Hefeng Yin

Dr. Hefeng Yin


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2018 in Pattern Recognition
Verified
Journal Article
Open access
PKPaul Koppen
Paul Koppen
ZFZhen-Hua Feng
Zhen-Hua Feng
JKJosef Kittler
Josef Kittler
MAMuhammad Awais
Muhammad Awais
WCWilliam Christmas
William Christmas
HYHefeng Yin
Hefeng Yin
3D Morphable Face Models (3DMM) have been used in pattern recognition for some time now. They have been applied as a basis for 3D face recognition, as well as in an assistive role for 2D face recognition to perform geometric and photometric normalisation of the input image, or in 2D face recognition system training. The statistical distribution underlying 3DMM is Gaussian. However, the single-Gaussian model seems at odds with reality when we consider different cohorts of data, e.g. Black and Chinese faces. Their means are clearly different. This paper introduces the Gaussian Mixture 3DMM (GM-3DMM) which models the global population as a mixture of Gaussian subpopulations, each with its own mean. The proposed GM-3DMM extends the traditional 3DMM naturally, by adopting a shared covariance structure to mitigate small sample estimation problems associated with data in high dimensional spaces. We construct a GM-3DMM, the training of which involves a multiple cohort dataset, SURREY-JNU, comprising 942 3D face scans of people with mixed backgrounds. Experiments in fitting the GM-3DMM to 2D face images to facilitate their geometric and photometric normalisation for pose and illumination invariant face recognition demonstrate the merits of the proposed mixture of Gaussians 3D face model

1 April 2020 in Pattern Recognition
Verified
Journal Article
Closed access
ZCZhe Chen
Zhe Chen
XWXiao-Jun Wu
Xiao-Jun Wu
HYHefeng Yin
Hefeng Yin
JKJosef Kittler
Josef Kittler

26 July 2021 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
DZDonglin Zhang
Donglin Zhang
XWXiao-Jun Wu
Xiao-Jun Wu
TXTianyang Xu
Tianyang Xu
HYHefeng Yin
Hefeng Yin
Given the merits in high computational efficiency and low storage cost, hashing techniques have been widely studied in cross-media retrieval. Existing methods usually adopt the equal length encoding scheme to represent the multimedia data. However, the strictly equal length scheme maybe not optimal because the dimension of different modalities is often various. Besides, there exists other challenges in designing a cross-media retrieval system, e.g., how to address the discrete constraints, how to avoid using the n*n similarity matrix, and how to effectively exploit the discriminative label information. To conquer the above challenges, we propose a novel method, i.e., discrete asymmetric hashing (DAH). Specifically, DAH exploits a flexible model, which can seamlessly deal with equal or unequal length encoding scenarios. Moreover, DAH constructs a supervised semantic embedding framework by jointly minimizing the distance-distance difference and label reconstructing error, significantly reducing the computational complexity. An asymmetric strategy is employed to establish the connection between hash codes and the latent subspace. Furthermore, the hash codes can be learned discretely by the designed optimization algorithm. In the training stage2, a semantic intersection scheme is proposed to learn more powerful hash functions. Experiments show that our DAH is effective in equal and unequal scenarios.

16 January 2019 in Pattern Analysis and Applications
Verified
Journal Article
Closed access
PDF file
WDWenhua Dong
Wenhua Dong
XWXiao-Jun Wu
Xiao-Jun Wu
JKJosef Kittler
Josef Kittler
HYHefeng Yin
Hefeng Yin

3 December 2019 in IEEE Access
Verified
Journal Article
Open access
HYHefeng Yin
Hefeng Yin
XWXiao-Jun Wu
Xiao-Jun Wu
SCSu-Gen Chen
Su-Gen Chen
Discriminative dictionary learning (DDL) has recently gained significant attention due to its impressive performance in various pattern classification tasks. However, the locality of atoms is not fully explored in conventional DDL approaches which hampers their classification performance. In this paper, we propose a locality constraint dictionary learning with support vector discriminative term (LCDL-SV), in which the locality information is preserved by employing the graph Laplacian matrix of the learned dictionary. To jointly learn a classifier during the training phase, a support vector discriminative term is incorporated into the proposed objective function. Moreover, in the classification stage, the identity of test data is jointly determined by the regularized residual and the learned multi-class support vector machine. Finally, the resulting optimization problem is solved by utilizing the alternative strategy. Experimental results on benchmark databases demonstrate the superiority of our proposed method over previous dictionary learning approaches on both hand-crafted and deep features. The source code of our proposed LCDL-SV is accessible at https://github.com/yinhefeng/LCDL-SV.

20 April 2025 in Measurement
Verified
Journal Article
Closed access
FJFeng Jiang
Feng Jiang
YZYanhong Zhang
Yanhong Zhang
LZLei Zhao
Lei Zhao
HLHongyue Liu
Hongyue Liu
ZSZhiqiang Song
Zhiqiang Song
YZYilin Zhu
Yilin Zhu