检索结果-内蒙古大学图书馆

Joint International Conference on Advances in data and Web Management, APWeb/WAIM 2009

作者： Xiao, Yanqin Zhang, Yansong Wang, Shan Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China MOE Beijing 100872 China School of Information Renmin University of China Beijing 100872 China Computer Center Hebei University Baoding Hebei 071002 China Department of Computer Science Harbin Finance College Harbin 150030 China

ISBN: (纸本)9783642006715

What-if analysis is an important method to analyze the hypothetical scenarios based on the historical data. It provides useful information for the decision- maker. Multiple versions are critical to what-if analysis. In this paper, we analyze the problem of multiple versions data processing and the incremental computation of cubes in what-if analysis, proposing a strategy to process multiple versions of what-if data. Our solution can adopt different data processing methods according to the type of aggregate functions, the efficiency of multiple versions data processing is improved. Furthermore, we proposes an algorithm of incremental computation of CUBE for max(min) function to reduce the access time of fact table, and the experimental results showed that the performance is improved about 10%. © Springer-Verlag Berlin Heidelberg 2009.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Source separation improves music emotion recognition 14

Source separation improves music emotion recognition

引用

2014 4th ACM International Conference on Multimedia Retrieval, ICMR 2014

作者： Xu, Jieping Li, Xirong Hao, Yun Yang, Gang Multimedia Computing Lab. School of Information Renmin University of China Beijing 100872 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing 100872 China Graduate School of Library and Information Science University of Illinois at Urbana-Champaign United States

ISBN: (纸本)1595930361

Despite the impressive progress in music emotion recognition, it remains unclear what aspect of a song, i.e., singing voice and accompanied music, carries more emotional information. As an initial attempt to answer the question, we introduce source separation into a standard music emotion recognition system. This allows us to compare systems with and without source separation, and consequently reveal the influence of singing voice and accompanied music on emotion recognition. Classification experiments on a set of 267 songs with *** annotations verify the new finding that source separation improves song music emotion recognition. Copyright is held by the owner/author(s).

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks with Learnable and Optimal Polynomial Bases

arXiv

引用

arXiv 2023年

作者： Guo, Yuhe Wei, Zhewei Gaoling School of Articial Intelligence Renmin University of China China Peng Cheng Laboratory China Beijing Key Laboratory of Big Data Management and Analysis Methods China MOE Key Lab of Data Engineering and Knowledge Engineering China

Polynomial filters, a kind of Graph Neural Networks, typically use a predetermined polynomial basis and learn the coefficients from the training data. It has been observed that the effectiveness of the model is highly dependent on the property of the polynomial basis. Consequently, two natural and fundamental questions arise: Can we learn a suitable polynomial basis from the training data? Can we determine the optimal polynomial basis for a given graph and node features? In this paper, we propose two spectral GNN models that provide positive answers to the questions posed above. First, inspired by Favard’s Theorem, we propose the FavardGNN model, which learns a polynomial basis from the space of all possible orthonormal bases. Second, we examine the supposedly unsolvable definition of optimal polynomial basis from Wang & Zhang (2022) and propose a simple model, OptBasisGNN, which computes the optimal basis for a given graph structure and graph signal. Extensive experiments are conducted to demonstrate the effectiveness of our proposed models. Our code is available at https://***/yuziGuo/FarOptBasis. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Interval valued fuzzy rough classifier and its application on privacy protection

Interval valued fuzzy rough classifier and its application o...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Su-Yun Zhao Si Lin Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China College of Science Beijing Forestry University Beijing China

Currently, most works on interval valued problems mainly focus on attribute reduction (i.e., feature selection) by using rough set technologies. However, less research work on classifier building on interval-valued problems has been conducted. It is promising to propose an approach to build classifier for interval-valued problems. In this paper, we propose a classification approach based on interval valued fuzzy rough sets. First, the concept of interval valued fuzzy granules are proposed, which is the crucial notion to build the reduction framework for the interval-valued databases. Second, the idea to keep the critical value invariant before and after reduction is selected. Third, the structure of reduction rule is completely studied by using the discernibility vector approach. After the description of rule inference system, a set of rules covering all the objects can be obtained, which is used as a rule based classifier for future classification. Finally, numerical examples are presented to illustrate feasibility and affectivity of the proposed method in the application of privacy protection.

关键词： Abstracts Diabetes Sonar Iris Accuracy

来源：评论

学校读者我要写书评

暂无评论

TREC: transient redundancy elimination-based convolution 22

TREC: transient redundancy elimination-based convolution

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jiawei Guan Feng Zhang Jiesong Liu Hsin-Hsuan Sung Ruofan Wu Xiaoyong Du Xipeng Shen Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Computer Science Department North Carolina State University

ISBN: (纸本)9781713871088

The intensive computations in convolutional neural networks (CNNs) pose challenges for resource-constrained devices; eliminating redundant computations from convolution is essential. This paper gives a principled method to detect and avoid transient redundancy, a type of redundancy existing in input data or activation maps and hence changing across inferences. By introducing a new form of convolution (TREC), this new method makes transient redundancy detection and avoidance an inherent part of the CNN architecture, and the determination of the best configurations for redundancy elimination part of CNN backward propagation. We provide a rigorous proof of the robustness and convergence of TREC-equipped CNNs. TREC removes over 96% computations and achieves 3.51× average speedups on microcontrollers with minimal (about 0.7%) accuracy loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Diagnosis of Glaucoma on Color Fundus Images Using Adaptive Mask Deep Network 1

