Results 21 to 30 of about 815 (137)
, 2019 针对自然生态蝴蝶多种特征检测的实际需求,以及生态环境下蝴蝶检测效率低、精度差问题,本文提出了一种基于迁移学习和可变形卷积深度神经网络的蝴蝶检测算法(Transfer learning and deformable convolution deep learning network,TDDNET).该算法首先使用可变形卷积模型重建ResNet-101卷积层,强化特征提取网络对蝴蝶特征的学习,并以此结合区域建议网络(Region proposal network, RPN)构建二分类蝴蝶检测网络 ...
张栋 +5 more
core +2 more sources
Synthesis of embroidery based on convolutional neural network(基于卷积神经网络的刺绣风格数字合成)
Zhejiang Daxue xuebao. Lixue ban, 2019 针对刺绣风格数字化模拟方法立体感不强、缺少线条方向等问题，提出了一种基于深度学习和卷积神经网络的算法，将刺绣艺术风格传输到目标图像。利用图像语义分割网络及风格迁移网络，分别对目标内容图像与刺绣艺术风格图像进行目标提取和风格迁移。首先，输入目标内容图像与刺绣艺术风格图像，采用基于条件随机场的图像语义分割，将目标内容图与刺绣艺术风格图的前景与背景分离，并进行二值化处理，形成掩模图像；其次，将目标内容图与刺绣艺术风格图的RGB 颜色空间转换为YIQ；最后，参照掩模图像使用VGG19 ...
ZHENGRui(郑锐) +3 more
doaj +1 more source
Video description method based on multidimensional and multimodal information [PDF]
, 2020 In order to solve the problem of complex information representation in automatic video description tasks,a multi-dimensional and multi-modal visual feature extraction and fusion method was proposed.Firstly,multi-dimensional features such as static and ...
Enjie DING +3 more
core +1 more source
Active defense technology against intelligent jammer [PDF]
, 2022 In the complex electromagnetic countermeasure environment, the intelligent development of jammer has caused a serious threat to wireless communication, while the traditional anti-jamming methods often passively adjusted the working mode or parameters ...
Hao HAN +6 more
core +1 more source
野生动物学报, 2022 蛇在野外广泛分布,不同种类的蛇具有不同的特性,实现蛇的准确识别对保护生物多样性和促进全球健康具有重要意义。为提高传统神经网络模型在蛇类图像上的识别效果,以中国地区常见蛇种作为研究对象,包括金环蛇(Bungarus fasciatus)、银环蛇(B.multicinctus)、圆斑蝰(Daboia russelli siamensis)、尖吻蝮(Deinagkistrodon acutus)、竹叶青(Trimeresurus stejnegeri)和王锦蛇(Elaphe carinata ...
周志斌 罗志聪 张展榜 孙奇燕
doaj
Food Image Classification Based on CBAM-Inception V3 Transfer Learning [PDF]
To improve the accuracy of automatic recognition and classification of food images, a classification model CBAM- InceptionV3 is proposed, which embeds the Convolutional Block Attention Module.
CUI Xiao-yi +3 more
core +1 more source
Research on Scene-specific Pedestrian Detection Method Based on Deep Learning [PDF]
, 2015 行人检测一直是计算机视觉中，尤其是目标检测领域的研究重点。而由于环境的时变性和多样性，不同场景之间样本不满足同分布，普通场景下训练得到的检测器直接应用到某一特定场景时性能会急剧下降。基于这样的背景，本文依据场景的复杂程度不同提出了两种对应的解决方法，主要工作和创新点如下： 1）当背景比较简单时，容易获取样本的标定信息，本文提出了一种快速的行人检测算法，首先基于结构化局部边缘模式计算样本特征，然后通过积分图技术快速计算分类器分数，从而使得检测过程更加高效 ...
袁德东
core
Network intrusion detection technology based on DeepInsight and transfer learning [PDF]
In the dynamic field of the internet in modern life, networks are increasingly vulnerable to a diverse range of cyberattacks. Conventional intrusion detection systems based on machine learning techniques require a large number of samples for training ...
Hongjuan GE +5 more
core +1 more source
Key technologies of 6G mobile network [PDF]
, 2022 The development and social needs of mobile communication networks were firstly introduced.Then four key technologies of 6G network were respectively introduced from the perspectives of communication spectrum, coverage dimension, communication empowerment,
Anqi CHEN +3 more
core +1 more source
International Journal of Applied Linguistics, EarlyView.ABSTRACT Self‐regulated learning (SRL) as a key predictor of language learning has been widely studied, but few studies have examined it from a cross‐linguistic perspective. The present study investigated whether first language (L1) SRL strategy use transfers to second language (L2) SRL strategy use and the conditions under which this transfer occurs ...
Barry Bai, Xuan Zang, Gurpinder Lailli
wiley +1 more source