检索结果-南通市图书馆

Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1192-1208页

作者： Zheyun Qin Xiankai Lu xiushan nie Dongfang Liu Yilong Yin Wenguan Wang the School of Software Shandong UniversityJinan 250101China the School of Computer Science and Technology Shandong Jianzhu UniversityJinan 250101China the College of Computer and Information Science Southwest UniversityChongqing 400715China the College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video *** from current discriminative tracking-by-detection solutions,our proposed hierarchical structural embedding learning can predict more highquality masks with accurate boundary details over spatio-temporal space via the normalizing *** formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and *** the video clip,our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine *** the mixing distribution,we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation *** qualitative,quantitative,and ablation experiments are performed on three representative video instance segmentation benchmarks(i.e.,YouTube-VIS19,YouTube-VIS21,and OVIS)and the effectiveness of the proposed method is *** impressively,the superior performance of our model on an unsupervised video object segmentation dataset(i.e.,DAVIS19)proves its *** algorithm implementations are publicly available at https://***/zyqin19/HEVis.

关键词： Embedding learning generative model normalizing flows video instance segmentation(VIS)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Spherical torus-based video hashing for near-duplicate video detection

引用

Science China(Information Sciences) 2016年第5期59卷 239-241页

作者： xiushan nie Yane CHAI Ju LIU Jiande SUN Yilong YIN School of Computer Science and Technology Shandong University of Finance and Economics Digital Media Technology Key Laboratory of Shandong Province Shandong University of Finance and Economics School of Information Science and Engineering Shandong University School of Computer Science and Technology Shandong University

Dear editor,With the rapid development of multimedia technologies,users can easily generate and share multiple videos through the ***,numerous illegal and useless near-duplicate videos generated through simple reformatting,transformation,and editing appear on the *** nearduplicate videos inconvenience users when they are surfing the Internet and are considered a copyright *** video hashing,which is also called video fingerprinting,does not require access to the video contents at the time of creation and can be used to detect existing *** general,

关键词：视频哈希相似视频检测时空信息球环非负矩阵分解

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Robust video hashing based on representative-dispersive frames

引用

Science China(Information Sciences) 2013年第6期56卷 216-226页

作者： nie xiushan LIU Ju SUN JianDe WANG LianQi YANG XiaoHui School of Information Science and Technology Shandong University of Finance and Economics School of Information Science and Engineering Shandong University Hisense State Key Laboratory of Digital Multi-Media Technology Department of Physics and Astronomy University of California

This study proposes a robust video hashing for video copy *** proposed method,which is based on representative-dispersive frames(R-D frames),can reveal the global and local information of a *** this method,a video is represented as a graph with frames as vertices.A similarity measure is proposed to calculate the weights between *** select R-D frames,the adjacency matrix of the generated graph is constructed,and the adjacency number of each vertex is calculated,and then some vertices that represent the R-D frames of the video are *** reveal the temporal and spatial information of the video,all R-D frames are scanned to constitute an image called video tomography image,the fourth-order cumulant of which is calculated to generate a hash sequence that can inherently describe the corresponding *** results show that the proposed video hashing is resistant to geometric attacks on frames and channel impairments on transmission.

关键词： representative-dispersive frames video hashing video tomography video copy detection

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Pre-course student performance prediction with multi-instance multi-label learning

引用

Science China(Information Sciences) 2019年第2期62卷 200-205页

作者： Yuling MA Chaoran CUI xiushan nie Gongping YANG Kashif SHAHEED Yilong YIN Software College Shandong University School of Information Engineering Shandong Yingcai College School of Computer Science and Technology Shandong University of Finance and Economics

Dear editor,Studying courses is one of the most basic and important tasks for college students. For each new course, the initial period of learning is crucial for students, and seriously influences subsequent learning activities. However, given a large number of classes in universities, it has become impossible for teachers to keep track of the individual performance of each student. In these circumstances, it is desirable to predict each student’s performance on a certain course prior to its commencement.