引用

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Yang, Gang Li, Fan Ding, Dayong Wu, Jun Xu, Jie Key Lab of Data Engineering and Knowledge Engineering Beijing China School of Information Renmin University of China Beijing China Vistel Inc. Beijing China School of Electronics and Information Northwestern Polytechnical University Xi’an China Beijing Tongren Hospital Beijing China

ISBN: (数字)9783030678357

ISBN: (纸本)9783030678340

Glaucoma, a disease characterized by the progressive and irreversible defect of the visual field, requires a lifelong course of treatment once it is confirmed, which highlights the importance of glaucoma early detection. Due to the diversity of glaucoma diagnostic indicators and the diagnostic uncertainty of ophthalmologists, deep learning has been applied to glaucoma diagnosis by automatically extracting characteristics from color fundus images, and that has achieved great performance recently. In this paper, we propose a novel adaptive mask deep network to obtain effective glaucoma diagnosis on retinal fundus images, which fully utilizes the prior knowledge of ophthalmologists on glaucoma diagnosis to synthesize attention masks of color fundus images to locate a reasonable region of interest. Based on the synthesized masks, our method could pay careful attention to the effective visual representation of glaucoma. Experiments on several public and private fundus datasets illustrate that our method could focus on the significant area of glaucoma diagnosis and simultaneously achieve great performance in both academic environments and practical medical applications, which provides a useful contribution to improve the automatic diagnosis of glaucoma. © 2021, Springer Nature Switzerland AG.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Initializing convolutional filters with semantic features for text classification

Initializing convolutional filters with semantic features fo...

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Li, Shen Zhao, Zhe Liu, Tao Hu, Renfen Du, Xiaoyong Institute of Chinese Information Processing Beijing Normal University China UltraPower-BNU Joint Laboratory for Artificial Intelligence Beijing Normal University China College of Chinese Language and Culture Beijing Normal University China School of Information Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE China

ISBN: (纸本)9781945626838

Convolutional Neural Networks (CNNs) are widely used in NLP tasks. This paper presents a novel weight initialization method to improve the CNNs for text classification. Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training. Experiments demonstrate the effectiveness of the initialization technique on seven text classification tasks, including sentiment analysis and topic classification. © 2017 Association for Computational Linguistics.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Personalized Clustering via Targeted Representation Learning

arXiv

引用

arXiv 2024年

作者： Geng, Xiwen Zhao, Suyun Yu, Yixin Peng, Borui Du, Pan Chen, Hong Li, Cuiping Wang, Mengdie Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Information Renmin University of China China School of Statistics Remin University of China China

Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users’ preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available. 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

USED: Universal Speaker Extraction and Diarization

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 33卷 96-110页

作者： Ao, Junyi Yldrm, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou The Chinese Univ. Of Hong Kong Shenzhen Research Institute Of Big Data School Of Data Science Shenzhen518172 China National University Of Singapore Department Of Electrical And Computer Engineering 119077 Singapore National University Of Singapore Saw Swee Hock School Of Public Health 117549 Singapore Shenzhen Research Institute Of Big Data Shenzhen518172 China Shanghai Jiao Tong University Auditory Cognition And Computational Acoustics Lab Department Of Computer Science And Engineering MoE Key Laboratory Of Artificial Intelligence Ai Institute Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker's voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating 'who spoke when'. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about 'who spoke what and when', which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. © 2014 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Second Order Enhanced Multi-glimpse Attention in Visual Question Answering 15th

Second Order Enhanced Multi-glimpse Attention in Visual Ques...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Sun, Qiang Xie, Binghui Fu, Yanwei Academy for Engineering and Technology Fudan University Shanghai China School of Data Science and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Fudan University Shanghai China

ISBN: (纸本)9783030695378

Visual Question Answering (VQA) is formulated as predicting the answer given an image and question pair. A successful VQA model relies on the information from both visual and textual modalities. Previous endeavours of VQA are made on the good attention mechanism, and multi-modal fusion strategies. For example, most models, till date, are proposed to fuse the multi-modal features based on implicit neural network through cross-modal interactions. To better explore and exploit the information of different modalities, the idea of second order interactions of different modalities, which is prevalent in recommendation system, is re-purposed to VQA in efficiently and explicitly modeling the second order interaction on both the visual and textual features, learned in a shared embedding space. To implement this idea, we propose a novel Second Order enhanced Multi-glimpse Attention model (SOMA) where each glimpse denotes an attention map. SOMA adopts multi-glimpse attention to focus on different contents in the image. With projected the multi-glimpse outputs and question feature into a shared embedding space, an explicit second order feature is constructed to model the interaction on both the intra-modality and cross-modality of features. Furthermore, we advocate a semantic deformation method as data augmentation to generate more training examples in Visual Question Answering. Experimental results on VQA v2.0 and VQA-CP v2.0 have demonstrated the effectiveness of our method. Extensive ablation studies are studied to evaluate the components of the proposed model. © 2021, Springer Nature Switzerland AG.

关键词： Embeddings

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：