检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethink Video Retrieval Representation for Video Captioning

SSRN

引用

SSRN 2024年

作者： Tian, Mingkai Li, Guorong Qi, Yuankai Wang, Shuhui Sheng, Quan Z. Huang, Qingming School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China School of Computing Macquarie University Australia Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy of Sciences China

Video captioning, a challenging task targeting the automatic generation of accurate and comprehensive descriptions based on video content, has witnessed substantial success recently driven by bridging video representations and textual semantics. Inspired by the nature of the video retrieval task, which learns visual features strongly related to text queries, we propose to take advantage of visual representation learning from the video retrieval framework to tackle video captioning tasks. However, a simple direct application of video retrieval models performs poorly due to the weak ability to capture sufficient video details and temporal information required for video captioning. To increase the attention on details, we propose a learnable token shift module, which flexibly captures subtle movements in local regions across the temporal sequence. Furthermore, we devise a Refineformer, which learns to integrate local video tokens strongly related to desired captions via a cross-attention mechanism. Extensive experiments on MSVD, MSR-VTT and VATEX demonstrate the favorable performance of our method. © 2024, 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

Emotional Knowledge Self-Distillation in Dialogue

Emotional Knowledge Self-Distillation in Dialogue

引用

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

作者： Zhongquan Jian Yancheng Wang Weichao Wu Junfeng Yao Meihong Wang Qingqiang Wu School of Informatics Xiamen University Xiamen China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of Mechanics and Civil Engineering China University of Mining & Technology Beijing China School of Film Xiamen University Xiamen China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in Natural Language Processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) have primarily focused on contextual features, while overlooking the importance of emotional features in emotion recognition. To address this gap, we focus on the role of emotional features in ERC and propose a novel method, Emotional Knowledge Self-Distillation (EmoKSD 1 ), to enhance the model’s emotional sensitivity. In EmoKSD, utterances are enriched with implicit ⟨mask⟩ tokens to represent conveyed emotions, allowing the distillation of emotional knowledge from explicit emotional tokens to implicit ⟨mask⟩ tokens, thereby enhancing the model’s ability to perceive subtle emotions within the dialogue. Through thorough evaluations on two public ERC datasets (i.e., IEMOCAP and MELD) using proposed coarse-grained utterance distillation and fine-grained token distillation techniques, EmoKSD demonstrates superior performance compared to existing methods, highlighting the significance of emotional features in ERC.

关键词： Representation learning Human computer interaction Emotion recognition Sensitivity Speech recognition Signal processing Natural language processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

SCESP: An Edge Server Placement Method Based on Spectral Clustering in Mobile Edge computing 8th

SCESP: An Edge Server Placement Method Based on Spectral Cl...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Wang, Lijuan Guo, Yingya Yao, Jiangyuan Zhou, Siyu College of Computer and Data Science Fuzhou University Fuzhou350000 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350000 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350003 China School of Computer Science and Cyberspace Security Hainan University Haikou570228 China Tandon School of Engineering New York University New York10012 United States

ISBN: (纸本)9783031067600

With the rapid development of Internet of Things (IoT) and 5G, mobile edge computing is gaining popularity for its low computation latency, bandwidth costs and energy consumption. In mobile edge computing, the placement of edge servers is one of the most significant problems and attracts worldwide attention. However, two major problems of edge server placement: high access delay and unbalanced workload of edge servers, have not been completely solved yet. To better solve these two problems, this paper proposes a new Spectral-Clustering-based Edge Server Placement (SCESP) algorithm, which can effectively reduce the access delay and make the workload of each edge server more balanced. In the evaluation, we use the Shanghai Telecom’s base station dataset to test the performance of SCESP and extensive experiments demonstrate the superior performance of SCESP in reducing the access delay and balancing the edge server workload. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overlapping Local Community Detection Algorithm Based on Node Transitivity and Modularity Density 15th

An Overlapping Local Community Detection Algorithm Based on ...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Huang, Xintong Wu, Ling Guo, Kun College of Mathematics and Computer Sciences Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350116 China

