Results 11 to 20 of about 673,799 (364)
Task Scheduling Strategy for Energy Consumption Optimization of Cloud Data Center Based on Improved Particle Swarm Algorithm [PDF]
Jisuanji kexue, 2023 With the development of cloud computing,energy consumptionhas increased dramatically,which further limits the improvement of the overall performance of the cloud data center,and thus the energy consumption issue has attracted the attention of industry ...
LIU Chenwei, SUN Jian, LEI Bingbing, XU Tao, WU Zhuiwei
doaj +1 more source
Research Progress of Lightweight Neural Network Convolution Design [PDF]
Jisuanji kexue yu tansuo, 2022 Traditional neural networks have the disadvantages of over-reliance on hardware resources and high requirements for application equipment performance. Therefore, they cannot be deployed on edge devices and mobile terminals with limited computing power ...
MA Jinlin, ZHANG Yu, MA Ziping, MAO Kaiji
doaj +1 more source
Artistic Image Technology and Computer Graphics
The Journal of The Institute of Image Information and Television Engineers, 2018 Nobuhiko Mukai +3 more
openaire +3 more sources
HSKDLR: Lightweight Lip Reading Method Based on Homogeneous Self-Knowledge Distillation [PDF]
Jisuanji kexue yu tansuo, 2023 In order to solve the problems of low recognition rate and large amount of calculation in lip reading, this paper proposes a lightweight model for lip reading named HSKDLR （homogeneous self-knowledge distillation for lip reading）.
MA Jinlin, LIU Yuhao, MA Ziping, GONG Yuanwen, ZHU Yanbin
doaj +1 more source
The impact of interdisciplinary dynamic images on public perception [PDF]
E3S Web of Conferences, 2021 Dynamic image, usually defined as motion graphics or dynamic graphics, is a kind of image art based on art design and computer science. In a broad sense, dynamic image is a discipline that integrates animation, film, and graphic design.
Shi ChaoYuan, Gu Li
doaj +1 more source
DigiFace-1M: 1 Million Digital Face Images for Face Recognition [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2022 State-of-the-art face recognition models show impressive accuracy, achieving over 99.8% on Labeled Faces in the Wild (LFW) dataset. Such models are trained on large-scale datasets that contain millions of real human face images collected from the ...
Gwangbin Bae +7 more
semanticscholar +1 more source
SE-IYOLOV3: An Accurate Small Scale Face Detector for Outdoor Security
Mathematics, 2020 Small scale face detection is a very difficult problem. In order to achieve a higher detection accuracy, we propose a novel method, termed SE-IYOLOV3, for small scale face in this work.
Zhenrong Deng +4 more
doaj +1 more source
Annals of GIS, 2023 This article is dedicated to the problem of realistic colour rendering of space object images using the tools of computer graphics. In the form of a short essay, the authors describe the essence, sources and functionality of modern graphics applications.
Vladimir Khokhlov +2 more
doaj +1 more source
Review of Extracting Methods for Lip Visual Features
Jisuanji kexue yu tansuo, 2021 Current research on lip recognition focuses on improving recognition accuracy and studying features of multimodal inputs. However, little attention has been paid to improving the effectiveness of lip visual features.
MA Jinlin, GONG Yuanwen, MA Ziping, CHEN Deguang, ZHU Yanbin, LIU Yuhao
doaj +1 more source
Review of Pre-training Techniques for Natural Language Processing
Jisuanji kexue yu tansuo, 2021 In the published reviews of natural language pre-training technology, most literatures only elaborate neural network pre-training technologies or a brief introduction to traditional pre-training technologies, which may result in the development process ...
CHEN Deguang, MA Jinlin, MA Ziping, ZHOU Jie
doaj +1 more source