University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Cross-modal subspace learning for fine-grained sketch-based image retrieval

Xu, P., Yin, Q., Huang, Y., Song, Yi-Zhe, Ma, Z., Wang, L., Xiang, T., Kleijn, W.B. and Guo, J. (2018) Cross-modal subspace learning for fine-grained sketch-based image retrieval Neurocomputing, 278. pp. 75-86.

Full text not available from this repository.


Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo. Compared with pixel-perfect depictions of photos, sketches are iconic renderings of the real world with highly abstract. Therefore, matching sketch and photo directly using low-level visual clues are insufficient, since a common low-level subspace that traverses semantically across the two modalities is non-trivial to establish. Most existing SBIR studies do not directly tackle this cross-modal problem. This naturally motivates us to explore the effectiveness of cross-modal retrieval methods in SBIR, which have been applied in the image-text matching successfully. In this paper, we introduce and compare a series of state-of-the-art cross-modal subspace learning methods and benchmark them on two recently released fine-grained SBIR datasets. Through thorough examination of the experimental results, we have demonstrated that the subspace learning can effectively model the sketch-photo domain-gap. In addition we draw a few key insights to drive future research. © 2017 Elsevier B.V.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Xu, P.
Yin, Q.
Huang, Y.
Ma, Z.
Wang, L.
Xiang, T.
Kleijn, W.B.
Guo, J.
Date : February 2018
DOI : 10.1016/j.neucom.2017.05.099
Uncontrolled Keywords : Cross-modal subspace learning; Fine-grained; Sketch-based image retrieval
Additional Information : No further action
Depositing User : Clive Harris
Date Deposited : 03 Jul 2019 15:21
Last Modified : 03 Jul 2019 15:21

Actions (login required)

View Item View Item


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