ISBN: (纸本)9789811625398

The local community detection (LCD) method can discover the local community structure in which the seed node is located. Compared with global community detection, local community detection is characterized by its low cost and high efficiency. However, most existing LCD methods only return a non-overlapping community. Individuals in the real world may participate in multiple communities, which can only be discovered by using overlapping local community detection methods. In this study, an overlapping local community detection algorithm based on modularity and node transitivity. First, the scope and structure information of the overlapping communities are obtained according to the node transitivity. Second, NMF is used to obtain the number of overlapping communities. Finally, the local modularity density based on edge weights is used to refine the detected local communities. The experimental results validate the high performance of our method to the other method in comparison. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A Distributed Storage Middleware Based on HBase and Redis 15th

A Distributed Storage Middleware Based on HBase and Redis

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Xu, Lingling Chen, Yuzhong Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

In the era of big data, traditional relational databases face challenges in massive data storage. HBase is a non-relational database based on column storage which is used widely for big data storage. The writing performance of HBase is high, but the unbalanced load caused by its uneven data storage strategy is the bottleneck of its reading performance. HBase needs to access disks to get query results. Therefore, the efficiency of disk access has a great impact on the query performance of HBase. In view of the above problems, this paper proposes a storage middleware which utilizes HBase for load balancing and Redis for memory caching. Specifically, we improve HBase’s original load balancing algorithm for Regions and RegionServers and customize a Redis cache eviction algorithm according to the data’s query and update frequency. Furthermore, the coprocessor of HBase is used to synchronize data between HBase and Redis. Experiments on synthetic datasets show that the proposed storage middleware achieves better writing and reading performance than HBase. The load balancing algorithm employed in the middleware is better than HBase's original algorithm. The hit rate of the customized cache eviction algorithm is also higher than that of the LRU algorithm. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of KMeans Based on Unified Batch and Streaming Processing 15th

The Design and Implementation of KMeans Based on Unified Bat...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Chen, Hao Guo, Kun Chen, Yuzhong Guo, Hong College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

Clustering algorithms aim at gathering similar data points from a dataset in an unsupervised manner. Although the batch clustering algorithms have relatively high accuracy, they cannot make use of the dynamic clustering results efficiently. The requirement of using the whole dataset in calculation results in the problems of resource waste and high time cost. On the contrary, incremental clustering only needs to update the varied part of a model upon the arrival of new data, which makes it unnecessary to recluster the whole data all the time. The feature is very suitable for the streaming data process, but it decreases the accuracy of the algorithms and cannot satisfy the low latency requirement of real-time data processing. In response to this problem, the paper proposes a novel unified batch and streaming clustering model (UBSCM) based on streaming computation, which includes a streaming cluster feature updating mechanism (SCFUM). The Flink framework is used to implement a new streaming KMeans algorithm based on UBSCM (KMeansUBSP). The experiments on the real-world datasets validate that the new streaming KMeans algorithm is effective in clustering the batch and streaming data in a unified manner. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Distributed Traffic Engineering in Hybrid Software Defined Networks: A Multi-agent Reinforcement Learning Framework

arXiv

引用

arXiv 2023年

作者： Guo, Yingya Tang, Qi Ma, Yulong Tian, Han Chen, Kai The College of Computer and Data Science Fuzhou University China The Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University China The Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fujian 350003 China The Department of Computer Science & Engineering Hong Kong University of Science & Technology Hong Kong

Traffic Engineering (TE) is an efficient technique to balance network flows and thus improves the performance of a hybrid Software Defined Network (SDN). Previous TE solutions mainly leverage heuristic algorithms to centrally optimize link weight setting or traffic splitting ratios under the static traffic demand. Note that as the network scale becomes larger and network management gains more complexity, it is notably that the centralized TE methods suffer from a high computation overhead and a long reaction time to optimize routing of flows when the network traffic demand dynamically fluctuates or network failures happen. To enable adaptive and efficient routing in TE, we propose a Multi-agent Reinforcement Learning method CMRL that divides the routing optimization of a large network into multiple small-scale routing decision-making problems. To coordinate the multiple agents for achieving a global optimization goal, we construct an interactive environment for training the routing agents that own partial link utilization observations. To optimize credit assignment of multi-agent, we introduce the difference reward assignment mechanism for encouraging agents to take better action. Extensive simulations conducted on the real traffic traces demonstrate the superiority of CMRL in improving TE performance, especially when traffic demands change or network failures happen. Copyright © 2023, The Authors. All rights reserved.

关键词： Global optimization

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：