检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Pan, Guandong Wu, Zhaobang Yang, Yaqian Wang, Xin Liu, Longzhao Zheng, Zhiming Tang, Shaoting School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Key laboratory of Mathematics Informatics and Behavioral Semantics Beihang University Beijing100191 China Institute of Medical Artificial Intelligence Binzhou Medical University Yantai264003 China Zhongguancun Laboratory Beijing100094 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing100191 China PengCheng Laboratory Shenzhen518055 China State Key Lab of Software Development Environment Beihang University Beijing100191 China

The need for automatic and high-quality emotion annotation is paramount in applications such as continuous emotion recognition and video highlight detection, yet achieving this through manual human annotations is challenging. Inspired by inter-subject correlation (ISC) utilized in neuroscience, this study introduces a novel Electroencephalography (EEG) based ISC methodology that leverages a single-electrode and feature-based dynamic approach. Our contributions are three folds: Firstly, we reidentify two potent emotion features suitable for classifying emotions—first-order difference (FD) an differential entropy (DE). Secondly, through the use of overall correlation analysis, we demonstrate the heterogeneous synchronized performance of electrodes. This performance aligns with neural emotion patterns established in prior studies, thus validating the effectiveness of our approach. Thirdly, by employing a sliding window correlation technique, we showcase the significant consistency of dynamic ISCs across various features or key electrodes in each analyzed film clip. Our findings indicate the method’s reliability in capturing consistent, dynamic shared neural synchrony among individuals, triggered by evocative film stimuli. This underscores the potential of our approach to serve as an indicator of continuous human emotion arousal. The implications of this research are significant for advancements in affective computing and the broader neuroscience field, suggesting a streamlined and effective tool for emotion analysis in real-world applications. © 2025, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Joint lifelong topic model and manifold ranking for document summarization

arXiv

引用

arXiv 2019年

作者： Lin, J Ianying Liu, Rui Ia, Quanye J. State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

Due to the manifold ranking method has a significant effect on the ranking of unknown data based on known data by using a weighted network, many researchers use the man- ifold ranking method to solve the document summarization task. However, their models only consider the original features but ignore the semantic features of sentences when they construct the weighted networks for the manifold ranking method. To solve this problem, we proposed two improved models based on the manifold ranking method. One is com- bining the topic model and manifold ranking method (JTMMR) to solve the document summarization task. This model not only uses the original feature, but also uses the se- mantic feature to represent the document, which can improve the accuracy of the manifold ranking method. The other one is combining the lifelong topic model and manifold rank- ing method (JLTMMR). On the basis of the JTMMR, this model adds the constraint of knowledge to improve the quality of the topic. At the same time, we also add the constraint of the relationship between documents to dig out a better document semantic features. The JTMMR model can improve the effect of the manifold ranking method by using the better semantic feature. Experiments show that our models can achieve a better result than other baseline models for multi-document summarization task. At the same time, our models also have a good performance on the single document summarization task. After combining with a few basic surface features, our model significantly outperforms some model based on deep learning in recent years. After that, we also do an exploring work for lifelong machine learning by analyzing the effect of adding feedback. Experiments show that the effect of adding feedback to our model is significant. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LSTM Based Semi-Supervised Attention Framework for Sentiment Analysis

LSTM Based Semi-Supervised Attention Framework for Sentiment...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Hanxue Ji Wenge Rong Jingshuang Liu Yuanxin Ouyang Zhang Xiong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9781728140346

ISBN: (纸本)9781728140353

With the rapid development of Internet technology and social media, people are accustomed to making comments on the Internet. Sentiment analysis, as an efficient technique, has been used by researchers in the tasks of analysing the sentiment polarity under these comments. To better achieve this target, the fundamental challenge is how to extract the feature and build a proper mechanism to learn them. A lot of word embedding based deep learning models for sentiment analysis are proposed in the literature. And the semi-supervised learning methods make it possible to use both lab.lled and unlab.lled data for this kind of task. Furthermore, the attention mechanism proposed in recent years has achieved great accomplishments for natural language processing (NLP) tasks since it helps to capture the important information of the documents. In this paper, inspired by these works, we proposed a long short term memory (LSTM) based semi-supervised attention framework for sentiment analysis tasks, which is composed of an unsupervised attention based LSTM encoder-decoder and an attention based supervised LSTM model attached by a Softmax layer. The unsupervised part worked for attaining the high dimensional representation of the documents, and the supervised part extracted feature and enhanced the important parts for classification. Experimental study on commonly used datasets has demonstrated its ability for sentiment analysis tasks.