关键词： KNN DT Pre-course student performance prediction with multi-instance multi-label learning SVM Figure BCS

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Learned local similarity prior embedding active contour model for choroidal neovascularization segmentation in optical coherence tomography images

引用

Science China(Information Sciences) 2018年第9期61卷 319-326页

作者： Xiaoming XI Xianjing MENG Lu YANG xiushan nie Zhilou YU Chunyun ZHANG Haoyu CHEN Yilong YIN Xinjian CHEN School of Computer Science and Technology Shandong University of Finance and Economics Technology Center Inspur Group Co. Ltd. Joint Shantou International Eye Center Shantou University and The Chinese University of Hong Kong School of Computer Science and Technology Shandong University School of Electronic and Information Engineering Soochow University

Dear editor,Choroidal neovascularization(CNV)is characterized by the growth of new blood vessels in the choroid *** new blood vessels break beneath the retina and damage the surrounding reti-

关键词： CNV ACM Learned local similarity prior embedding active contour model for choroidal neovascularization segmentation in optical coherence tomography images LSP

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Difficulty-aware bi-network with spatial attention constrained graph for axillary lymph node segmentation

引用

Science China(Information Sciences) 2022年第9期65卷 74-85页

作者： Qing XU Xiaoming XI Xianjing MENG Zheyun QIN xiushan nie Yongjian WU Dongsheng ZHOU Yi QU Chenglong LI Yilong YIN School of Software Shandong University School of Computer Science and Technology Shandong Jianzhu University School of Computer Science and Technology Shandong University of Finance and Economics Shandong Provinvial Qianfoshan Hospital The First Hospital Affiliated with Shandong First Medical University Department of Geriatrics Qilu Hospital of Shandong University

Axillary lymph node(ALN) segmentation in ultrasound images is important for the diagnosis and treatment of breast cancer. Recently, deep learning methods for automatic medical image segmentation have improved significantly. However, two problems arise.(1) A unified model is often employed to segment all images without considering the difficulty diversity.(2) The relationship between elements in the learned class probability map is disregarded. To address these two issues, we propose a novel difficulty-aware binetwork with a spatial attention constrained graph. First, a difficulty grading module(DGM) is developed to learn the difficulty grade of input images. Based on the difficulty grade of images, a novel bi-network architecture is proposed to segment the image adaptively using different branches. In complex branches,a novel spatial attention module(SAM) and graph-based energy with spatial attention constraint are proposed. The learned spatial attention map can provide additional discriminative information. Moreover,the graph-based segmentation framework can capture the relationship between pixels, further improving the segmentation performance for complex images. We conducted an experiment on our ultrasound database using 216 cases. The overall dice similarity coefficient, Jaccard coefficient, volumetric overlap error, and false positive rate are 83.41%, 74.4%, 12.02%, and 13.36% for ALN segmentation, respectively. The comparison results demonstrated that the proposed method outperforms other deep learning methods.

关键词： ultrasound image axillary lymph nodes segmentation difficulty-aware segmentation graph with spatial attention

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Qos-Based Optimal Resource Allocation for Multimedia Transmission in Wireless Networks

引用

International Journal of Communications, Network and System Sciences 2017年第5期10卷 292-300页

作者： Qian Wang Yilong Yin xiushan nie School of Computer Science and Technology Shandong University of Finance and Economics Jinan China School of Computer Science and Technology Shandong University Jinan China

In this paper, aiming to improve the quality of multimedia transmission while satisfying the quality of service (QoS) requirements, we propose an optimal subcarrier allocation by jointly considering the video coding rate and the available power resource. We jointly analyses the effects on the performance of multimedia transmission from video coding rate at the application layer as well as the power control at the physical layer. This proposed joint power and subcarrier allocation algorithm in MIMO OFDM systems enables us both to overcome the challenge of full CSI (channel state information) with RD (the rate-distortion) to make minimum of the distortion of each users under delay and power constraints. Simulation results show that the proposed optimal subcarrier allocation algorithm improves the multimedia transmission quality considerably through the comparison with the resource allocation algorithms only use a single layer of information.

