检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Tang, Huadong Zhao, Youpeng Jiang, Yingying Gan, Zhuoxin Wu, Qiang University of Technology Sydney School of Electrical and Data Engineering Australia China University of Central Florida Department of Computer Science United States

ISBN: (纸本)9781728163277

Exploring spatial contextual information is a well-adopted approach to achieving better semantic segmentation performance. However, most existing methods neglect the class association between the neighboring pixels. In this paper, we propose a CACINet, which consists of a Semantic Affinity Module (SAM) and a Class Association Module (CAM), to generate class-aware contextual information among pixels on a fine-grained level. SAM analyzes the affiliation of any two given pixels belonging to the same or different class. It produces intra-class and inter-class pixel contextual information. CAM classifies the image into different class regions globally and then it encodes the pixel based on the degree of affiliation of the pixels with each class in the image. In this way, it augments the class affiliation of the pixels into the corresponding context calculation. Comprehensive experiments demonstrate that the proposed method achieves competitive performance on two semantic segmentation benchmarks: ADE20K and PASCAL-Context. © 2023 IEEE.

关键词： class-aware contextual information semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

MeHyper: Accelerating Hypergraph Neural Networks by Exploring Implicit dataflows 31

MeHyper: Accelerating Hypergraph Neural Networks by Explorin...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhao, Wenju Yao, Pengcheng Chen, Dan Zheng, Long Liao, Xiaofei Wang, Qinggang Ma, Shaobo Li, Yu Liu, Haifeng Xiao, Wenjing Sun, Yufei Zhu, Bing Jin, Hai Xue, Jingling Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore Guangxi University School of Computer Electronics and Information NanNing530004 China University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

ISBN: (纸本)9798331506476

Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation tasks for hyperedges and vertices, leading to significant computational redundancy. This redundancy arises from recalculating shared information across different tasks. For the first time, we identify and harness implicit dataflows (i.e., dependencies) within HGNNs, introducing the microedge concept to effectively capture and reuse intricate shared information among aggregation tasks, thereby minimizing redundant computations. We have developed a new microedge-centric dataflow model that processes shared information as fine-grained microedge aggregation tasks. This dataflow model is supported by the Read-Process-Activate-Generate execution model, which aims to optimize parallelism among these tasks. Furthermore, our newly developed MeHyper, a microedge-centric HGNN accelerator, incorporates a decoupled pipeline for improved computational parallelism and a hierarchical feature management strategy to reduce off-chip memory accesses for large volumes of intermediate feature vectors generated. Our evaluation demonstrates that MeHyper substantially outperforms the leading CPUbased system PyG-CPU and the GPU-based system HyperGef, delivering performance improvements of 1,032.23 × and 10.51 ×, and energy efficiencies of 1,169.03 × and 9.96 ×, respectively. © 2025 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Improving Entity Linking in Chinese Domain by Sense Embedding Based on Graph Clustering

引用

Journal of computer science & Technology 2023年第1期38卷 196-210页

作者：张照博钟芷漫袁平鹏金海 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Service Computing Technology and System Laboratory Huazhong University of Science and Technology Wuhan 430074China Cluster and Grid Computing Laboratory Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China

Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity *** is of great significance to some NLP(natural language processing)tasks,such as question *** English entity linking,Chinese entity linking requires more consideration due to the lack of spacing and capitalization in text sequences and the ambiguity of characters and words,which is more evident in certain *** Chinese domains,such as industry,the generated candidate entities are usually composed of long strings and are heavily *** addition,the meanings of the words that make up industrial entities are sometimes *** semantic space is a subspace of the general word embedding space,and thus each entity word needs to get its exact ***,we propose two schemes to achieve better Chinese entity ***,we implement an ngram based candidate entity generation method to increase the recall rate and reduce the nesting ***,we enhance the corresponding candidate entity ranking mechanism by introducing sense *** the contradiction between the ambiguity of word vectors and the single sense of the industrial domain,we design a sense embedding model based on graph clustering,which adopts an unsupervised approach for word sense induction and learns sense representation in conjunction with *** test the embedding quality of our approach on classical datasets and demonstrate its disambiguation ability in general *** confirm that our method can better learn candidate entities’fundamental laws in the industrial domain and achieve better performance on entity linking through experiments.