关键词： Task analysis Decoding Sentiment analysis Feature extraction Unsupervised learning Encoding Logic gates

来源：评论

学校读者我要写书评

暂无评论

A cooperative scheduling framework for shared transportation services 19

A cooperative scheduling framework for shared transportation...

引用

19th COTA International Conference of Transportation Professionals: Transportation in China - Connecting the World, CICTP 2019

作者： Wang, Xinli Qiao, Yanan Wang, Tianyu Guo, Jifu Zhou, Xuesong Xian, Kai Tong, Lu Carol Xie, Jindong Natl. Eng. Lab. for Compreh. Transp. Big Data Applic. Technol. Sch. of Transp. Sci. and Engineering Beihang Univ. Beijing100191 China State Key Lab of Software Development Environment School of Computer Science and Engineering Beihang Univ. Beijing100191 China Beijing Transport Institute No. 9 LiuLiQiao South Lane Fengtai District China

ISBN: (数字)9780784482292

ISBN: (纸本)9780784482292

To improve the efficiency of metropolitan shared transportation services (STS), this paper proposes a cooperative scheduling framework to avoid congestion. Two procedures are considered: shared path scheduling and congestion solving. In a known static traffic network, classic vehicle routing problem (VRP) solutions may obtain an optimal path. But with an increasing number of shared transportation services required, congestion is likely, triggered by open loop VRP scheduling, especially when shared vehicles overwhelm private ones. Dynamic traffic assignment (DTA) solutions could be employed for short-term traffic situation prediction. However, VRP and DTA cannot be combined linearly, due to uncontrolled recursive calls of routing procedures within VRP and DTA. Hence, a software structure is further studied to guarantee convergence of the cooperative framework. Using two open-source transportation packages, VRPLite and DTALite, we test our framework with the Western 3rd Ring Road of the Beijing regional network. Results verify the framework's usability and flexibility. © ASCE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Learning with noisy lab.ls for sentence-level sentiment classification

arXiv

引用

arXiv 2019年

作者： Wang, Hao Liu, Bing Li, Chaozhuo Yang, Yan Li, Tianrui School of Information Science and Technology Southwest Jiaotong University Department of Computer Science University of Illinois at Chicago State Key Lab of Software Development Environment Beihang University

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy lab.ls and tested on data with clean lab.ls, the model may perform poorly. This paper studies the problem of learning with noisy lab.ls for sentence-level sentiment classification. We propose a novel DNN model called NETAB (as shorthand for convolutional neural NETworks with AB-networks) to handle noisy lab.ls during training. NETAB consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy lab.ls and the other for predicting 'clean' lab.ls. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A split-and-recombine approach for follow-up query analysis

arXiv

引用

arXiv 2019年

作者： Liu, Qian Chen, Bei Liu, Haoyan Lou, Jian-Guang Fang, Lei Zhou, Bin Zhang, Dongmei State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China State Key Lab of Software Development Environment Beihang University China Microsoft Research Beijing China

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information. To accomplish the task, we propose STAR, a novel approach with a well-designed two-phase process. It is parser-independent and able to handle multifarious follow-up scenarios in different domains. Experiments on the FollowUp dataset show that STAR outperforms the state-of-the-art baseline by a large margin of nearly 8%. The superiority on parsing results verifies the feasibility of follow-up query analysis. We also explore the extensibility of STAR on the SQA dataset, which is very promising. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Personalized group of readers' emotion traits modeling based on sentimental analysis of novels

Personalized group of readers' emotion traits modeling based...

引用

IEEE International Conference on Cognitive Informatics

作者： Yuya Hatakeyama Runhe Huang Bowen Du Neil Yen Haiquan Wang Graduate School of C.I.S Hosei University Japan State Key Lab of Software Development Environment Beihang University China School of Computer Science and Engineering University of Aizu Japan College of Software Beihang University China

ISBN: (数字)9781728114194

ISBN: (纸本)9781728104966

Studies concerning sentiment analysis haven drawn attentions from a wide spectrum of researchers in the past few years. One of the most eye-catching topics within this emerging field is how emotion can be dectected and extracted properly from the given contexts. This study chooses content from novel to stimulate above mentioned long contexts, and expects analysis results can be projected to a three-dimensions space model. Two major tasks are conducted. First, specific content selected from novel is proceeded through morpheme analysis to estimate emotion status. Second, obtained emotion status is calculated through existing emotion dictionary which was built based on data from the novel. Results are then demonstrated on the three-dimensions space model. At last, two experiments, a systematic way to compare emotion status and an empirical questionnaire, are conducted to verify the performance of proposed method.

