multimedia (MM 18), 22-26 Oct 2018, Seoul, Republic of Korea.

Full text not available from this repository.

Abstract

Under person re-identification (Re-ID), a query photo of the target person is often required for retrieval. However, one is not always guaranteed to have such a photo readily available under a practical forensic setting. In this paper, we define the problem of Sketch Re-ID, which instead of using a photo as input, it initiates the query process using a professional sketch of the target person. This is akin to the traditional problem of forensic facial sketch recognition, yet with the major difference that our sketches are whole-body other than just the face. This problem is challenging because sketches and photos are in two distinct domains. Specifically, a sketch is the abstract description of a person. Besides, person appearance in photos is variational due to camera viewpoint, human pose and occlusion. We address the Sketch Re-ID problem by proposing a cross-domain adversarial feature learning approach to jointly learn the identity features and domain-invariant features. We employ adversarial feature learning to filter low-level interfering features and remain high-level semantic information. We also contribute to the community the first Sketch Re-ID dataset with 200 persons, where each person has one sketch and two photos from different cameras associated. Extensive experiments have been performed on the proposed dataset and other common sketch datasets including CUFSF and QUML-shoe. Results show that the proposed method outperforms the state-of-the-arts.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Pang, L.
Wang, Y.
Song, Yi-Zhey.song@surrey.ac.uk
Huang, T.
Tian, Y.
Date : 15 October 2018
DOI : 10.1145/3240508.3240606
Uncontrolled Keywords : Adversarial feature learning; Cross-domain matching; Domain-invariant features; Sketch re-identification
Related URLs :
Additional Information : No further action
Depositing User : Clive Harris
Date Deposited : 05 Jul 2019 10:17
Last Modified : 05 Jul 2019 10:17
URI: http://epubs.surrey.ac.uk/id/eprint/852108

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800