检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zheng, Heqi Zhang, Xiao Chi, Zewen Huang, Heyan Yan, Tan Lan, Tian Wei, Wei Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Huazhong University of Science and Technology China

Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 English-centric language pairs. Experimental results show that XPR outperforms state-of-the-art baselines which utilize word-level or sentence-level representations. XPR also shows impressive zero-shot transferability that enables the model to perform retrieval in an unseen language pair during training. Our dataset, code, and trained models are publicly available at ***/cwszz/XPR/. © 2022, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

An Improved Dynamic NSGA-II for Unrelated Parallel Machine Rescheduling under Machine Breakdowns

An Improved Dynamic NSGA-II for Unrelated Parallel Machine R...

引用

Chinese Control and Decision Conference, CCDC

作者： XiaoLong Li Yang Liu Jiao Yu Wei Sun Department of Intelligent Data and Systems Engineering Northeastern University Shenyang China Beijing Institute of Computer Technology and Applications Beijing China Ecological Environment Bureau of Chifeng City Inner Mongolia China Business School Liaoning University Shenyang China

We consider a rescheduling problem of the unrelated parallel machines under machine breakdowns. Rescheduling is triggered whenever machine breakdowns and repairs occur (i.e., a rescheduling point arrives). At each rescheduling point, we establish a multi-objective mathematical model where the makespan is considered as an efficiency measure and stability is gauged in terms of the sum of deviation in completion times of jobs in the previous and new schedule. Then, we develop an improved dynamic NSGA-II to fast-track non-dominated solutions, where a population re-initialization strategy is used to effectively respond to machine breakdowns and repairs. Extensive experiments were conducted to demonstrate the performance of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks

arXiv

引用

arXiv 2024年

作者： Yao, Quanming Zhang, Yongqi Wang, Yaqing Yin, Nan Kwok, James Yang, Qiang Department of Electronic Engineering the Tsinghua University China Department of Data Science and Analytics Thrust the Hong Kong University of Science and Technology Guangzhou China Beijing Institute of Mathematical Sciences and Applications China Department of Computer Science and Engineering the Hong Kong University of Science and Technology Hong Kong

The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as "building blocks" to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised analysis of encrypted video traffic based on levenshtein distance 6th

Unsupervised analysis of encrypted video traffic based on le...

引用

6th International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2020

作者： Yang, Luming Zeng, Yingming Fu, Shaojing Luo, Yuchuan College of Computer National University of Defense Technology Changsha China Beijing Institute of Computer Technology and Applications Beijing China State Key Laboratory of Cryptology Beijing China

ISBN: (纸本)9789811590306

It is effective for supervisors to monitor the network by analyzing traffic from *** this way, illegal video can be detected when it is played on the network. Most Internet traffic is encrypted, which brings difficulties to traffic analysis. However, many researches suggest that even if the video traffic is encrypted, the information of video segmentation leaked by DASH (Dynamic Adaptive Streaming over HTTP) can also be used to identify the content of encrypted video traffic without decryption. Moreover, each encrypted video stream can be represented by a fragment sequence. This paper presents two methods based on Levenshtein distance for encrypted video traffic analysis. Using the distance distribution fitted by gamma distribution functions, we calculated a threshold to determine whether two encrypted video traffic belonging to the same video. The accuracy of the judgment using the threshold reached 89%, stably. As far as I am concerned, it is the first work to apply unsupervised methods for content analysis of encrypted video traffic. © Springer Nature Singapore Pte Ltd 2020.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Hashing with Semantic Concept Mining

arXiv

引用

arXiv 2022年

作者： Tu, Rong-Cheng Mao, Xian-Ling Lin, Kevin Qinghong Cai, Chengfei Qin, Weize Wang, Hongfa Wei, Wei Huang, Heyan School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China Beijing Institute of Technology Southeast Academy of Information Technology Fujian China National University of Singapore Singapore School of Computer Science Zhejiang University Zhejiang China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science Huazhong University of Science and Technology Wuhan China

Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model. However, most of these methods tend to ignore high-level abstract semantic concepts contained in images. Intuitively, concepts play an important role in calculating the similarity among images. In real-world scenarios, each image is associated with some concepts, and the similarity between two images will be larger if they share more identical concepts. Inspired by the above intuition, in this work, we propose a novel Unsupervised Hashing with Semantic Concept Mining, called UHSCM, which leverages a VLP model to construct a high-quality similarity matrix. Specifically, a set of randomly chosen concepts is first collected. Then, by employing a vision-language pretraining (VLP) model with the prompt engineering which has shown strong power in visual representation learning, the set of concepts is denoised according to the training images. Next, the proposed method UHSCM applies the VLP model with prompting again to mine the concept distribution of each image and construct a high-quality semantic similarity matrix based on the mined concept distributions. Finally, with the semantic similarity matrix as guiding information, a novel hashing loss with a modified contrastive loss based regularization item is proposed to optimize the hashing network. Extensive experiments on three benchmark datasets show that the proposed method outperforms the state-of-the-art baselines in the image retrieval task. The source codes are available 1 Copyright © 2022, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic spectrum chipless radio frequency identification:A review

引用

Digital Communications and Networks 2020年第3期6卷 377-388页

作者： Qingjuan Li Rana Sadaf Anwar Huansheng Ning Jun Wang Lingfeng Mao School of Computer and Communication Engineering University of Science and TechnologyBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Beijing Electro-Mechanical Engineering Institute Beijing100074China

Over the past few years,Radio Frequency IDentification(RFID)has stridden significantly due to its adoption in many business and daily life *** empowers end-to-end and item-by-item visibility,letting the customers or decision-makers effectively trail the personnel and resources for improved *** research and development in this area have transformed the inexpensive,miniaturized technology of RFIDs without chip *** Radio Frequency IDentification(CRFID)is a unique wireless technology based on radar principle to sense,identify,and track the *** are simplified and miniaturized tags of traditional RFID,which can widely be used in small and cheap objects/applications in our daily *** paper reviews the definition,principle,and most recent development in *** on the reported researches,the ElectroMagnetic Spectrum(EMS)method is typical,which has been concerned by many RFID ***,this paper reviews different types of EMS CRFID tag and classifies these tags based on structure design emphasizing their significant geometries in comparison with performance *** and coding methods of the EMS CRFID are also elaborated,contrasting the tag capacity and coding ***,we briefly summarize the challenges and limitations in this emerging field and look forward to the prospects of future CRFID.

关键词： CRFID Electromagnetic Tag structure Coding

来源：评论

学校读者我要写书评

暂无评论

Learning a Subspace and Clustering Simultaneously with Manifold Regularized Nonnegative Matrix Factorization

引用

Guidance, Navigation and Control 2024年第3期4卷 147-165页

作者： Feiping Nie Huimin Chen Heng Huang Chris H.Q.Ding Xuelong Li School of Computer Science Northwestern Polytechnical University Xi'an 710072 P.R.China School of Artificial Intelligence Optics and Electronics(iOPEN)Northwestern Polytechnical University Xi'an 710072 P.R.China Key Laboratory of Intelligent Interaction and Applications(Northwestern Polytechnical University)Ministry of Industry and Information Technology Xi'an 710072 P.R.China Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA 15260USA Department of Computer Science and Engineering The Chinese University of Hong Kong Shenzhen 518172 P.R.China Institute of Artificial Intelligence(TeleAI)China Telecom Corporation Limited 31 Jinrong Street Beijing 100033P.R.China

With the incredible growth of high-dimensional data such as microarray gene expression data and web blogs from internet, the researchers are desirable to develop new clustering techniques to address the critical problem created by irrelevant dimensions. Properties of Nonnegative Matrix Factorization(NMF) as a clustering method were studied by relating its formulation to other methods such as K-means clustering. In this paper, by introducing clustering indicator constraints on NMF and incorporating manifold regularization to preserve geometric structures,we propose a novel manifold regularized NMF method that can simultaneously learn subspace and do clustering. As a result, our clustering results can directly assign cluster label to data points. Extensive experimental results show that our method outperforms related other methods.

