Institution
Dalian University of Technology
Education•Dalian, China•
About: Dalian University of Technology is a education organization based out in Dalian, China. It is known for research contribution in the topics: Catalysis & Finite element method. The organization has 60890 authors who have published 71921 publications receiving 1188356 citations. The organization is also known as: Dàlián Lǐgōng Dàxué.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this article, the impact of redox potentials on gene expression, protein biosynthesis and metabolism as well as redox-potential control strategies for more efficient production of fermentation products are reviewed.
201 citations
••
TL;DR: The neural correlates of maintaining a state or switching between states are explored, and it is argued that the anterior cingulate cortex and striatum play a critical role in state maintenance, whereas the insula has a major role in switching betweenStates.
201 citations
••
14 Jun 2020
TL;DR: This work presents a novel Adaptive Pyramid Loss (APLoss) to hierarchically calculate the estimation losses of sub-regions, which alleviates the training bias and demonstrates the superiority of the proposed approach to alleviate the counting performance differences in different regions.
Abstract: Convolutional Neural Network (CNN) based methods generally take crowd counting as a regression task by outputting crowd densities. They learn the mapping between image contents and crowd density distributions. Though having achieved promising results, these data-driven counting networks are prone to overestimate or underestimate people counts of regions with different density patterns, which degrades the whole count accuracy. To overcome this problem, we propose an approach to alleviate the counting performance differences in different regions. Specifically, our approach consists of two networks named Density Attention Network (DANet) and Attention Scaling Network (ASNet). DANet provides ASNet with attention masks related to regions of different density levels. ASNet first generates density maps and scaling factors and then multiplies them by attention masks to output separate attention-based density maps. These density maps are summed to give the final density map. The attention scaling factors help attenuate the estimation errors in different regions. Furthermore, we present a novel Adaptive Pyramid Loss (APLoss) to hierarchically calculate the estimation losses of sub-regions, which alleviates the training bias. Extensive experiments on four challenging datasets (ShanghaiTech Part A, UCF_CC_50, UCF-QNRF, and WorldExpo'10) demonstrate the superiority of the proposed approach.
201 citations
••
TL;DR: A review of current research and development activities in the field of high-rise structure health monitoring using the Global Positioning System (GPS) is presented in this paper, where existing problems and promising research efforts in the GPS-based health monitoring are given.
Abstract: SUMMARY
Monitoring the response of structures, especially tall buildings, under severe loading conditions is an important requirement for the validation of their design and construction, as well as being a maintenance concern. This paper presents a review of current research and development activities (since 1995) in the field of high-rise structure health monitoring using the Global Positioning System (GPS). The GPS monitoring technology and its accurate assessment method are firstly briefly described. Then, the progresses on monitoring the displacement of the high-rise structure caused by the ambient effects including wind, thermal variation, and earthquake-induced responses are discussed in details. Following that, the states of the art of augmenting the GPS monitoring technology are reviewed. Finally, existing problems and promising research efforts in the GPS-based health monitoring are given. Copyright © 2012 John Wiley & Sons, Ltd.
201 citations
••
01 Oct 2019TL;DR: In this paper, a gradient-guided siamese network is proposed to exploit the discriminative information in gradients and update the template in the Siamese networks through feed-forward and backward operations.
Abstract: The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network. However, this manner cannot capture the temporal variations of targets or background clutter. In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations. To be specific, the algorithm can utilize the information from the gradient to update the template in the current frame. In addition, a template generalization training method is proposed to better use gradient information and avoid overfitting. To our knowledge, this work is the first attempt to exploit the information in the gradient for template update in siamese-based trackers. Extensive experiments on recent benchmarks demonstrate that our method achieves better performance than other state-of-the-art trackers.
201 citations
Authors
Showing all 61205 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yang Yang | 171 | 2644 | 153049 |
Yury Gogotsi | 171 | 956 | 144520 |
Hui Li | 135 | 2982 | 105903 |
Michael I. Posner | 134 | 414 | 104201 |
Anders Hagfeldt | 129 | 600 | 79912 |
Jian Zhou | 128 | 3007 | 91402 |
Chao Zhang | 127 | 3119 | 84711 |
Bin Wang | 126 | 2226 | 74364 |
Chi Lin | 125 | 1313 | 102710 |
Tao Zhang | 123 | 2772 | 83866 |
Bo Wang | 119 | 2905 | 84863 |
Zhenyu Zhang | 118 | 1167 | 64887 |
Liang Cheng | 116 | 1779 | 65520 |
Anthony G. Fane | 112 | 565 | 40904 |
Xuelong Li | 110 | 1044 | 46648 |