Article
Engineering, Electrical & Electronic
Ying Yi, Hu Zhang, Wei Zhang, Yahua Yuan, Changping Li
Summary: This article presents a novel fatigue detection algorithm based on facial multifeature fusion, which exhibits promising properties of immediacy and accuracy, avoiding the inefficiency, safety concerns, and health problems caused by working under fatigue states.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Jin Xie, Jing Nie, Bonan Ding, Mingyang Yu, Jiale Cao
Summary: RGB-infrared object detection is crucial for around-the-clock UAV surveillance. We propose a CLGNet that integrates cross-modal local calibration and global context modeling to improve detection accuracy.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Engineering, Civil
Shuo Yang, Huimin Lu, Jianru Li
Summary: This study proposes a multi-feature fusion network (MFFNet) to improve the detection precision of 3D point cloud data by combining global features with local features. Experimental results on the KITTI and Waymo datasets demonstrate the high efficiency and location accuracy of the proposed method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Ying Yi, Hu Zhang, Wei Zhang, Yahua Yuan, Changping Li
Summary: Working under fatigue states is inefficient and poses safety and health risks. This article introduces a novel fatigue detection algorithm based on facial multifeature fusion, showcasing its immediacy and accuracy. By processing video frames and extracting facial features in real-time, the algorithm can identify fatigue grades with high accuracy and quick response, providing reliable results in detecting fatigue behaviors.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Qihan Bo, Wei Ma, Yu-Kun Lai, Hongbin Zha
Summary: This paper proposes a deep framework for Semantic Edge Detection (SED) using a new multi-stage feature fusion structure and two enhancement modules. The method effectively fuses detail features and semantic context in images, improving the accuracy of edge localization and classification.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Xiaobin Xu, Lei Zhang, Jian Yang, Chenfei Cao, Zhiying Tan, Minzhou Luo
Summary: This article presents an object detection fusion algorithm based on LiDAR point cloud and camera image, combining object detection with YOLOv4 and point cloud processing to achieve high accuracy in target detection.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Giovani Bernardes Vitor, Alessandro Correa Victorino, Janito Vaqueiro Ferreira
Summary: This article presents an approach to improve the perception capability of intelligent vehicles in complex urban environments by modeling occupancy grids from semantic context images associated with depth information and using the evidential formalism of the Dempster-Shafer theory to manage uncertainties. Real experiments show that the proposed method is able to better handle semantic, dynamic and uncertainty aspects in the environment representation.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Wei-Yen Hsu, Wen-Yen Lin
Summary: This study proposes a new ratio-and-scale-aware YOLO method to address the issue of low pedestrian detection performance caused by small pedestrian ratios and significant differences in input image aspect ratios. Results show that the method performs well in detecting extremely small objects and images with large aspect ratio differences.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Geochemistry & Geophysics
Mingfeng Zh, Wenbin Qian, Wenji Yang, Yilu Xu
Summary: This letter proposes a novel ship detection model based on multifeature transformation and fusion (MFTF-Net) to address the issues of high false alarm detection rate and prone missed detection in SAR image ship detection. The proposed model utilizes anchor frame clustering, local enhancement network, improved transformer structure, and four-scale residual feature fusion network to achieve better performance compared to 13 baseline models.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Chao Yang, Yongpeng Li, Longyu Jiang, Jianxing Huang
Summary: In this paper, two modules are proposed to solve the problems of widespread noise and lack of high-frequency information in sonar image object detection. The foreground semantic enhancement module associates the semantic map with features to increase the foreground-background distance, while the foreground edge enhancement module enhances edges by spatial semantic information. A novel detection architecture, FEN network, is designed based on these modules to improve classification and localization accuracy.
