检索结果-南通市图书馆

Intelligent design of multimedia content in alibaba

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2019年第12期20卷 1657-1664页

作者： Kui-long LIU Wei LI Chang-yuan YANG YANG Guang Alibaba Group Hangzhou 311121China

Multimedia content is an integral part of alibaba’s business ecosystem and is in great demand. The production of multimedia content usually requires high technology and much money. With the rapid development of artificial intelligence(AI) technology in recent years, to meet the design requirements of multimedia content, many AI auxiliary tools for the production of multimedia content have emerged and become more and more widely used in alibaba’s business ecology. Related applications include mainly auxiliary design, graphic design, video generation,and page production. In this report, a general pipeline of the AI auxiliary tools is introduced. Four representative tools applied in the Alibaba Group are presented for the applications mentioned above. The value brought by multimedia content design combined with AI technology has been well verified in business through these tools. This reflects the great role played by AI technology in promoting the production of multimedia content. The application prospects of the combination of multimedia content design and AI are also indicated.

关键词： Multimedia content alibaba Artificial intelligence Design Business application

维普期刊数据库

A robust QRS detection and accurate R-peak identification algorithm for wearable ECG sensors

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第8期64卷 213-229页

作者： Kai ZHAO Yongfu LI Guoxing WANG Yu PU Yong LIAN Department of Micro and Nano Electronics Shanghai Jiao Tong University Alibaba Group

This paper presents a robust QRS detection algorithm that is capable of detecting QRS complexes as well as accurately identifying R-peaks. The proposed bilateral threshold scheme combined with QRS watchdog greatly improves the detection accuracy and robustness, resulting in consistent detection performance on 9 available ECG databases. Simulations show that the proposed algorithm achieves good results on the datasets from both QTDB healthy database and MITDB arrhythmia database, i.e. the sensitivity of99.99% and 99.88%, the precision of 99.98% and 99.88%, and the detection error rate of 0.04% and 0.31%,respectively. Furthermore, it also outperforms many existing algorithms on six other ECG databases, such as NSTDB, TWADB, STDB, SVDB, AFTDB, and FANTASIADB.

关键词： signal processing QRS detection R-peak detection wearable ECG sensors bilateral threshold

Overfitting effect of artificial neural network based nonlinear equalizer: from mathematical origin to transmission evolution

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第6期63卷 67-79页

作者： Zheng YANG Fan GAO Songnian FU Ming TANG Deming LIU Wuhan National Laboratory for Optoelectronics School of Optical and Electronic InformationHuazhong University of Science and Technology alibaba Infrastructure Service Alibaba Group

Overfitting effect of artificial neural network(ANN) based nonlinear equalizer(NLE) leads to a trap of bit error ratio(BER) overestimation in optical fiber communication system, especially when the performance is evaluated by the commonly-used pseudo-random binary sequence(PRBS). First, we mathematically investigate the PRBS generation and Gray code mapping rules, in comparison with the use of Mersenne Twister random sequence(MTRS). Under the condition of a symbol erasure channel, we identify that ANN can recognize both the PRBS generation and symbol mapping rules, by increasing the weights of NLE at specific positions, whereas the MTRS is currently safe owing to the limited input length of current ANN based NLE. Then, we design four channel models of fiber optical transmission to experimentally examine various impairments on the evolution of overfitting effect. When both the additive white Gaussian noise(AWGN) channel and the bandwidth limited channel are considered, the mitigation of overfitting becomes possible by the use of pruned PRBS(P-PRBS) training set with removing the generation and mapping rules determined input symbols. However, as for both the chromatic dispersion(CD) uncompensated channel and the CD managed channel, the overfitting effect becomes serious, because both CD and fiber nonlinearity induced inter-symbol interference(ISI) is beneficial for ANN to identify the PRBS symbol rules. Finally,possible solutions to mitigate the overfitting effect are summarized.

