检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Cai, Jinmian Wang, Zheng Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Biren Technology IHPC A-STAR

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Real-world data is often unbalanced and exhibits long-tailed distribution over classes. Vanilla classification models trained on imbalanced datasets inherently exhibit bias towards dominant classes. Existing debiasing methods mostly balance the data or the loss during training. Nevertheless, these data-acquiring methods are not suitable for situations where training data are unavailable. In this paper, we appeal to solutions without access to training data and propose a datafree debiasing (Free-D) method that serves as a plug-and-play module for any standard classification model. Specifically, our method adjusts both the feature representation via feature representation shifting and the classifier weight via class prior compensation in a data-free manner. We evaluate and compare our methods on four long-tailed visual recognition datasets, i.e., long-tailed CIFAR-10/-100, ImageNet-LT, and Places-LT. Extensive experiments demonstrate that the proposed data-free method achieves comparable results of other data-acquired methods. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Efficiently learning significant fourier feature pairs for statistical independence testing 24

Efficiently learning significant fourier feature pairs for s...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Yixin Ren Yewei Xia Hao Zhang Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China and Machine Learning Department MBZUAI Abu Dhabi UAE SIAT Chinese Academy of Sciences Shenzhen China Department of Computer Science and Technology Tongji University Shanghai China

ISBN: (纸本)9798331314385

We propose a novel method to efficiently learn significant Fourier feature pairs for maximizing the power of Hilbert-Schmidt Independence Criterion (HSIC) based independence tests. We first reinterpret HSIC in the frequency domain, which reveals its limited discriminative power due to the inability to adapt to specific frequency-domain features under the current inflexible configuration. To remedy this shortcoming, we introduce a module of learnable Fourier features, thereby developing a new criterion. We then derive a finite sample estimate of the test power by modeling the behavior of the criterion, thus formulating an optimization objective for significant Fourier feature pairs learning. We show that this optimization objective can be computed in linear time (with respect to the sample size n), which ensures fast independence tests. We also prove the convergence property of the optimization objective and establish the consistency of the independence tests. Extensive empirical evaluation on both synthetic and real datasets validates our method's superiority in effectiveness and efficiency, particularly in handling high-dimensional data and dealing with large-scale scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Computation for the Forest Matrix of an Evolving Graph

arXiv

引用

arXiv 2024年

作者： Sun, Haoxin Zhou, Xiaotian Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

The forest matrix plays a crucial role in network science, opinion dynamics, and machine learning, offering deep insights into the structure of and dynamics on networks. In this paper, we study the problem of querying entries of the forest matrix in evolving graphs, which more accurately represent the dynamic nature of real-world networks compared to static graphs. To address the unique challenges posed by evolving graphs, we first introduce two approximation algorithms, SFQ and SFQPlus, for static graphs. SFQ employs a probabilistic interpretation of the forest matrix, while SFQPlus incorporates a novel variance reduction technique and is theoretically proven to offer enhanced accuracy. Based on these two algorithms, we further devise two dynamic algorithms centered around efficiently maintaining a list of spanning converging forests. This approach ensures O(1) runtime complexity for updates, including edge additions and deletions, as well as for querying matrix elements, and provides an unbiased estimation of forest matrix entries. Finally, through extensive experiments on various real-world networks, we demonstrate the efficiency and effectiveness of our algorithms. Particularly, our algorithms are scalable to massive graphs with more than forty million nodes. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Characterizing and Understanding Development of Social Computing Through DBLP: A Data-Driven Analysis

引用

Journal of Social Computing 2022年第4期3卷 287-302页

作者： Jiaqi Wu Bodian Ye Qingyuan Gong Atte Oksanen Cong Li Jingjing Qu Felicia F.Tian Xiang Li Yang Chen the Shanghai Key Lab of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200438China the Faculty of Social Sciences Tampere UniversityTampere 33100Finland School of Information Science and Technology Fudan UniversityShanghai 200438China Shanghai Artificial Intelligence Laboratory Shanghai 200232China. School of Social Development and Public Policy Fudan UniversityShanghai 200433China. Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous SystemsTongji UniversityShanghai 200092China.

During the past decades,the term“social computing”has become a promising interdisciplinary area in the intersection of computer science and social *** this work,we conduct a data-driven study to understand the development of social computing using the data collected from Digital Bibliography and Library Project(DBLP),a representative computer science bibliography *** have observed a series of trends in the development of social computing,including the evolution of the number of publications,popular keywords,top venues,international collaborations,and research *** findings will be helpful for researchers and practitioners working in relevant fields.

关键词： social computing Digital Bibliography and Library Project(DBLP) bibliometric evolution visualization

来源：评论

学校读者我要写书评

暂无评论

Improving Automatic Piano Transcription by Refined Feature Fusion and Weighted Loss 9th

Improving Automatic Piano Transcription by Refined Feature ...