关键词： natural language processing(NLP) domain entity linking computational linguistics word sense disambiguation knowledge graph

来源：评论

学校读者我要写书评

暂无评论

An API Field Design Method Based on Pre-trained Model 14

An API Field Design Method Based on Pre-trained Model

引用

14th International Conference on Software Technology and engineering, ICSTE 2024

作者： Wang, Hai Lou, Yihua Yang, Yi Xu, Ranbin Yang, Jingbo Liao, Xingchuang Center of Civil Aviation Big Data TravelSky Technology Limited Beijing Engineering Research Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China

ISBN: (纸本)9798350378955

Application programming interface (API) plays an important role in modern software development, a well designed API can provide tremendous convenience for developers. However, designing an excellent API is not a trivial task, each field in the API should avoid any ambiguity. Besides, in some special cases, for instance, a Chinese developer might not accurately translate the meaning of a Chinese API field into its English counterpart. Therefore, there exists a tremendous requirement in designing high quality API field. In this paper, a fine-tuning pre-trained model based method is proposed for API field design task. Firstly, we consider the design of API fields as a translation task, converting the fields from another language into English. Secondly, we fine-tune a pre-trained model for API field design task. In the end, we curate two datasets to illustrate our method and the experiment results demonstrate that our method has a better performance in designing API field. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

The Evolution of Zero Trust Architecture (ZTA) from Concept to Implementation 29

The Evolution of Zero Trust Architecture (ZTA) from Concept ...

引用

29th International Conference on Information Technology, IT 2025

作者： Nasiruzzaman, Md Ali, Maaruf Salam, Iftekhar Miraz, Mahdi H. Xiamen University Malaysia School of Computing and Data Science Malaysia Universiteti Metropolitan Tirana Faculty of Computer Science and IT Albania The Doctoral College United Kingdom Xiamen University Malaysia Mahdi H. Miraz Is with the School of Computing and Data Science Malaysia Wrexham University School of Computing Faculty of Arts Science and Technology United Kingdom University of South Wales Faculty of Computing Engineering and Science United Kingdom

ISBN: (纸本)9798331517649

Zero Trust Architecture (ZTA) is one of the paradigm changes in cybersecurity, from the traditional perimeter-based model to perimeterless. This article studies the core concepts of ZTA, its beginning, a few use cases and future trends. Emphasising the always-verify and least privilege access, some key tenets of ZTA have grown to be integration technologies like Identity Management, Multi-Factor Authentication (MFA) and real-time analytics. ZTA is expected to strengthen cloud environments, education, work environments (including from home) while controlling other risks like lateral movement and insider threats. Despite ZTA's benefits, it comes with challenges in the form of complexity, performance overhead and vulnerabilities in the control plane. These require phased implementation and continuous refinement to keep up with evolving organisational needs and threat landscapes. Emerging technologies, such as Artificial Intelligence (AI) and Machine Learning (ML) will further automate policy enforcement and threat detection in keeping up with dynamic cyber threats. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetic Foot Ulcer Detection and Classification using ConvMixer Model 5

Diabetic Foot Ulcer Detection and Classification using ConvM...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Anusha, N. Vidhya, R. Jani Anbarasi, L. Dhanya, D. Pushparani, S. Mohan, Geetha Vellore Institute of Technology School of Computer Science and Engineering Department of IoT Vellore Campus Vellore India Agni College of Technology Department of Information Technology Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India Mar Ephraem College of Engineering and Technology Department of Artificial Intelligence and Data Science Elavuvilai India Meenakshi College of Engineering Department of Cse Chennai India Institute of Applied Technology Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331504403

Diabetic foot ulcer (DFUs) are a common and significant consequence of diabetes, frequently resulting in severe illness and amputations if not promptly identified and treated. The growing occurrence of DFUs is a substantial obstacle to healthcare globally. Precise and prompt categorization of DFUs is essential for efficient treatment and avoidance of consequences. This research analyzed ConvMixer model for comprehensive classification designed to accurately evaluate DFU. The DFU images are preprocessed using the watershed algorithm that helps in separating different regions of an image, such as the ulcer and surrounding tissues, to improve the neural network's ability to extract high-quality information. The framework utilizes depthwise and pointwise convolutions to mix spatial and channel-wise information in an efficient manner to effectively extract pertinent information from various clinical DFU dataset. The proposed work features a multi-layered depthwise and pointwise convolutional architecture, created especially to manage the complex patterns and variances found in various diabetic foot ulcer stages and variants (DFUs). By integrating these convolutions and skip associations, the network facilitates hierarchical extraction of features and robust representation of features. Experimental results on a substantial and varied DFU dataset demonstrate that the ConvMixer model achieves an impressive accuracy rate of 97.16%, with a precision, F1-score and a sensitivity of 97%, 97% and 99.08% respectively. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification 24