关键词： artificial neural network nonlinear equalizer pseudo-random binary sequence overfitting

Quantum Contextuality for Training Neural Networks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2020年第6期29卷 1178-1184页

作者： ZHANG Junwei LI Zhao School of Computer Science and Technology Tianjin University Search Division Alibaba Group

In the training process of Neural networks(NNs),the selection of hyper-parameters is crucial,which determines the final training effect of the model.Among them,the Learning rate decay(LRD) can improve the learning speed and accuracy;the Weight decay(WD)improves the over-fitting to varying degrees.However,the decay methods still have problems such as hysteresis and stiffness of parameter adjustment,so that the final model will be inferior.Based on the Quantum contextuality(QC)theory,we propose a Quantum contextuality constraint(QCC) to constrain the weights of nodes in NNs to further improve the training effect.In the simplest classification model,we combine this constraint with different methods of LRD and WD to verify that QCC can further improve the training effect on the decay method.The performance of the experiments shows that QCC can significantly improve the convergence and accuracy of the model.

关键词： Quantum contextuality Non-classical probability constraints Training neural networks

Feature context learning for human parsing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第12期62卷 6-19页

作者： Tengteng HUANG Yongchao XU Song BAI Yongpan WANG Xiang BAI School of Electronic Information and Communications Huazhong University of Science and Technology Alibaba Group

Parsing inconsistency, referring to the scatters and speckles in the parsing results as well as imprecise contours, is a long-standing problem in human parsing. It results from the fact that the pixel-wise classification loss independently considers each pixel. To address the inconsistency issue, we propose in this paper an end-to-end trainable, highly flexible and generic module called feature context module(FCM).FCM explores the correlation of adjacent pixels and aggregates the contextual information embedded in the real topology of the human body. Therefore, the feature representations are enhanced and thus quite robust in distinguishing semantically related parts. Extensive experiments are done with three different backbone models and four benchmark datasets, suggesting that FCM can be an effective and efficient plug-in to consistently improve the performance of existing algorithms without sacrificing the inference speed too much.

关键词： human parsing context learning fully convolutional networks graph convolutional network semantic segmentation

Multi-scale cross-domain alignment for person image generation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第2期9卷 374-387页

作者： Liyuan Ma Tingwei Gao Haibin Shen Kejie Huang Department of Information Science&Electronic Engineering Zhejiang UniversityHangzhouZhejiangChina Alibaba Group HangzhouChina

Person image generation aims to generate images that maintain the original human appearance in different target poses.Recent works have revealed that the critical element in achieving this task is the alignment of appearance domain and pose domain.Previous alignment methods,such as appearance flow warping,correspondence learning and cross attention,often encounter challenges when it comes to producing fine texture details.These approaches suffer from limitations in accurately estimating appearance flows due to the lack of global receptive field.Alternatively,they can only perform cross-domain alignment on high-level feature maps with small spatial dimensions since the computational complexity increases quadratically with larger feature sizes.In this article,the significance of multi-scale alignment,in both low-level and high-level domains,for ensuring reliable cross-domain alignment of appearance and pose is demonstrated.To this end,a novel and effective method,named Multi-scale Crossdomain Alignment(MCA)is proposed.Firstly,MCA adopts global context aggregation transformer to model multi-scale interaction between pose and appearance inputs,which employs pair-wise window-based cross attention.Furthermore,leveraging the integrated global source information for each target position,MCA applies flexible flow prediction head and point correlation to effectively conduct warping and fusing for final transformed person image generation.Our proposed MCA achieves superior performance on two popular datasets than other methods,which verifies the effectiveness of our approach.

关键词： artificial intelligence image processing image reconstruction

应用于电子商务环境的商业模式挖掘和预测方法（英文）

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2015年第9期16卷 707-719页

作者： Zhou-zhou HE Zhong-fei ZHANG Chun-ming CHEN Zheng-gang WANG Department of Information Science and Electronic Engineering Zhejiang University Alibaba Group

目的:随着电子商务的发展,商品交易形式发生了翻天覆地的变化。在这种新型虚拟交易平台上,消费者快速而又广泛地浏览、购买、评价各种价廉物美的商品,而商品也同样地进行着产品创新、营销拓展、物流改善。所以,消费者和商品之间早已不... 详细信息

