Weihua Ou

Dr. Weihua Ou

School of Bigdata and Computer Science, Guizhou Normal University, Guiyang, Guizhou, China
orcid

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 January 2019 in Expert Systems with Applications
Verified
Journal Article
Closed access
Jianping GouJianping Gou
Jianping Gou
HMHongxing Ma
Hongxing Ma
WOWeihua Ou
Weihua Ou
SZShaoning Zeng
Shaoning Zeng
YRYunbo Rao
Yunbo Rao
HYHebiao Yang
Hebiao Yang

1 April 2014 in Pattern Recognition
Verified
Journal Article
Closed access
WOWeihua Ou
Weihua Ou
XYXinge You
Xinge You
DTDacheng Tao
Dacheng Tao
PZPengyue Zhang
Pengyue Zhang
YTYuanyan Tang
Yuanyan Tang
ZZZiqi Zhu
Ziqi Zhu

20 September 2019 in IEEE Access
Verified
Journal Article
Open access
FLFei Long
Fei Long
KZKai Zhou
Kai Zhou
WOWeihua Ou
Weihua Ou
Recent years, many scientists address the research on text sentiment analysis of social media due to the exponential growth of social multimedia content. Natural language ambiguities and indirect sentiments within the social media text have made it hard to classify by using traditional machine learning approaches, such as support vector machines, naive Bayes, hybrid models and so on. This article aims to investigate the sentiment analysis of social media Chinese text by combining Bidirectional Long-Short Term Memory (BiLSTM) networks with a Multi-head Attention (MHAT) mechanism in order to overcome the deficiency of Sentiment Analysis that is performed with traditional machine learning. BiLSTM networks, not only solve the long-term dependency problem, but they also capture the actual context of the text. Due to the fact that the MHAT mechanism can learn the relevant information from a different representation subspace by using multiple distributed calculations, the purpose is to add influence weights to the constructed text sequence. The results of the numerical experiments show that the proposed model achieves better performance than the existing wellestablished methods.

26 September 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
Jianping GouJianping Gou
Jianping Gou
LSLiyuan Sun
Liyuan Sun
BYBaosheng Yu
Baosheng Yu
Shaohua WanShaohua Wan
Shaohua Wan
WOWeihua Ou
Weihua Ou
ZYZhang Yi
Zhang Yi
Recently, model compression has been widely used for the deployment of cumbersome deep models on resource-limited edge devices in the performance-demanding industrial Internet of Things (IoT) scenarios. As a simple yet effective model compression technique, knowledge distillation (KD) aims to transfer the knowledge (e.g., sample relationships as the relational knowledge) from a large teacher model to a small student model. However, existing relational knowledge distillation methods usually build sample correlations directly from the feature maps at a certain middle layer in deep neural networks, which tends to overfit the feature maps of the teacher model and fails to address the most important sample regions. Inspired by this, we argue that the characteristics of important regions are of great importance and thus introduce attention maps to construct sample correlations for knowledge distillation. Specifically, with attention maps from multiple middle layers, attention-based sample correlations are newly built upon the most informative sample regions, and can be used as an effective and novel relational knowledge for knowledge distillation. We refer to the proposed method as multi-level attention-based sample correlations for knowledge distillation (or MASCKD). We perform extensive experiments on popular knowledge distillation datasets for image classification, image retrieval, and person re-identification, where the experimental results demonstrate the effectiveness of the proposed method for relational knowledge distillation.

4 May 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YSYufeng Shi
Yufeng Shi
YZYue Zhao
Yue Zhao
XLXin Liu
Xin Liu
FZFeng Zheng
Feng Zheng
WOWeihua Ou
Weihua Ou
QPQinmu Peng
Qinmu Peng
Cross-modal hashing that leverages hash functions to project high-dimensional data from different modalities into the compact common hamming space, has shown immeasurable potential in cross-modal retrieval. To ease labor costs, unsupervised cross-modal hashing methods are proposed. However, existing unsupervised methods still suffer from two factors in the optimization of hash functions: 1) similarity guidance, they barely give a clear definition of whether is similar or not between data points, leading to the residual of the redundant information; 2) optimization strategy, they ignore the fact that the similarity learning abilities of different hash functions are different, which makes the hash function of one modality weaker than the hash function of the other modality. To alleviate such limitations, this paper proposes an unsupervised cross-modal hashing method to train hash functions with discriminative similarity guidance and adaptively-enhanced optimization strategy, termed Deep Adaptively-Enhanced Hashing (DAEH). Specifically, to estimate the similarity relations with discriminability, Information Mixed Similarity Estimation (IMSE) is designed by integrating information from distance distributions and the similarity ratio. Moreover, Adaptive Teacher Guided Enhancement (ATGE) optimization strategy is also designed, which employs information theory to discover the weaker hash function and utilizes an extra teacher network to enhance it. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed DAEH against the state-of-the-arts.

19 April 2018 in World Wide Web
Verified
Journal Article
Closed access
PDF file
QZQuan Zhou
Quan Zhou
WYWenbing Yang
Wenbing Yang
GGGuangwei Gao
Guangwei Gao
WOWeihua Ou
Weihua Ou
HLHuimin Lu
Huimin Lu
LLLongin Jan Latecki
Longin Jan Latecki