Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition

Dongliang CHEN; Peng SONG; Wenjing ZHANG; Weijian ZHANG; Bingui XU; Xuan ZHOU

doi:10.1587/transinf.2020EDL8074

Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition

Dongliang CHEN, Peng SONG, Wenjing ZHANG, Weijian ZHANG, Bingui XU, Xuan ZHOU

Full Text Views

0

Cite this

Summary :

In this letter, we propose a novel robust transferable subspace learning (RTSL) method for cross-corpus facial expression recognition. In this method, on one hand, we present a novel distance metric algorithm, which jointly considers the local and global distance distribution measure, to reduce the cross-corpus mismatch. On the other hand, we design a label guidance strategy to improve the discriminate ability of subspace. Thus, the RTSL is much more robust to the cross-corpus recognition problem than traditional transfer learning methods. We conduct extensive experiments on several facial expression corpora to evaluate the recognition performance of RTSL. The results demonstrate the superiority of the proposed method over some state-of-the-art methods.

Publication: IEICE TRANSACTIONS on Information Vol.E103-D No.10 pp.2241-2245

Publication Date: 2020/10/01

Publicized: 2020/07/20

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020EDL8074

Type of Manuscript: LETTER

Category: Pattern Recognition

Authors

Dongliang CHEN
  Yantai University
Peng SONG
  Yantai University
Wenjing ZHANG
  Yantai University
Weijian ZHANG
  Yantai University
Bingui XU
  Shandong Institute of Space Electronic Technology
Xuan ZHOU
  Shandong Institute of Space Electronic Technology

Keyword

facial expression recognition, subspace learning, transfer learning, graph Laplacian

Cite this

Copy

Dongliang CHEN, Peng SONG, Wenjing ZHANG, Weijian ZHANG, Bingui XU, Xuan ZHOU, "Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition" in IEICE TRANSACTIONS on Information, vol. E103-D, no. 10, pp. 2241-2245, October 2020, doi: 10.1587/transinf.2020EDL8074.
Abstract: In this letter, we propose a novel robust transferable subspace learning (RTSL) method for cross-corpus facial expression recognition. In this method, on one hand, we present a novel distance metric algorithm, which jointly considers the local and global distance distribution measure, to reduce the cross-corpus mismatch. On the other hand, we design a label guidance strategy to improve the discriminate ability of subspace. Thus, the RTSL is much more robust to the cross-corpus recognition problem than traditional transfer learning methods. We conduct extensive experiments on several facial expression corpora to evaluate the recognition performance of RTSL. The results demonstrate the superiority of the proposed method over some state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8074/_p

Copy

@ARTICLE{e103-d_10_2241,
author={Dongliang CHEN, Peng SONG, Wenjing ZHANG, Weijian ZHANG, Bingui XU, Xuan ZHOU, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition},
year={2020},
volume={E103-D},
number={10},
pages={2241-2245},
abstract={In this letter, we propose a novel robust transferable subspace learning (RTSL) method for cross-corpus facial expression recognition. In this method, on one hand, we present a novel distance metric algorithm, which jointly considers the local and global distance distribution measure, to reduce the cross-corpus mismatch. On the other hand, we design a label guidance strategy to improve the discriminate ability of subspace. Thus, the RTSL is much more robust to the cross-corpus recognition problem than traditional transfer learning methods. We conduct extensive experiments on several facial expression corpora to evaluate the recognition performance of RTSL. The results demonstrate the superiority of the proposed method over some state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2020EDL8074},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 2241
EP - 2245
AU - Dongliang CHEN
AU - Peng SONG
AU - Wenjing ZHANG
AU - Weijian ZHANG
AU - Bingui XU
AU - Xuan ZHOU
PY - 2020
DO - 10.1587/transinf.2020EDL8074
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2020
AB - In this letter, we propose a novel robust transferable subspace learning (RTSL) method for cross-corpus facial expression recognition. In this method, on one hand, we present a novel distance metric algorithm, which jointly considers the local and global distance distribution measure, to reduce the cross-corpus mismatch. On the other hand, we design a label guidance strategy to improve the discriminate ability of subspace. Thus, the RTSL is much more robust to the cross-corpus recognition problem than traditional transfer learning methods. We conduct extensive experiments on several facial expression corpora to evaluate the recognition performance of RTSL. The results demonstrate the superiority of the proposed method over some state-of-the-art methods.
ER -