Huibo Zhou

Dr. Huibo Zhou


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
11 February 2016 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
JSJunhong Song
Junhong Song
SSShenmin Song
Shenmin Song
HZHuibo Zhou
Huibo Zhou

10 April 2025 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
RCRuolan Chen
Ruolan Chen
HZHuibo Zhou
Huibo Zhou
HXHui Xie
Hui Xie
BWBingyang Wang
Bingyang Wang

6 October 2025 in Measurement
Verified
Journal Article
Closed access
HXHui Xie
Hui Xie
HZHuibo Zhou
Huibo Zhou
RCRuolan Chen
Ruolan Chen
BWBingyang Wang
Bingyang Wang

23 December 2016 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
HZHuibo Zhou
Huibo Zhou
SSShen-Min Song
Shen-Min Song
JSJun-Hong Song
Jun-Hong Song

24 April 2024 in Symmetry
Verified
Journal Article
Open access
PDF file
MZMing Zhao
Ming Zhao
HZHuibo Zhou
Huibo Zhou
XLXue Li
Xue Li
Exploring the ocean’s resources requires finding underwater objects, which is a challenging task due to blurry images and small, densely packed targets. To improve the accuracy of underwater target detection, we propose an enhanced version of the YOLOv7 network called YOLOv7-SN. Our goal is to optimize the effectiveness and accuracy of underwater target detection by introducing a series of innovations. We incorporate the channel attention module SE into the network’s key part to improve the extraction of relevant features for underwater targets. We also introduce the RFE module with dilated convolution behind the backbone network to capture multi-scale information. Additionally, we use the Wasserstein distance as a new metric to replace the traditional loss function and address the challenge of small target detection. Finally, we employ probe heads carrying implicit knowledge to further enhance the model’s accuracy. These methods aim to optimize the efficacy of underwater target detection and improve its ability to deal with the complexity and challenges of underwater environments. We conducted experiments on the URPC2020, and RUIE datasets. The results show that the mean accuracy (mAP) is improved by 5.9% and 3.9%, respectively, compared to the baseline model.

1 January 2024 in Mathematical Biosciences and Engineering
Verified
Journal Article
Open access
PDF file
XLXue Li
Xue Li
HZHuibo Zhou
Huibo Zhou
MZMing Zhao
Ming Zhao
The threat posed by forged video technology has gradually grown to include individuals, society, and the nation. The technology behind fake videos is getting more advanced and modern. Fake videos are appearing everywhere on the internet. Consequently, addressing the challenge posed by frequent updates in various deepfake detection models is imperative. The substantial volume of data essential for their training adds to this urgency. For the deepfake detection problem, we suggest a cascade network based on spatial and channel reconstruction convolution (SCConv) and vision transformer. Our network model's front portion, which uses SCConv and regular convolution to detect fake videos in conjunction with vision transformer, comprises these two types of convolution. We enhance the feed-forward layer of the vision transformer, which can increase detection accuracy while lowering the model's computing burden. We processed the dataset by splitting frames and extracting faces to obtain many images of real and fake faces. Examinations conducted on the DFDC, FaceForensics++, and Celeb-DF datasets resulted in accuracies of 87.92, 99.23 and 99.98%, respectively. Finally, the video was tested for authenticity and good results were obtained, including excellent visualization results. Numerous studies also confirm the efficacy of the model presented in this study.