Category-Prompt Refined Feature Learning for Long-Tailed Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yan, Jiexuan Huang, Sheng Mu, Nankun Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798400706868

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image Classification (LTMLC). In such contexts, imbalanced data distribution and multi-object recognition pose significant hurdles. To address this issue, we propose a novel and effective approach for LTMLC, termed Category-Prompt Refined Feature Learning (CPRFL), utilizing semantic correlations between different categories and decoupling category-specific visual representations for each category. Specifically, CPRFL initializes category-prompts from the pretrained CLIP's embeddings and decouples category-specific visual representations through interaction with visual features, thereby facilitating the establishment of semantic correlations between the head and tail classes. To mitigate the visual-semantic domain bias, we design a progressive Dual-Path Back-Propagation mechanism to refine the prompts by progressively incorporating context-related visual information into prompts. Simultaneously, the refinement process facilitates the progressive purification of the category-specific visual representations under the guidance of the refined prompts. Furthermore, taking into account the negative-positive sample imbalance, we adopt the Asymmetric Loss as our optimization objective to suppress negative samples across all classes and potentially enhance the head-to-tail recognition performance. We validate the effectiveness of our method on two LTMLC benchmarks and extensive experiments demonstrate the superiority of our work over *** code is available at https://***/jiexuanyan/CPRFL. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Path-KGE: Preference-Aware Knowledge Graph Embedding with Path Semantics for Link Prediction 1

引用

24th International Conference on Web Information Systems engineering, WISE 2023

作者： Yang, Liu Zhao, Jie Long, Jun Huang, Jincai Wang, Zidong Chen, Tingxuan School of Computer Science and Engineering Central South University Changsha China Big Data Institute Central South University Changsha China

ISBN: (数字)9789819972548

ISBN: (纸本)9789819972531

Knowledge graph embedding (KGE) aims to transfer entities and relations into low-dimensional vector space while preserving underlying semantics in knowledge graph (KG). Some existing models directly learn embeddings based on original triples, while others integrate external information to enhance the limited semantic information in KG. However, most of them ignore latent user preferences in their interactions with real-world KG applications, not even considering the relational semantics implied in historical interaction data, which are practical and essential for many downstream tasks like link prediction. To address these issues, we propose a novel preference-aware knowledge graph embedding with path semantics model Path-KGE, which learns semantic information of relation paths and integrates it into embedding process. First, we mine multi-hop relations with frequent and temporal characteristics as semantic relation paths in user interaction data, to obtain implicit user preference features. Second, we design a path importance function to distinguish the semantic impacts of user preferences on distinct relation paths. Finally, we utilize weight scores as long-term constraints to learn preference-aware embeddings, so that the representation vectors of entity pairs connected by preferred relation paths can remain close distances in vector space as in reality. The experimental results show that our model outperforms state-of-the-art translation-based models on link prediction and triple classification tasks. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient distributed algorithms for holistic aggregation functions on random regular graphs

引用

science China(Information sciences) 2022年第5期65卷 32-50页

作者： Lin JIA Qiang-Sheng HUA Haoqiang FAN Qiuping WANG Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology Institute for Interdisciplinary Information Science Tsinghua University

In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic aggregation functions include SELECTION（select the k-th largest or smallest element）,DISTINCT（query the count of distinct elements）, MODE（query the most frequent element）. We design three basic techniques — Pre-order Network Partition, Pairwise-independent Random Walk, and Random Permutation Delivery, and devise the algorithms based on the techniques. The round complexity of the distributed SELECTION is Θ（log N） which meets the lower bound where N is the number of nodes and each node holds a numeric element. The round complexity of the distributed DISTINCT and MODE algorithms are O（log3N/log log N） and O（log2N log log N） respectively. All of our results break the lower bounds obtained on general graphs and our distributed algorithms are all based on the CON GE S T model, which restricts each node to send only O（log N） bits on each edge in one round under synchronous communications.

关键词： distributed algorithms holistic aggregation function random regular graph $\mathcal{CONGEST}$ model communication complexity round complexity

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：