您当前所在位置: 首页 > 首发论文
筛选条件

时间

领域

全部

计算机科学技术(15)

电子、通信与自动控制技术(2)

中医学与中药学(0) 显示更多>>

临床医学(0) 交通运输工程(0) 体育科学(0) 信息科学与系统科学(0) 农学(0) 冶金工程技术(0) 力学(0) 动力与电气工程(0) 化学(0) 化学工程(0) 图书馆、情报与文献学(0) 土木建筑工程(0) 地球科学(0) 基础医学(0) 天文学(0) 安全科学技术(0) 工程与技术科学基础学科(0) 心理学(0) 教育学(0) 数学(0) 机械工程(0) 材料科学(0) 林学(0) 核科学技术(0) 水产学(0) 水利工程(0) 测绘科学技术(0) 物理学(0) 环境科学技术(0) 生物学(0) 畜牧科学、动物医学(0) 矿山工程技术(0) 管理学(0) 纺织科学技术(0) 经济学(0) 能源科学技术(0) 航空航天科学技术(0) 药学(0) 预防医学与卫生学(0) 食品科学技术(0)

学术评议

实时热搜榜

我的筛选 >
2003-2020 全部
为您找到包含“卷积网络”的内容共17

ZHOU Fei,XUE Bin,AN Kangning,GAO Jianjun

Object tracking is a hot and difficult research topic in computer vision. In this paper, we propose a object tracking algorithm based on L2 regularization least squares method and convolution network under the particle filter framework. Firstly, the extent of occlusion can be evaluated by L2 tracker. Secondly, convolutional networks is used to locate the target object if the extent of occlusion satisfies two inequality constraints. In order to make convolutional networks suitable for tracking tasks with high real-time requirements, this thesis uses a simple two-layer convolutional networks to represent the targets robustly. Finally, most of the insignificant samples are removed before applying convolutional networks, which reduces the complexity of the algorithm. The experimental results on numerous challenging image sequences show that the proposed method is more robust and stable than L2 tracker when the target object undergoes dramatic appearance changes such as pose variation or rotation and is superior in accuracy to other classical tracking algorithms.

2018-04-16

National Natural Science Foundation of China(No.61471077

Chongqing Key Laboratory of Optical Communication and Networks, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China;Chongqing Key Laboratory of Optical Communication and Networks, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China;Chongqing Key Laboratory of Optical Communication and Networks, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China;Chongqing Key Laboratory of Optical Communication and Networks, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China,,,

#Electrics, Communication and Autocontrol Technology#

0评论(0 分享(0)

Guo Qin ,Luo Mingxing ,Ma Songya ,Wang Licheng ,Yang Yixian

In this paper, we present an algorithm to construct the convolutional multicast network coding over any finite directed cyclic graph from a brand-new point. In this algorithm, we consider the dual line graph of a directed cyclic graph as a system, in which the global encoding kernels in the original graph are the corresponding inputs or outputs and the local encoding kernels in original graph are gains of channels. Then we can construct the convolutional multicast by using the classical Mason formula on the system.

2009-02-10

National Natural Science Foundation of China and the Research Grants Council of Hong Kong Joint Research(60731160626

National Basic Research Program of China&(2007CB310704

Information Security Center, State Key Laboratory of Networking and Switching Technology,Beijing University of Posts and Telecommunications;National Engineering Laboratory for Disaster Backup and Recovery,Information Security Center, State Key Laboratory of Networking and Switching Technology,Beijing University of Posts and Telecommunications;National Engineering Laboratory for Disaster Backup and Recovery,Information Security Center, State Key Laboratory of Networking and Switching Technology,Beijing University of Posts and Telecommunications;National Engineering Laboratory for Disaster Backup and Recovery,Information Security Center, State Key Laboratory of Networking and Switching Technology,Beijing University of Posts and Telecommunications;National Engineering Laboratory for Disaster Backup and Recovery,Information Security Center,

#Electrics, Communication and Autocontrol Technology#

0评论(0 分享(0)

黄天,肖波

2018-12-18

图像描述是当前人工智能研究中的热门问题,它将计算机视觉与自然语言生成联系起来,目标是实现自动生成符合图像内容的描述文本。图像描述中常常通过迁移图像识别等领域中的深度卷积网络实现图像的特征映射。本文对

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876,School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876

#计算机科学技术#

0评论(0 分享(0)

单傲,闫丹凤

2019-11-29

多变量时间序列数据在日常生活中分布广泛,并且在很多领域中得到广泛研究。但是其中仍然存在着一些挑战,比如提取时间序列内部的短期和长期依存关系、捕获序列中的多种周期模式。本文提出了聚类卷积递归神经网络来应对其中的种种问题。经过多变量时间序列聚类之后,模型分别使用卷积递归神经网络与展平卷积递归神经网络来提取不同聚类类别之间与类别内部的差异性与相似性,并且组件中同时使用注意力机制和多个卷积层来捕获序列中不同的周期性模式。本文中提出的模型在各种数据集上的效果都取得了显着改善且具有很高的实用性,所有实验结果将在稍后的论文中展示。

国家重点研发项目(2018YFC0831500

国家自然科学基金(61972047

北京邮电大学网络技术研究院,北京 100876,北京邮电大学网络技术研究院,北京 100876

#计算机科学技术#

0评论(0 分享(0)

Cheng Chuxuan,Shen Qiwei,Wang Jing

In recent years, deep learning has made outstanding achievements in image classification, recognition, segmentation and generation. And some breakthroughs have been made in the research of image inpainting based on deep learning.The existing algorithms workwell, but they cannot inference in real time.In order to realize fast and efficient image inpainting,optimization is carried out from three aspectsbased on gated convolution. Using the pyramid sample to optimize the dilated gating convolution layers and proposing a coarse-to-fine pyramid sampling network(PUNet), compared with the gating convolution network, PUNet has less computation and more parameters to learn characteristics, as well as integrating different depth characteristics. Proposing holistic,pair-wise,pixel-wise loss function to enhance the local and global consistency. Introducing knowledge distillation into image inpainting and designs a multi-level self-distillation method. Experiments show that PUNet achieves the similar performance to gated convolutional network with 22% inference time.

2020-01-17

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

#Computer Science and Technology#

0评论(0 分享(0)

范仲悦,赵志诚

2018-12-14

精准的脑部肿瘤分割是癌症诊断、治疗方案和术后措施制定的重要参考因素。尽管基于全卷积网络的深度模型在脑瘤图像分割上已经取得了巨大的成功, 但是对于形态复杂、多变的肿瘤分割依然是一个巨大的挑战。本文通过

北京邮电大学多媒体通信与模式识别实验室,北京 100876,北京邮电大学多媒体通信与模式识别实验室,北京 100876

#计算机科学技术#

0评论(0 分享(0)