Search

Your search keyword '"Fang, Yuming"' showing total 764 results
Start Over Author "Fang, Yuming"

Refine your results

764 results on '"Fang, Yuming"'

205. Analysis of the Impact of Medical Features and Risk Prediction of Acute Kidney Injury for Critical Patients Using Temporal Electronic Health Record Data With Attention-Based Neural Network

Author

Chen, Zhimeng, primary, Chen, Ming, additional, Sun, Xuri, additional, Guo, Xieli, additional, Li, Qiuna, additional, Huang, Yinqiong, additional, Zhang, Yuren, additional, Wu, Lianwei, additional, Liu, Yu, additional, Xu, Jinting, additional, Fang, Yuming, additional, and Lin, Xiahong, additional

Published
2021
Full Text
View/download PDF

241. Visual attention modeling and its applications

Author

Fang, Yuming, Lin Weisi, School of Computer Engineering, and Centre for Multimedia and Network Technology

Subjects
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision [DRNTU]
Abstract

The visual environment for observers is usually complex, and it is impossible for the human visual system (HVS) to process all signal components and figure out their relationships immediately. Selective attention in the HVS allocates most processing resources to the salient regions rather than the entire visual view equally. There are two different types of visual attention mechanism: bottom-up and top-down. Visual attention mechanism will cause the salient regions automatically ‘pop out’ in visual scenes. In this thesis, we explore the visual attention modeling and its applications in visual signal processing. Firstly, we propose a saliency detection model for images based on human visual sensitivity and amplitude spectrum. The amplitude spectrum is adopted to represent color, intensity, and orientation distributions for image patches. The saliency value of each image patch is calculated by not only the differences between amplitude spectrum of this patch and other patches in the whole image, but also the visual impacts of these differences determined by human visual sensitivity. Due to the integration of the characteristics of the HVS and better feature representation, the proposed saliency detection model can achieve better performance than existing ones. DOCTOR OF PHILOSOPHY (SCE)

Published
2019

242. Single Image Deraining: From Model-Based to Data-Driven and Beyond

Author

Yang, Wenhan, Tan, Robby T., Wang, Shiqi, Fang, Yuming, Liu, Jiaying, Yang, Wenhan, Tan, Robby T., Wang, Shiqi, Fang, Yuming, and Liu, Jiaying

Abstract

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future directions., Comment: https://flyywh.github.io/Single_rain_removal_survey

Published
2019

243. Salient object detection on hyperspectral images using features learned from unsupervised segmentation task

Author

Imamoglu, Nevrez, Ding, Guanqun, Fang, Yuming, Kanezaki, Asako, Kouyama, Toru, Nakamura, Ryosuke, Imamoglu, Nevrez, Ding, Guanqun, Fang, Yuming, Kanezaki, Asako, Kouyama, Toru, and Nakamura, Ryosuke

Abstract

Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us to obtain redundant spectral information of the observed scenes from the reflected light source from objects. A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved. In this work, we proposed a salient object detection model on hyperspectral images by applying manifold ranking (MR) on self-supervised Convolutional Neural Network (CNN) features (high-level features) from unsupervised image segmentation task. Self-supervision of CNN continues until clustering loss or saliency maps converges to a defined error between each iteration. Finally, saliency estimations is done as the saliency map at last iteration when the self-supervision procedure terminates with convergence. Experimental evaluations demonstrated that proposed saliency detection algorithm on hyperspectral images is outperforming state-of-the-arts hyperspectral saliency models including the original MR based saliency model., Comment: 5 pages, 3 figures, accepted to appear in IEEE ICASSP 2019 (accepted version)

Published
2019

244. Electrically tunable liquid crystal coplanar waveguide stepped-impedance resonator.

Author

Fan, Xingye, Li, Ruozhou, Yan, Jing, Fang, Yuming, and Yu, Ying

Abstract

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Published
2021
Full Text
View/download PDF

245. Design and simulation of a frequency self-tuning vibration energy harvester for rotational applications.

Author

Deng, Licheng, Jiang, Jian, Zhou, Lin, Zhang, Dingli, and Fang, Yuming

Subjects
FREQUENCIES of oscillating systems, CENTRIFUGAL force, DATA analysis, ROTATIONAL motion
Abstract

In order to broaden the operating frequency bandwidth of the vibration energy harvester (VEH), a novel frequency self-tuning VEH is proposed for rotating applications. Under the rotating excitation, the proposed VEH can simultaneously adjust two parameters that affect the resonant frequency by centrifugal force, which is the key to realize frequency self-matching of the VEH in a certain frequency range. The two parameters are the axial force and effective length of the piezoelectric beam. A frequency tuning mass was designed to effectively adjust the axial force of the piezoelectric beam, and a nonlinear spring was designed to accurately control the effective length of the piezoelectric beam. The proposed VEH was simulated with ANSYS. The simulation results show that there is only one frequency matching point in a certain rotation frequency range when the centrifugal force only changes the axial force of the piezoelectric beam, which is the reason why the reported self-tuning VEH can not achieve frequency self-matching within a certain frequency range. When the centrifugal force simultaneously changes the axial force and the effective length of the piezoelectric beam, the frequency self-matching can be realized in a certain frequency range instead of only one frequency point. Simulation data analysis shows that the proposed VEH can achieve frequency self-matching in the range of 10–20 Hz through easy spring design. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

246. Video Saliency Detection by 3D Convolutional Neural Networks

Author

Ding, Guanqun and Fang, Yuming

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Computer Science - Computer Vision and Pattern Recognition
Abstract

Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks. First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences. Then, we design a 3D deconvolutional network (Deconv3DNet) to combine the spatiotemporal features to predict the final saliency map for video sequences. Experimental results show that the proposed saliency detection model performs better in video saliency prediction compared with the state-of-the-art video saliency detection methods.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results