目的:随着电子商务的发展,商品交易形式发生了翻天覆地的变化。在这种新型虚拟交易平台上,消费者快速而又广泛地浏览、购买、评价各种价廉物美的商品,而商品也同样地进行着产品创新、营销拓展、物流改善。所以,消费者和商品之间早已不是简单的一对一直接买卖关系,而是消费者和消费者之间的社交网络,消费者和商品之间的交易网络构成电子商务中最重要的物质载体。于是,对于商品销量预测这一传统经济问题,在电子商务的大环境下有了新型的研究意义。为了能有效和深入地研究在电子商务环境下的商品销量发展模式,本文的目的在于提供一种应用于电子商务的商品销量预测算法,该算法注重于从消费者社会影响力分析入手,更好地适应真实电子商务环境中的销量预测需求。创新点:首先,本文算法不仅考虑到消费者自身的特征,同时还考虑到存在于消费者之间的社会影响力,考虑到在真实的电子商务中,消费者之间传递商品的价格信息或评价信息十分便捷,因而本文算法很好地切合了实际的应用环境。其次,本文算法定义了交易环境中的两种社会影响力,即"同一商品中消费者互相作用产生的影响力"和"不同商品之间消费者互相作用产生的影响力",分别考虑到单一商品的交易环境和多个商品互相作用的交易环境中消费者行为,其中以上两种社会影响力都是由真实消费者社交网络分析提炼得来的,使得本算法更加切合真实交易网络的内在结构。方法:本文算法将商品销量分为主体部分和噪声部分,很好地模拟了真实交易环境中,商品销量的构成是受多成分影响的。并且在预测模型中,对主体部分和噪声部分分别设置了不同的约束条件,具体为要求商品销量的主体部分在时间上应该保持平滑性,并要求商品销量的噪声部分是稀疏的,以上两个约束很好地反映了真实交易环境中商品销量的变化形式。结论:本文研究电子商务环境下商品销量的发展模式,并提出描述消费者之间关系的两种社会影响力网络。将此社会影响力网络整合入商品销量构成模型中,最后提出对这些商品销量的预测算法。特别是通过在真实的数据环境中(阿里巴巴女装数据)进行算法测试,并结合与传统销量预测算法的比较,展示在复杂数据环境下本算法的有效性。

关键词：电子商务商业模式预测消费者影响力社会网络销量预测

维普期刊数据库

DataV:Data Visualization on large high-resolution displays

在线全文

学校读者我要写书评

暂无评论

Visual Informatics 2020年第3期4卷 12-23页

作者： Honghui Mei Huihua Guan Chengye Xin Xiao Wen Wei Chen Alibaba Group China State Key Lab of CAD&CG Zhejiang UniversityChina Joint Institute of Frontier Technologies Alibaba-Zhejiang UniversityChina

In recent years,the technology and applications of visualizations on large high-resolution displays(LHDs)have received widespread attention because of its perceptual benefits and improved productivity.However,existing work on LHD visualization lacks both comprehensive guidance for design requirements and tools developed for its specific usage scenarios.In this paper,we present the scenarios,design,and implementation of DataV,a Software-as-a-Service(SaaS)visual deployment tool that enables rapid construction and cross-platform publishing of interactive visualization on LHDs.Our framework can support rich components for the high-performance rendering of multisource heterogeneous data.DataV provides a full-fledged toolchain to help the user efficiently specify layout and interactions.We present its accessibility and impressive visual effects with examples and comparison with Tableau,Power BI,VisComposer,and iVisDesigner.We also report the performance of using DataV for 3D map rendering by comparing it with deck.gl.

关键词： Information visualization Large high-resolution displays Interactive design Software-as-a-service

G6:A web-based library for graph visualization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Visual Informatics 2021年第4期5卷 49-55页

作者： Yanyan Wang Zhanning Bai Zhifeng Lin Xiaoqing Dong Yingchaojie Feng Jiacheng Pan Wei Chen Ant group China Alibaba Group China tate Key Lab of CAD&CG Zhejiang UniversityHangzhouZhejiangChina

Authoring graph visualization poses great challenges to developers due to its high requirements on both domain knowledge and development skills.Although existing libraries and tools reduce the difficulty of generating graph visualization,there are still many challenges.We work closely with developers and formulate several design goals,then design and implement G6,a web-based library for graph visualization.It combines template-based configuration for high usability and flexible customization for high expressiveness.To enhance development efficiency,G6 proposes a range of optimizations,including state management and interaction modes.We demonstrate its capabilities through an extensive gallery,a quantitative performance evaluation,and an expert interview.G6 was first released in 2017 and has been iterated for 317 versions.It has served as a web-based library for thousands of applications and received 8312 stars on GitHub.

关键词： Graph visualization Node-link diagram Web-based visualization Visualization library