关键词： QoS Cross Layer Design Resource Allocation Wireless Networks

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Efficient Power Allocation for Distributed MIMO System

引用

International Journal of Communications, Network and System Sciences 2017年第5期10卷 283-291页

The rapid increasing demands of multi-media applications have busted the improvement of video transmission. By the increase of multimedia transmission, quality of experience (QoE) has become the hot topic of the wireless networks’ research. This paper proposes a QoE-aware resource allocation algorithm in MIMO-OFDM Networks. The power allocation estimation is formulated to maximize according to QoE by considering the video transmission rate and the subcarrier schemes under the constraint of minimum power. In this paper, we will analyses the the performance of video transmission from transmission rate at the application layer to the power allocation at the physical layer. From simulation results, we can see that the proposed subcarrier allocation algorithm maximizes the video QoE by minimizing the sum distortion of multi-users in MIMO networks with power constraints.

关键词： QoE Cross Layer Design Resource Allocation MIMO

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Research of Stock Price Prediction Based on PCA-LSTM Model

Research of Stock Price Prediction Based on PCA-LSTM Model

引用

作者： Yulian Wen Peiguang Lin xiushan nie School of Computer Science and Technology Shandong University of Finance and Economics

At present,there are some problems in domestic stock market,such as difficulty in extracting effective features and inaccuracy in stock price *** paper proposes a stock price prediction model based on Principal Component Analysis（PCA） and Long Short-Term Memory（LSTM）.Firstly,PCA is used to extract the principal components of the technical indicators affecting stock prices,so as to reduce the data correlation and realize data dimensionality ***,LSTM is used to model and predict the stock *** to the experimental results of Pingan Bank,compared with the traditional stock price prediction models,the stock price prediction model based on PCA and LSTM can accurately predict the stock price fluctuation trend.

关键词： Artificial Intelligence PCA LSTM Stock price prediction Deep learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

密集异构网络中基于强化学习的流量卸载算法

引用

计算机研究与发展 2018年第8期55卷 1706-1716页

作者：王倩聂秀山尹义龙山东财经大学计算机科学与技术学院济南250014 山东大学齐鲁软件学院济南250101

近年来互联网用户规模和网络流量呈现爆炸式的增长,不断逼近蜂窝移动通信网络的容量极限.流量卸载技术可充分利用现有网络,将蜂窝网络的部分流量卸载到空闲网络中,进行跨网协作实现对蜂窝网络容量的极大提升,可有效解决有限的无线带宽... 详细信息

近年来互联网用户规模和网络流量呈现爆炸式的增长,不断逼近蜂窝移动通信网络的容量极限.流量卸载技术可充分利用现有网络,将蜂窝网络的部分流量卸载到空闲网络中,进行跨网协作实现对蜂窝网络容量的极大提升,可有效解决有限的无线带宽资源与海量高速业务需求的矛盾.将强化学习的思想引入流量卸载算法中,提出了一种异构网络中基于强化学习的流量卸载算法.该算法把流量卸载问题映射为一个强化学习问题.基于前一状态完成的动作,以WiFi网络吞吐量作为回报函数,准确地预测需卸载的流量,并计算当前网络的最大卸载量,寻找最佳的WiFi网络接入点(access point,AP),并推导出最优的流量卸载判决规则,达到异构网络整体吞吐量最大化.仿真结果表明:基于Q学习的流量卸载算法可有效地实现自适应流量卸载控制规则,有效地避免过度卸载引起的碰撞冲突和系统性能急剧恶化,达到跨网协作的负载均衡点,在保证WiFi用户服务质量的条件下,最大限度地提高LTE系统吞吐量,保证密集异构网络的整体性能.

关键词：强化学习密集异构网络流量卸载吞吐量效用函数

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：