A Serial-Parallel Self-Attention Network Joint With Multi-Scale Dilated Convolution

Wang, Gaihua; Zhang, Tianlun; Yingying, Dai; Lin, Jinheng; Cheng, Lei

doi:10.1109/access.2021.3079243

Cited by 14 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study concluded that WOMAC scores of patients after surgery were significantly lower than the score before surgery ( P < 0.001), and the effective rate of treatment of patients at 6 months after surgery was 98.3%, indicating that TKA has a high value in improving the comprehensive condition of patients, accelerating their recovery after TKA, and significantly improving their quality of life. In the study of scholar Ackerman I.N, 121 cases with KOA who underwent TKA were followed up, and it was found that the WOMAC score at 3 months after surgery was (34.9 ± 5.2), while the score at 6 months after surgery was (26.4 ± 4.5), both of which were significantly lower than that before surgery ( P < 0.001) [ 16 – 19 ], indicating that TKA can effectively relieve the symptoms and improve the quality of life of patients. It is noteworthy that this study only investigated the curative effect of patients within 6 months after surgery, and the long-term treatment outcomes cannot be judged comprehensively.…”

Section: Discussionmentioning

confidence: 99%

Safety of Total Knee Arthroplasty in the Treatment of Knee Osteoarthritis and Its Effect on Postoperative Pain and Quality of Life of Patients

Zhang

Liu

2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Objective. To explore the safety of total knee arthroplasty (TKA) in the treatment of knee osteoarthritis (KOA) and its impact on patients’ postoperative pain and quality of life. Methods. A total of 60 KOA patients admitted to our hospital from January 2019 to January 2020 were selected as the research objects. The knee joint scores (HSS) before and after TKA were compared, and the patients’ quality of life was evaluated using the Osteoarthritis Index of Western Ontario and McMaster University (WOMAC). At the same time, the number of patients with complications was recorded, and the efficacy of TKA was comprehensively analyzed. Results. The postoperative HSS score was significantly higher than the preoperative score ( P < 0.05 ), the postoperative pain score increased with time, and the pain gradually decreased. The postoperative WOMAC score was significantly lower than the preoperative score ( P < 0.001 ), and the score at 6 months after surgery was significantly lower than that at 3 months after surgery ( P < 0.001 ). There were no complications such as severe prosthesis fracture, secondary sepsis, and patellar tendon rupture, and the total incidence of complications was 11.7%. The effective rate of treatment at 6 months after operation was 98.3%, which was significantly higher than that at 3 months after operation ( P < 0.05 ). Conclusion. Total knee arthroplasty can improve the knee joint function of patients with knee osteoarthritis, with low postoperative pain, low complication rate, and good quality of life for patients. It is worthy of promotion and application.

show abstract

Section: Discussionmentioning

confidence: 99%

Safety of Total Knee Arthroplasty in the Treatment of Knee Osteoarthritis and Its Effect on Postoperative Pain and Quality of Life of Patients

Zhang

Liu

2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…erefore, it has also helped oil painting creation find many novel and creative perspectives and speed up the creation process from a certain angle. e oil painting generation system framework [7] based on computer image processing technology is shown in Figure 1.…”

Section: Image Fusion System Of Cloud Platformmentioning

confidence: 99%

The Optimization Function of Computer Image Technology in Processing Oil Painting Creation

Zhu

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In terms of processing methods, machine learning mainly takes the network as the core and uses the network as a medium to provide services such as computing and delivery. The “cloud” is mainly composed of computers and servers, and the Internet is used to provide network services. With the continuous progress and development of computer technology, digital image processing technology based on machine learning is widely used in production and life. Machine learning uses its own storage and computing capabilities to make the development space of image processing technology broader and effectively realize the rational allocation of resources. This article mainly analyzes the basic knowledge of machine learning, the construction of image processing cloud platforms, and the image fusion system. Then, we aim to optimize the oil painting creation. Through a simple explanation of the basic connotation of images, it is clear that digital image technology and oil painting creation are closely related and complementary. The impact of education and focusing on the application of computer graphics technology to some of the techniques often used in oil painting creation makes the created works more beautiful and artistic and puts forward the application of image processing technology and computer-aided technology in oil painting creation.

show abstract

“…The attention mechanism is to select the information that is more critical to the current task from a large amount of information. Relevant studies have shown that the integration of attention mechanism and CNNs helps to enhance the spatial correlation of feature maps [ 20 – 22 ]. Bell et al [ 23 ] introduced a spatial attention mechanism into the architecture to improve the spatial relevance of the model.…”

Section: Related Workmentioning

confidence: 99%

Instance segmentation convolutional neural network based on multi-scale attention mechanism

et al. 2022

Self Cite

View full text Add to dashboard Cite

Instance segmentation is more challenging and difficult than object detection and semantic segmentation. It paves the way for the realization of a complete scene understanding, and has been widely used in robotics, automatic driving, medical care, and other aspects. However, there are some problems in instance segmentation methods, such as the low detection efficiency for low-resolution objects and the slow detection speed of images with complex backgrounds. To solve these problems, this paper proposes an instance segmentation method with multi-scale attention, which is called a Hybrid Kernel Mask R-CNN. Firstly, the hybrid convolution kernel is constructed by combining different kernels and groups, which can complement each other to extract rich information. Secondly, a multi-scale attention mechanism is designed by assign weights to different convolution kernels, which can retain more important information. After the introduction of our strategy, the network is more inclined to focus on the low-resolution objects in the image. The proposed method achieves the best accuracy over the anchor-based method. To verify the universality of the model, we test Hybrid Kernel Mask R-CNN on Balloon, xBD and COCO datasets. The test results exceed the state of art methods. And the visualization results show our method can extract low-resolution objects effectively.

show abstract

A Serial-Parallel Self-Attention Network Joint With Multi-Scale Dilated Convolution

Cited by 14 publications

References 20 publications

Safety of Total Knee Arthroplasty in the Treatment of Knee Osteoarthritis and Its Effect on Postoperative Pain and Quality of Life of Patients

Safety of Total Knee Arthroplasty in the Treatment of Knee Osteoarthritis and Its Effect on Postoperative Pain and Quality of Life of Patients

The Optimization Function of Computer Image Technology in Processing Oil Painting Creation

Instance segmentation convolutional neural network based on multi-scale attention mechanism

Contact Info

Product

Resources

About