Yao Fu

Yao Fu

Auto-generated profile, based on publicly available information

Yao Fu

Hikvision Research Institute, Hangzhou, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
24 August 2024
Verified
Conference Paper
Open access
YFYuye Feng
Yuye Feng
WZWei Zhang
Wei Zhang
YFYao Fu
Yao Fu
WJWeihao Jiang
Weihao Jiang
JZJiang Zhu
Jiang Zhu
WRWenqi Ren
Wenqi Ren
Unsupervised anomaly detection in multivariate time series (MTS) has always been a challenging problem, and the modeling based on reconstruction has garnered significant attention. The insensitivity of these methods towards normal patterns poses challenges in distinguishing between normal and abnormal points. Firstly, the general reconstruction strategies may exhibit limited sensitivity to spatio-temporal dependencies, and their performance remains largely unaffected by such dependencies. Secondly, most methods fail to model the heteroscedastic uncertainty in MTS, hindering their abilities to derive a distinguishable criterion. For instance, normal data with high noise levels may lead to detection failure due to excessively high reconstruction errors. In this work, we emphasize the necessity of sensitivity to normal patterns, which could improve the discrimination between normal and abnormal points remarkably. To this end, we propose SensitiveHUE, a probabilistic network by implementing both reconstruction and heteroscedastic uncertainty estimation. Its core includes a statistical feature removal strategy to ensure the dependency sensitive property, and a novel MTS-NLL loss for modeling the normal patterns in important regions. Experimental results demonstrate that SensitiveHUE exhibits nontrivial sensitivity to normal patterns and outperforms the existing state-of-the-art alternatives by a large margin. Code is publicly available at this URL\footnotehttp://github.com/yuesuoqingqiu/SensitiveHUE.

4 August 2023
Verified
Conference Paper
Open access
HWHuizhao Wang
Huizhao Wang
YFYao Fu
Yao Fu
TYTao Yu
Tao Yu
LHLinghui Hu
Linghui Hu
WJWeihao Jiang
Weihao Jiang
SPShiliang Pu
Shiliang Pu
Graph Neural Networks (GNNs) have been a powerful tool to acquire high-quality node representations dealing with graphs, which strongly depends on a promising graph structure. In the real world scenarios, it is inevitable to introduce noises in graph topology. To prevent GNNs from the disturbance of irrelevant edges or missing edges, graph structure learning is proposed and has attracted considerable attentions in recent years. In this paper, we argue that current graph structure learning methods still pay no regard to the status of nodes and just judge all of their connections simultaneously using a monotonous standard, which will lead to indeterminacy and instability in the optimization process. We designate these methods as status-unaware models. To demonstrate the rationality of our point of view, we conduct exploratory experiments on publicly available datasets, and discover some exciting observations. Afterwards, we propose a new model named Graph Structure Learning via Progressive Strategy (PROSE) according to the observations, which uses a progressive strategy to acquire ideal graph structure in a status-aware way. Concretely, PROSE consists of progressive structure splitting module (PSS) and progressive structure refining module (PSR) to modify node connections according to their global potency, and we also introduce horizontal position encoding and vertical position encoding in order to capture fruitful graph topology information ignored by previous methods. On several widely-used graph datasets, we conduct extensive experiments to demonstrate the effectiveness of our model, and the source code 1 https://github.com/tigerbunny2023/PROSE is provided.

1 October 2020 in International Journal of Multimedia Data Engineering and Management
Verified
Journal Article
Closed access
PDF file
ZZZehui Zhang
Zehui Zhang
YFYao Fu
Yao Fu
TGTiegang Gao
Tiegang Gao
Image encryption algorithms usually have two processes: permutation and diffusion. In order to enhance the performance of the permutation process, this study proposes a dynamic permutation method based on XOR operation and sorting. Combined with the hyper-chaotic system, SHA-256, the proposed permutation method and the simplified advanced encryption system (S-AES), a novel image encryption algorithm is presented in this paper. Firstly, the SHA-256 is used to generate initial condition values of the chaotic system and control parameters of the permutation method. Then, the chaotic system generates pseudo-random numbers, which are used in the permutation method and S-AES. Finally, the proposed permutation method and S-AES are used to encrypt the plain-image. In particular, parallel computing is used in this study to accelerate encryption speed. The results and analysis indicate that the proposed algorithm has excellent security to resist various typical attacks and fast encryption speed.