引用

9th Conference on Sound and Music Technology, CSMT 2021

作者： Zhao, Jiahao Wu, Yulun Wen, Liang Ma, Lianhang Ruan, Linping Wang, Wantao Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China CETHIK Group Co. Ltd Hangzhou311199 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789811947025

Automatic Piano Transcription is to transcribe raw audio files into annotated piano rolls. In recent studies, jointly estimating pitch, onset, offset, and velocity of each note is commonly used. The previous state-of-the-art "Onsets and Frames" model chooses to concatenate the output of both onset and offset sub-tasks with extracted features to improve the frame-wise pitch detection, which is, however, low-efficiency in our opinion. In this paper, we proposed an improved piano transcription model by doing feature fusion and loss weighting. Our proposed model outperforms the baselines by a large margin. It also shows comparable performance with the state-of-the-art "High-Res PT" model in note metrics and outperforms it in frame metrics with an F1 score of 90.27%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Musical instruments

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based pathological analysis of liver cancer:Current advancements and interpretative strategies

引用

iLIVER 2024年第1期3卷 82-89页

作者： Guang-Yu Ding Jie-Yi Shi Xiao-Dong Wang Bo Yan Xi-Yang Liu Qiang Gao Department of Liver Surgery and Transplantation Liver Cancer InstituteZhongshan HospitalShanghai 200032China Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education Fudan UniversityShanghai 200032China School of Computer Science and Technology Xidian UniversityXi'an 710126China School of Computer Science Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghai 200433China Institute of Biomedical Sciences Fudan UniversityShanghai 200030China State Key Laboratory of Genetic Engineering Fudan UniversityShanghai 200433China

In recent years,significant advances have been achieved in liver cancer management with the development of artificial intelligence(AI).AI-based pathological analysis can extract crucial information from whole slide images to assist clinicians in all aspects from diagnosis to prognosis and molecular ***,AI techniques have a“black box”nature,which means that interpretability is of utmost importance because it is key to ensuring the reliability of the methods and building trust among clinicians for actual clinical *** this paper,we provide an overview of current technical advancements in the AI-based pathological analysis of liver cancer,and delve into the strategies used in recent studies to unravel the“black box”of AI's decision-making process.

关键词： Liver cancer Artificial intelligence Pathology Interpretative model

来源：评论

学校读者我要写书评

暂无评论

NPV: Fast Network Policy Verification for Cloud-Native Networking

NPV: Fast Network Policy Verification for Cloud-Native Netwo...

引用

International Conference on Distributed Computing Systems

作者： Shunbin Dong Yumin Xie Jin Zhao Kun Qiu School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Network policy plays a crucial role in cloud-native networking, especially in multi-tenant scenarios. It provides precise control over connectivity by specifying source and destination endpoints, traffic types, and other criteria to allow or deny traffic. However, manual configuration of these policies introduces the risk of errors, leading to isolation violations or network service unavailability. Therefore, network policy verification is essential for maintaining security and quality of service in cloud-native networking. Currently, a naïve approach involves individually checking each policy within the cluster, which can take over 100s for verification in a cluster size of over 100k. Existing verification frameworks, like Kano and Verikube, improve performance by leveraging pre-filtering and Satisfiability Modulo Theories (SMT) solvers, achieving a 3.12x to 12.99x performance boost over the naïve baseline. However, as network policy changes rapidly within 100ms in real cloud-native networks, both frameworks need over 10s to perform verification for cluster sizes over 100k, which is far from satisfying. To overcome these issues, we propose and implement a novel network policy verification framework NPV, which utilizes the policy-label pre-filter process with bitwise compression. We further enhance the policy verification algorithm with a policy-namespace divide-and-conquer strategy to improve the data-level parallelism. We implement NPV on commodity servers and evaluate its performance using real network policy datasets. Our experiments indicate that, compared with the state-of-the-art methods, NPV can achieve up to 139.00x to 651.06x improvement in verification time compared to Kano and Verikube, with 65% less memory usage.

关键词： Memory management Clustering algorithms Quality of service Manuals Parallel processing Servers Security

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Guoshan Liu Hailong Yin Bin Zhu Jingjing Chen Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Singapore Management University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset.

关键词： Training computer vision Accuracy Computational modeling Stochastic processes Predictive models Reliability Faces

来源：评论

学校读者我要写书评

暂无评论

BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method Using Kolmogorov-Arnold Networks

BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method ...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhicheng Zhang Ganghui Ru Wei Li School of Computer Science and Technology Fudan University Shanghai China School of Computer Science and Technology Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we propose an efficient and drum-attuned beat tracking method based on Kolmogorov-Arnold networks (KAN). Traditional MLP-based frameworks struggle with complex musical signals due to limited capacity in modeling intricate patterns. Inspired by KAN’s efficient ability to capture complex time-frequency relationships, we leverage it to enhance our model by employing learnable nonlinear activation functions on convolutional kernels. Additionally, we utilize music source separation techniques to extract drum tracks from the original audio, thereby expanding the existing beat datasets and simulating the human perception of beats through drum sounds. Experimental results demonstrate that our approach significantly reduces the parameter count while maintaining high accuracy in beat tracking.

关键词： Time-frequency analysis Accuracy Source separation Convolution information retrieval Acoustics Kernel Speech processing

来源：评论

学校读者我要写书评

暂无评论

Caregiving in Digital Healthcare Setting: Impacts of Data-driven Technologies to Caregivers in Practice 25

Caregiving in Digital Healthcare Setting: Impacts of Data-dr...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Wang, Bin Zhao, Jin Sun, Yuling Fudan University School of Computer Science Shanghai China Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China East China Normal University School of Computer Science and Technology Shanghai China

ISBN: (纸本)9781665405270

Using data-driven technologies to support healthcare has been largely celebrated as an effective means. Yet, most existing data-driven technologies are designed with the purposes of improving productivity, efficiency, and effectiveness etc., i.e. care administer-centric design. The needs and perceptions of caregiver, the actual users of most technologies, are largely ignored. In this paper, we examine the impacts of data-driven technologies from the perspective of caregivers. Through a questionnaire study with 191 caregivers in shanghai China, we quantify the impacts of data-driven technologies to caregivers' work and experiences. Our results show that while the embedded data-driven technologies provide significant benefits to caregivers' work, these benefits are often limited by the complex, situated and fragmented nature of healthcare. We analyze the results and propose our suggestions to the further design. © 2022 IEEE.

关键词： Health care

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：