MACHINE VISION AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jialu Zhang, Jianfeng Ren, Qian Zhang, Jiang Liu, Xudong Jiang
Summary: In this paper, a multi-branch deep neural network is proposed for multi-label image classification. It effectively utilizes label-related semantic information, background context, and spatial semantic information to better detect target objects. Experimental results show that the proposed method outperforms the state-of-the-art methods for multi-label image classification.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Ying Yi, Zhushijie Zhou, Wei Zhang, Mingyue Zhou, Yahua Yuan, Changping Li
Summary: This article proposes a novel fatigue detection algorithm using the Dlib toolkit to mark facial feature points and considers the eye's multifeature. The algorithm achieves an optimal weight distribution for fusion and improves the reliability and error tolerance rate of detection. The testing results demonstrate a high accuracy rate of 95%, indicating strong potential in fatigue detection applications.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Yongming Rao, Wenliang Zhao, Zheng Zhu, Jie Zhou, Jiwen Lu
Summary: We present GFNet, a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain. GFNet outperforms Transformer-based models and CNNs in terms of efficiency, generalization ability, and robustness. We provide a series of isotropic and hierarchical models based on GFNet design.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Manufacturing
Philipp Ulrich, Nour Ramzy, Marco Ratusny
Summary: Demand planning in the semiconductor industry is challenging due to extended cycle times, rapid innovation cycles, and the Bullwhip Effect. This study proposes a methodology called SCIM-NN that incorporates semantic context information into the classification task, resulting in improved overall performance compared to a benchmark CNN model. The application of SCIM-NN on a use case in the domain of COB demonstrates its effectiveness on customer data of Infineon Technologies AG.
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING
(2023)
Article
Engineering, Electrical & Electronic
Fushuo Huo, Xuegui Zhu, Lei Zhang, Qifeng Liu, Yu Shu
Summary: The study proposed an efficient encoder-decoder network named Context-guided Stacked Refinement Network (CSRNet), which reduces computational cost using a lightweight backbone and efficient decoder parts, fuses RGB and T modalities through the Context-guided Cross Modality Fusion (CCMF) module, and refines features progressively via the Stacked Refinement Network (SRN).
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Dailin Lv, Yaqi Wang, Shuai Wang, Qianni Zhang, Wuteng Qi, Yunxiang Li, Lingling Sun
Summary: The proposed Cascade-SEME framework effectively detects COVID-19 cases by evaluating chest x-ray images, improving model performance significantly in pneumonia infection type diagnosis and COVID-19 detection tasks. The application of SEME structure in the network enhances the performance of ResNet50 and DenseNet169, while Regional Learning corrects the impact of non-lesion features and directs the network's attention to relevant pathological regions in lung radiographs.
Article
Cardiac & Cardiovascular Systems
Emrah Erdogan, Xingru Huang, Jackie Cooper, Ajay Jain, Anantharaman Ramasamy, Retesh Bajaj, Ryo Torii, James Moon, Andrew Deaner, Christos Costa, Hector M. Garcia-Garcia, Vincenzo Tufaro, Patrick W. Serruys, Francesca Pugliese, Anthony Mathur, Jouke Dijkstra, Andreas Baumbach, Qianni Zhang, Christos V. Bourantas
Summary: This study compared the reproducibility of IVUS volumetric analysis at fixed frame intervals and at end diastolic (ED) frames, showing that ED analysis was more reproducible and stable, providing more accurate results for longitudinal studies assessing novel pharmacotherapies.
CATHETERIZATION AND CARDIOVASCULAR INTERVENTIONS
(2022)
Article
Cardiac & Cardiovascular Systems
Retesh Bajaj, Xingru Huang, Yakup Kilic, Anantharaman Ramasamy, Ajay Jain, Mick Ozkor, Vincenzo Tufaro, Hannah Safi, Emrah Erdogan, Patrick W. Serruys, James Moon, Francesca Pugliese, Anthony Mathur, Ryo Torii, Andreas Baumbach, Jouke Dijkstra, Qianni Zhang, Christos Bourantas
Summary: This study aimed to develop and validate a deep learning methodology for automated and accurate segmentation of IVUS image sequences in real-time. The results demonstrated that the developed DL methodology showed minimal differences compared to expert analysts, indicating its accuracy and reliability for segmenting IVUS images.