1 December 2008
Verified
Conference Paper
Closed access
YLYinghua Lu
Yinghua Lu
XLXiaolu Li
Xiaolu Li
MQMiao Qi
Miao Qi
JLJinsong Li
Jinsong Li
YFYao Fu
Yao Fu
JKJun Kong
Jun Kong
This paper presents a novel lossless and content-based hidden transmission method of biometric images to improve the security and secrecy of biometric verification. Chaos is used to encrypt the watermark. The secret keys which called biokey are generated from the biometric image and used as the parameter value and initial condition of the chaotic map. The digital watermark embedded losslessly in the region of interest (ROI) of palmprint is used to recognize the palmprint has been destroyed or not and regarded as a user information index for verification. The watermarked ROI is hidden in the general public image using content-based steganography technology and transmitted secretly in case of attracting the attackerspsila attention. Our method can overcome the disadvantage of block-based steganographic techniques. Experimental results show that the security and performance of the proposed scheme are high.

21 October 2023
Verified
Conference Paper
Open access
ZHZhihui Hu
Zhihui Hu
YFYao Fu
Yao Fu
HZHong Zhao
Hong Zhao
XCXiaoyu Cai
Xiaoyu Cai
WJWeihao Jiang
Weihao Jiang
SPShiliang Pu
Shiliang Pu
Graph Convolutional Networks (GCNs) have made outstanding achievements in many tasks on graphs in recent years, but their success relies on sufficient training data. In practice, sparsely labeled graphs widely exist in the real world so self-training methods have become popular approaches by adding pseudo labeled nodes to enhance the performance of GCNs. However, we observe that most selected high-confidence pseudo labeled nodes by the existing methods would surround the true labeled nodes. It is what we called pseudo label over-dependence, which could lead to the non-uniform pseudo label distribution. Furthermore, a thorough experiment shows that the classification accuracy changes significantly under different label densities and the label-sparse regions show great potential improvement in the model performance. Based on the above findings, we theoretically analyze the constraint factors in the label-sparse regions and further propose reducing the feature distribution difference between the label-dense regions and label-sparse regions can effectively decrease the classification error. Thus, in this paper, we propose a novel Graph Label Information Migration framework (GLIM) to liberate pseudo labels from over-dependence. Specifically, we first propose a training dynamics module (TDM) that uses abundant training process information to find more reliable node labels and improve the model robustness against label noise. Then we propose a label migration module (LMM) that migrates label information from label-dense regions to label-sparse regions by a spectral based graph matching algorithm. These migrated labels are like the glimmers in the darkness, providing the supervision signals for the unlabeled nodes in label-sparse regions. Finally, we conduct extensive experiments to demonstrate the effectiveness of the proposed GLIM.

21 October 2023
Verified
Conference Paper
Open access
YFYao Fu
Yao Fu
JWJunhong Wan
Junhong Wan
JYJunlan Yu
Junlan Yu
WJWeihao Jiang
Weihao Jiang
SPShiliang Pu
Shiliang Pu
The recent developments in technologies bring not only increasing amount of information but also multiple information sources for Graph Representation Learning. With the success of Graph Neural Networks (GNN), there have been increasing attempts to learn representation of multi-source information leveraging its graph structures. However, existing graph methods basically combine multi-source information with different contribution scores and over-simplify the graph structures based on prior knowledge, which fail to unify complex and conflicting multi-source information. Multisensory Processing theory in cognitive neuroscience reveals human mechanism of learning multi-source information by identifying the redundancy and complementarity. Inspired by that, we propose Graph Redundancy Network (GRN) that: 1). learns a suitable representation space that maximizes multi-source interactions; 2). encodes the redundant and complementary information according to Graph Intersection and Difference of their graph structures; 3). further reinforces and explores the redundant and complementary information through low-pass and high-pass graph filters. The empirical study shows that GRN outperforms existing methods on various tasks.