关键词： Subspace learning clustering nonnegative matrix factorization manifold learning

来源：评论

学校读者我要写书评

暂无评论

Performance Creativity Enhancement Method Based on Emotional Analysis and Concentration

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 1019-1048页

作者： Liu, Chang Zhang, Longfei Huang, Tianyu Wu, Yufeng Zhang, Fuquan Lin, Qi Department of Computer Science and Technology Beijing Institute of Technology 100081 China Beijing Key Laboratory of Digital Performance and Simulation Technology 100081 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Informatics King’s College London LondonWC2R 2LS United Kingdom

Intelligent performance creativity is a new research direction of the intersection of technology and art. At present, the cutting-edge technologies such as computer simulation, emotional computing and machine learning have been applied to the evaluation and enhancement of intelligent performance creativity. The application of these technologies has greatly increased the diversity of performance forms and the complexity of performance content. For the traditional stage performance, due to the lack of timely feedback from the audience, it is difficult for the director to enhance the creativity effec-tively. In order to solve this problem, this paper proposes concentration level enhancement method (CLEM). The CLEM extracts and analyzes the physiological and emotional characteristics of the audience by collecting the multimodal physiological signal data of the audience. Through the analysis of the features, the concentration information of the audience is obtained and the concentration level (CL) is defined. Based on the physiological and emotional induction mechanism, a performance creativity enhancement strategy is proposed, which enhances the performance creativity in two aspects: " Visual-based" and " Content-based". Through the concentration level enhancement method, compare the audience’s performance attention changes before and after the performance creativity enhancement, select the effective strategies to enhance the performance creativity, and provide the director with quantifiable performance creativity enhancement feedback results. The experimental results show that the CLEM proposed in this paper can effectively induce significant changes in the audience’s emotion, and the selected creative enhancement strategy can significantly improve the audience’s concentration and achieve the purpose of enhancing the creativity of the performance. © 2023, Journal of Network Intelligence.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

Improving neural machine translation with sentence alignment learning

引用

Neurocomputing 2021年 420卷 15-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

Neural machine translation (NMT) optimized by maximum likelihood estimation (MLE) usually lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge from bilingual sentence alignment learning. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates. The discriminator is constructed by gated self-attention based sentence encoders and trained with an N -pair loss for better capturing lexical evidences from bilingual sentence pairs. Then we propose an adversarial training framework as well as a sentence alignment-aware decoding method for NMT to transfer the discriminator’s learned semantic knowledge to NMT models. We conduct our experiments on Chinese → English, Uyghur → Chinese and English → German translation tasks. Experimental results show that our proposed methods outperform baseline NMT models on all these three translation tasks. Further analysis also indicates the characteristics of our approaches and details the semantic knowledge that transfered from the discriminator to the NMT model.

关键词： Neural machine translation Sentence alignment Adversarial training

来源：评论

学校读者我要写书评

暂无评论

(Semi) automatic Assertion Generation from Controlled Chinese Natural Language: A Practice in Aerospace Industry

(Semi) automatic Assertion Generation from Controlled Chines...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Shiyu Liu Dongfang Li Yasha Chen Guang Yang Beijing Institute of Computer Technology and Applications Beijing China Systems Engineering Institute Academy of Military Sciences Beijing China

ISBN: (纸本)9781665478373

Due to the effectiveness of assertion based verification (ABV) in programmable logic verification, and the error-proneness and time-consuming of the manual writing of assertions, the research on automatic generation of System Verilog Assertion (SVA) from English has developed rapidly in the past decade. The demand for high reliability verification in the aerospace industry urges us to explore the role of automatic assertion generation in Chinese. In this work, we proposed a controlled Chinese natural language (CCNL) framework to translate natural language assertions (NLA) into SVA. The step of capturing controlled Chinese NLAs from specification documents remains manually, which is the reason for so-called semi-automatic generation. CCNL framework consists of Chinese controlled word list, regular expression based semantic parser and assertion translator. We used this framework to extract assertions from requirements documents in Chinese, evaluated the framework, and proved its effectiveness.

关键词： Natural languages Semantics Transforms Software quality Manuals Robustness Timing

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：