关键词： Dictionaries Analytical models Estimation Mathematical model Computational modeling software Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

DPA-2: a large atomic model as a multi-task learner

arXiv

引用

arXiv 2023年

作者： Zhang, Duo Liu, Xinzijian Zhang, Xiangyu Zhang, Chengqian Cai, Chun Bi, Hangrui Du, Yiming Qin, Xuejian Peng, Anyang Huang, Jiameng Li, Bowen Shan, Yifan Zeng, Jinzhe Zhang, Yuzhi Liu, Siyuan Li, Yifan Chang, Junhan Wang, Xinyan Zhou, Shuo Liu, Jianchuan Luo, Xiaoshan Wang, Zhenyu Jiang, Wanrun Wu, Jing Yang, Yudi Yang, Jiyuan Yang, Manyi Gong, Fu-Qiang Zhang, Linshuang Shi, Mengchao Dai, Fu-Zhi York, Darrin M. Liu, Shi Zhu, Tong Zhong, Zhicheng Lv, Jian Cheng, Jun Jia, Weile Chen, Mohan Ke, Guolin Weinan, E. Zhang, Linfeng Wang, Han AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China CAS Key Laboratory of Magnetic Materials and Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of Sciences Ningbo315201 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development School of Chemistry and Molecular Engineering East China Normal University Shanghai200062 China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States Department of Chemistry Princeton University PrincetonNJ08540 United States College of Chemistry and Molecular Engineering Peking University Beijing100871 China Yuanpei College Peking University Beijing100871 China School of Electrical Engineering and Electronic Information Xihua University Chengdu610039 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China Key Laboratory of Material Simulation Methods & Software of Ministry of Education College of Physics Jilin University Changchun130012 China International Center of Future Science Jilin University Changchun130012 China Key Laboratory for Quantum Materials of Zhejiang Province Department of Physics School of Science Westlake University Zhejiang Hangzhou310030 China Atomistic Simulations Italia

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Front Cover: AuNP-Modulated qPCR: An Optimized System for Detecting MIR Biophotons Released in DNA Replication (Chem. Eur. J. 8/2023)

引用

Chemistry – A European Journal 2023年第8期29卷

作者： Yu Yang Prof. Dr. Daoling Peng Prof. Dr. Zhenglong Gu Prof. Dr. Lei Jiang Prof. Dr. Bo Song State Key Laboratory of Genetic Engineering Collaborative Innovation Center of Genetics and Development School of Life Sciences Fudan University 200438 Shanghai P. R. China Key Laboratory of Theoretical Chemistry of Environment Ministry of Education School of Environment South China Normal University 510006 Guangzhou P. R. China Key Laboratory of Optical Technology and Instrument for Medicine Ministry of Education Shanghai Key Lab of Modern Optical System School of Optical-Electrical Computer Engineering University of Shanghai for Science and Technology 200093 Shanghai P. R. China Key Laboratory of Bio-inspired Materials and Interfacial Science Technical Institute of Physics and Chemistry Chinese Academy of Sciences 100190 Beijing P. R. China School of Future Technology University of Chinese Academy of Sciences 100049 Beijing P. R. China

来源：评论

学校读者我要写书评

暂无评论

Adaptive unimodal cost volume filtering for deep stereo matching

arXiv

引用

arXiv 2019年

作者： Zhang, Youmin Chen, Yimin Bai, Xiao Yu, Suihanjin Yu, Kun Li, Zhiwei Yang, Kuiyuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China DeepMotion

state-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained. In this paper, we propose to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities. In addition, variances of the unimodal distributions for each pixel are estimated to explicitly model matching uncertainty under different contexts. The proposed architecture achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks. In particular, our method ranked the 1st place of KITTI 2012 evaluation and the 4th place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are availab.e at: https://***/DeepMotionAIResearch/ DenseMatchingBenchmark. Copyright © 2019, The Authors. All rights reserved.

关键词： Uncertainty analysis

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：