检索结果-内蒙古大学图书馆

Creating knowledge and Wisdom via big data Analytics: Preface for ITQM 2017

Procedia Computer Science 2017年 122卷 1-9页

作者： Ahuja, Vandana Shi, Yong Khazanchi, Deepak Abidi, Naseem Tian, Yingjie Berg, Daniel Tien, James M. Jaypee Business School A-10 Sector-62 Noida Uttar Pradesh201 307 India School of Economics and Management University of Chinese Academy of Sciences Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha Chinese Academy of Sciences OmahaNE68182 United States College of Engineering University of Miami Coral GablesFL33124 United States

来源：评论

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

Generating Action-conditioned Prompts for Open-vocabulary Vi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Estimating Noisy Class Posterior with Part-level labels for Noisy label Learning

arXiv

引用

arXiv 2024年

作者： Zhao, Rui Shi, Bin Ruan, Jianfei Pan, Tianze Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Province Key Lab of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Physics Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Amplitudes and frequencies cross modulation of epileptic EEG between 16 leads 3

Amplitudes and frequencies cross modulation of epileptic EEG...

引用

3rd International Conference on Biological Information and Biomedical engineering, BIBE 2019

作者： Cai, Yujie Dai, Jiafei Li, Jin Wang, Jun Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Nanjing General Hospital of Nanjing Military Command Nanjing China College of Physics and Information Technology Shaanxi Normal University Xi'an China Key Laboratory of Biomedical Functional Materials China Pharmaceutical University Nanjing China

ISBN: (纸本)9783800750269

Epilepsy is caused by abnormal brain nerves. In order to analyze the similarities and differences of EEG signals between patients with epilepsy and normal people, this paper introduced a cross modulation algorithm. This paper analyzed the correlation between amplitude and frequency between EEG signals in various parts of the brain. The approach overcomes the limitation to complexity of the algorithm and found abnormalities in EEG signals of temporal lobe and occipital lobe. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Cross-Modulated Amplitudes and Frequencies of Epileptic EEG 4

Cross-Modulated Amplitudes and Frequencies of Epileptic EEG

引用

2019 4th Annual International Conference on Information System and Artificial Intelligence, ISAI 2019

作者： Cai, Yujie Dai, Jiafei Li, Jin Wang, Jun Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing210003 China Nanjing General Hospital of Nanjing Military Command Nanjing China College of Physics and Information Technology Shaanxi Normal University Xi'an China Key Laboratory of Biomedical Functional Materials China Pharmaceutical University Nanjing China

Epilepsy is a neural disorder with the hallmark of recurrent seizures. To characterize the epileptic brain electrical activities, we employed the cross modulation of instantaneous amplitudes and frequencies to separate synchronous and anti-synchronous modulation. Amplitude-amplitude, amplitude-frequency and frequency-frequency cross modulation were adopted to analyse the difference between EEG signal of epileptic patients and that of normal people. By comparing the observed patterns with two groups of EEG signals we demonstrate that the cross-modulation exponentials at the temporal region and the occipital region of right hemisphere are significant different. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Fast One-Pass Approximation for Matrix-Based Rényi's Entropy

SSRN

引用

SSRN 2024年

作者： Gong, Tieliang Dong, Yuxin Gao, Zeyu Chen, Hong Zhang, Weizhan Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China Department of Oncology University of Cambridge CambridgeCB2 1TN United Kingdom Department of Mathematics and Statistics Huazhong Agriculture University Hubei Wuhan430070 China

This paper is concerned with improving the computational efficiency of the matrix-based Rényi's α-order entropy, which enables directly being accessed from the given data without knowing the probability density function of the underlying data. However, leveraging either trace estimation or the eigenvalue-based methods will cost O(n3) in time complexity, where n is the number of observed samples. The intensive computational demands impede its utility in modern large-scale machine learning tasks. Recently, the Hutch++ based entropy approximation was developed, by converting the original entropy estimation problem into stochastic trace estimation. It reduces the time complexity to O(n2s) (s © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

arXiv

引用

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 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

CLDG: Contrastive Learning on Dynamic Graphs

CLDG: Contrastive Learning on Dynamic Graphs

引用

International Conference on data engineering

作者： Yiming Xu Bin Shi Teng Ma Bo Dong Haoyi Zhou Qinghua Zheng Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epileptic brain network analysis based on Kendall's improved synchronization algorithm 1

Epileptic brain network analysis based on Kendall's improved...

引用

1st International Conference on Physics, Mathematics and Statistics, ICPMS 2018

作者： Ding, Chuchu Sun, Ting Zou, Xin Dai, Jiafei Li, Jin Wang, Jun Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Nanjing General Hospital of Nanjing Military Command Nanjing210002 China College of Physics and Information Technology Shaanxi Normal University Xi'an China Key Laboratory of Biomedical Functional Materials China Pharmaceutical University Nanjing210009 China

In this paper, we use a new algorithm, the IRC algorithm, to improve the Kendall algorithm. Research on complex networks has gradually deepened into all areas of social science. The study of brain networks has become a hot topic in the study of brain function. The method of wavelet filtering is used to filter the EEG data to obtain the required α-band (8-16 Hz). Using the improved IRC algorithm, the brain functional network is constructed based on the EEG data, and the related characteristics of the brain network constructed are analyzed. The experimental results show that the method is suitable for distinguishing the network degree indicators of epilepsy and normal brain tissue, and further deepening the study of the neurokinetic behavior of the brain. © Published under licence by IOP Publishing Ltd.

关键词： Complex networks

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：