INTERNATIONAL JOURNAL OF CARDIOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Yibao Sun, Xingru Huang, Huiyu Zhou, Qianni Zhang
Summary: The proposed similarity based region proposal networks (SRPN) for nuclei and cells detection in histology images utilize an embedding layer for similarity learning to enhance classification performance. Experimental results demonstrate that networks applying similarity learning outperform conventional methods on both tasks of multi-organ nuclei detection and signet ring cells detection.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Lei Tong, Zhihua Liu, Zheheng Jiang, Feixiang Zhou, Long Chen, Jialin Lyu, Xiangrong Zhang, Qianni Zhang, Abdul Sadka, Yinhai Wang, Ling Li, Huiyu Zhou
Summary: Depression is a common mental health disorder, and many sufferers do not seek help due to shame or lack of awareness. This paper proposes a novel classifier, CBPT, which can accurately detect depression by mining online social behaviors. The results show that the framework has promising potential for identifying Twitter users with depression.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Information Systems
Yunxiang Li, Guodong Zeng, Yifan Zhang, Jun Wang, Qun Jin, Lingling Sun, Qianni Zhang, Qisi Lian, Guiping Qian, Neng Xia, Ruizi Peng, Kai Tang, Shuai Wang, Yaqi Wang
Summary: The article introduces an automated evaluation method for root canal therapy results using computer vision and artificial intelligence, proposing a novel AGMB-Transformer network to improve diagnostic accuracy. Through collecting a large-scale dataset of root canal therapy X-ray images, the experimental results demonstrate the effectiveness and accuracy of the approach.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Automation & Control Systems
Aite Zhao, Jianbo Li, Junyu Dong, Lin Qi, Qianni Zhang, Ning Li, Xin Wang, Huiyu Zhou
Summary: This article proposes a novel hybrid model to learn gait differences between different neurodegenerative diseases, Parkinson's disease severity levels, and healthy individuals and patients through fusion and aggregation of data from multiple sensors. The model utilizes a spatial feature extractor and a new correlative memory neural network architecture to capture temporal information, along with a multiswitch discriminator to associate observations with individual state estimations. Compared to several state-of-the-art techniques, the framework shows more accurate classification results.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Biology
Jinhao Li, Shuai Wang, Shaodan Hu, Yiming Sun, Yaqi Wang, Peifang Xu, Juan Ye
Summary: This paper proposes a novel method, CAA-Net, for automatically diagnosing infectious keratitis using corneal photographs. The method combines class-awareness and attention strategies, and has been verified to be effective in diagnosing different types of infectious keratitis.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Biomedical
Edgar Giussepi Lopez Molina, Xingru Huang, Qianni Zhang
Summary: This research combines co-training and attention mechanisms to propose a new type of attention based on disagreement, which improves model generalization. It also introduces an innovative deep supervision approach that trains the model following the sequence of supervision branches. Extensive experiments on LiTS17 and CT-82 datasets verify the effectiveness of these approaches.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Ji Lin, Xingru Huang, Huiyu Zhou, Yaqi Wang, Qianni Zhang
Summary: Automated retinal blood vessel segmentation in fundus images is a challenging task due to the variety in scale and appearance of blood vessels, as well as the similarity in visual features between lesions and retinal vascular. In this study, a Stimulus-Guided Adaptive Transformer Network (SGAT-Net) is proposed to accurately segment retinal blood vessels by extracting compound features, enriching contextual embedding representation, and adjusting the receptive field based on the task. Experimental results on multiple datasets demonstrate the competitive performance and advantage of the proposed method in avoiding errors in areas with similar visual features. The source code is publicly available at https://github.com/Gins-07/SGAT.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhihua Liu, Lei Tong, Long Chen, Feixiang Zhou, Zheheng Jiang, Qianni Zhang, Yinhai Wang, Caifeng Shan, Ling Li, Huiyu Zhou
Summary: The study introduces a novel method called CANet for brain glioma segmentation, which outperforms other methods and is better at incorporating contextual information of tumor cells and their surrounding environment.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Information Systems
Zongyi Xu, Wei Chang, Yindi Zhu, Le Dong, Huiyu Zhou, Qianni Zhang
Summary: Two approaches are proposed to estimate high-fidelity human body models, one based on 3D scanner point clouds and the other based on 2D images from smartphones. Extensive experiments demonstrate that both approaches can robustly build believable and animatable human body models.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jingxiong Li, Yaqi Wang, Qianni Zhang
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2019), PT II
(2019)
Article
Computer Science, Information Systems
Liang Xie, Jili Tao, Qianni Zhang, Huiyu Zhou
Proceedings Paper
Engineering, Biomedical
Zhaoyang Xu, Faranak Sohhani, Carlos Fernandez Moro, Qianni Hang
2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019)
(2019)