Visible to the public Biblio

Filters: Author is Wang, Peng  [Clear All Filters]
2022-04-22
Zhang, Cuicui, Sun, Jiali, Lu, Ruixuan, Wang, Peng.  2021.  Anomaly Detection Model of Power Grid Data Based on STL Decomposition. 2021 IEEE 5th Information Technology,Networking,Electronic and Automation Control Conference (ITNEC). 5:1262—1265.
This paper designs a data anomaly detection method for power grid data centers. The method uses cloud computing architecture to realize the storage and calculation of large amounts of data from power grid data centers. After that, the STL decomposition method is used to decompose the grid data, and then the decomposed residual data is used for anomaly analysis to complete the detection of abnormal data in the grid data. Finally, the feasibility of the method is verified through experiments.
2021-06-01
Chen, Zhenfang, Wang, Peng, Ma, Lin, Wong, Kwan-Yee K., Wu, Qi.  2020.  Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :10083–10092.
Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring expression datasets, however, fail to provide an ideal test bed for evaluating the reasoning ability of the models, mainly because 1) their expressions typically describe only some simple distinctive properties of the object and 2) their images contain limited distracting information. To bridge the gap, we propose a new dataset for visual reasoning in context of referring expression comprehension with two main features. First, we design a novel expression engine rendering various reasoning logics that can be flexibly combined with rich visual properties to generate expressions with varying compositionality. Second, to better exploit the full reasoning chain embodied in an expression, we propose a new test setting by adding additional distracting images containing objects sharing similar properties with the referent, thus minimising the success rate of reasoning-free cross-domain alignment. We evaluate several state-of-the-art REF models, but find none of them can achieve promising performance. A proposed modular hard mining strategy performs the best but still leaves substantial room for improvement.