Deep High-Resolution Network With Double Attention Residual Blocks for Human Pose Estimation

Huo, Zhanqiang; Jin, Han; Qiao, Yingxu; Luo, Fen

doi:10.1109/access.2020.3044885

Cited by 7 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method further improves tracking accuracy through approximation measurement and subset selection. The literature introduces a high-resolution human keypoint detection network based on attention mechanism, and based on this, designs and implements a correction system for athletes' starting movements (Huo et al 2020). In order to support the effective application of corrective systems, the literature designed a dataset of athlete starting posture images containing three stages: positioning stage, preparation stage, and running stage.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Simulated Track and Field Starting Motion Based on Spectral Sensors and Motion Capture Algorithms

2024

Preprint

View full text Add to dashboard Cite

In track and field movements, effective starting movements can improve an athlete's explosive power and acceleration, and enhance their competitive level. The existing methods are mainly based on manual visual inspection and two-dimensional image analysis. Therefore, this study proposes a new method based on spectral sensors and motion capture algorithms to better analyze starting movements. The study used spectral sensors and motion capture systems to collect data on starting movements. Spectral sensors measure the movement status of various parts of the athlete's body in real-time, accurately capturing the movement changes during the starting process. In order to analyze the key links and motion trajectories of the starting motion, the motion capture algorithm processes the data collected by sensors in real time, and obtains key parameters based on changes in body parts to analyze the details of the starting motion. By analyzing the collected data, a quantitative evaluation and feedback on the starting movement can be obtained. These evaluation results can help athletes and coaches better understand the advantages and improvement space of the starting movement, and provide them with targeted training suggestions.

show abstract

Section: Related Workmentioning

confidence: 99%

Analysis of Simulated Track and Field Starting Motion Based on Spectral Sensors and Motion Capture Algorithms

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In [40], the improvement of YOLOv5s using the CA mechanism resulted in a 30% smaller size than the original model, but still ensured its good detection accuracy. The CAM and parallel residual attention blocks were used in [41,42] to improve the accuracy of the then-highest accuracy models on vehicle model recognition and human pose estimation applications, respectively. It has been proved that mixed attention can effectively improve the robustness of the network as well as the accuracy in practical application.…”

Section: Attention Mechanismmentioning

confidence: 99%

YOLOv7 Optimization Model Based on Attention Mechanism Applied in Dense Scenes

Wang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With object detection technology, real-time detection of dense scenes has become an important application requirement in various industries, which is of great significance for improving production efficiency and ensuring public safety. However, the current mainstream target detection algorithms have problems such as insufficient accuracy or inability to achieve real-time detection when detecting dense scenes, and to address this problem this paper improves the YOLOv7 model using attention mechanisms that can enhance critical information. Based on the original YOLOv7 network model, part of the traditional convolutional layers are replaced with the standard convolution combined with the attention mechanism. After comparing the optimization results of three different attention mechanisms, CBAM, CA, and SimAM, the YOLOv7B-CBAM model is proposed, which effectively improves the accuracy of object detection in dense scenes. The results on VOC datasets show that the YOLOv7B-CBAM model has the highest accuracy, reaching 87.8%, 1.5% higher than that of the original model, and outperforms the original model as well as other models with improved attention mechanisms in the subsequent results of two other different dense scene practical application scenarios. This model can be applied to public safety detection, agricultural detection, and other fields, saving labor costs, improving public health, reducing the spread and loss of plant diseases, and realizing high-precision, real-time target detection.

show abstract

“…Some improvements are also made to give full paly to HRNet. For example, Huo et al [58] adopt the attention to suppress the unimportant information and Wang et al [59] additionally consider the multi-level semantic information. In the task of image restoration and enhancement, Zamir et al follow such design principle and further propose the MIRNet [2].…”

Section: Multi-resolution Strategymentioning

confidence: 99%

Image quality enhancement using hybrid attention networks

Wang

Chen

Yan

2021

IET Image Processing

View full text Add to dashboard Cite

Image quality enhancement aims to recover rich details from degraded images, which is applied into many fields, such as medical imaging, filming production and autonomous driving. Deep convolutional neural networks (CNNs) have enabled rapid development of image quality enhancement. However, most existing CNN-based methods lack versatility when targeting different subtasks in terms of the design of networks. Besides, they often fail to balance precise spatial representations and necessary contextual information. To deal with these problems, this paper proposes a novel unified framework for low-light image enhancement, image denoising and image super-resolution. The core of this architecture is a residual hybrid attention block (RHAB), which consists of several dynamic down-sampling modules (DDM) and hybrid attention up-sampling modules (HAUM). Specifically, multi-scale feature maps are fully interacted with each other with the help of nested subnetworks so that both high-resolution spatial details and high-level contextual information can be combined to improve the representation ability of the network. Further, a hybrid attention network (HAN) is proposed and evaluations on three separate subtasks demonstrate its good performance. Extensive experiments on the authors' synthetic dataset, a more complex version, show that the authors' method achieve better quantitative and visual results compared to other state-of-the-art methods.

show abstract

Deep High-Resolution Network With Double Attention Residual Blocks for Human Pose Estimation

Cited by 7 publications

References 31 publications

Analysis of Simulated Track and Field Starting Motion Based on Spectral Sensors and Motion Capture Algorithms

Analysis of Simulated Track and Field Starting Motion Based on Spectral Sensors and Motion Capture Algorithms

YOLOv7 Optimization Model Based on Attention Mechanism Applied in Dense Scenes

Image quality enhancement using hybrid attention networks

Contact Info

Product

Resources

About