检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jin, Wei Li, Ping Shan Tan, Li School of Mathematics and Computational Science Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China School of Statistics and Data Science Jiangxi University of Finance and Economics Jiangxi Nanchang330013 China School of Mathematics and Statistics Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China

A non-complete graph is 2-distance-transitive if, for i = 1, 2 and for any two vertex pairs (u1, v1) and (u2, v2) with the same distance i in the graph, there exists an element of the graph automorphism group that maps (u1, v1) to (u2, v2). This is a generalization concept of the classical well-known distance-transitive graphs. In this paper, we completely determine the family of 2-distance-transitive Cayley graphs over the generalized quaternion groups. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task Groupings Regularization: data-Free Meta-Learning with Heterogeneous Pre-trained Models

arXiv

引用

arXiv 2024年

作者： Wei, Yongxian Hu, Zixuan Shen, Li Wang, Zhenyi Li, Yu Yuan, Chun Tao, Dacheng Tsinghua Shenzhen International Graduate School Tsinghua University China College of Computing & Data Science Nanyang Technological University Singapore School of Cyber Science and Technology Sun Yatsen University China University of Maryland College Park United States Department of Computer Science and Engineering The Chinese University of Hong Kong China

data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen tasks. Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts. In this paper, we empirically and theoretically identify and analyze the model heterogeneity in DFML. We find that model heterogeneity introduces a heterogeneity-homogeneity trade-off, where homogeneous models reduce task conflicts but also increase the overfitting risk. Balancing this trade-off is crucial for learning shared representations across tasks. Based on our findings, we propose Task Groupings Regularization that benefits from model heterogeneity by grouping and aligning conflicting tasks. Specifically, we embed pre-trained models into a task space to compute dissimilarity, and group heterogeneous models together based on this measure. Then, we introduce implicit gradient regularization within each group to mitigate potential conflicts. By encouraging a gradient direction suitable for all tasks, the meta-model captures shared representations that generalize across tasks. Comprehensive experiments showcase the superiority of our approach in multiple benchmarks, effectively tackling the model heterogeneity in challenging multi-domain and multi-architecture scenarios. Code is available here. © 2024, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining 23

From Misuse to Mastery: Enhancing Code Generation with Knowl...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

作者： Xiaoxue Ren Xinyuan Ye Dehai Zhao Zhenchang Xing Xiaohu Yang School of Software Technology Zhejiang University Hangzhou China School of Computing Australian National University Canberra Australia CSIRO's Data61 Sydney Australia CSIRO's Data61 & Australian National University Sydney Australia College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350329964

Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of good programming practice, especially in exception handling. In this paper, we first conduct an empirical study and summarize three crucial challenges of LLMs in exception handling, i.e., incomplete exception handling, incorrect exception handling and abuse of try-catch. We then try prompts with different granularities to address such challenges, finding fine-grained knowledge-driven prompts works best. Based on our empirical study, we propose a novel Knowledge-driven Prompt Chaining-based code generation approach, name Kpc, which decomposes code generation into an AI chain with iterative check-rewrite steps and chains fine-grained knowledge-driven prompts to assist LLMs in considering exception-handling specifications. We evaluate our KPC-based approach with 3,079 code generation tasks extracted from the Java official API documentation. Extensive experimental results demonstrate that the KPC-based approach has considerable potential to ameliorate the quality of code generated by LLMs. It achieves this through proficiently managing exceptions and obtaining remarkable enhancements of 109.86% and 578.57% with static evaluation methods, as well as a reduction of 18 runtime bugs in the sampled dataset with dynamic validation.

关键词： large language model

来源：评论

学校读者我要写书评

暂无评论

Split Learning without Local Weight Sharing To Enhance Client-side data Privacy

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Pham, Ngoc Duy Phan, Tran Khoa Abuadbba, Alsharif Gao, Yansong Nguyen, Van-Doan Chilamkurti, Naveen La Trobe University School of Computing Engineering and Mathematical Sciences VIC Australia CSIRO's Data61 Cybersecurity CRC Australia The University of Western Australia Department of Computer Science and Software Computing Australia

Split learning (SL) aims to protect user data privacy by distributing deep models between the client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for the local model updates. This paper first reveals data privacy leakage exacerbated by local weight sharing among the clients in SL through model inversion attacks. Then, to reduce the data privacy leakage issue, we propose and analyze privacy-enhanced SL (P-SL) (or SL without local weight sharing). We further propose a parallelized P-SL to expedite the training process by duplicating multiple server-side model instances without compromising accuracy. Finally, we explore P-SL with late participating clients and devise a server-side cache-based training method to address the forgetting phenomenon in SL when late clients join. The experiment results demonstrate that P-SL helps reduce up to 50\% of client-side data leakage, which essentially achieves a better privacy-accuracy trade-off than the current trend by using differential privacy mechanisms. Moreover, P-SL and its cache-based version achieve comparable accuracy to baseline SL under various data distributions, while incurring lower costs for computation and communication. Additionally, caching-based training in P-SL mitigates the negative effect of forgetting, stabilizes learning, and enables practical and low-complexity training in a dynamic environment with late-arriving clients. © 2004-2012 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

A Localization Method of High Energy Transients for All-sky Gamma-ray Monitor

引用

Research in Astronomy and Astrophysics 2024年第10期24卷 25-35页

作者： Yi Zhao Wangchen Xue Shaolin Xiong Qi Luo Yuanhao Wang Jiacong Liu Heng Yu Xiaoyun Zhao Yue Huang Jinyuan Liao Jianchao Sun Xiaobo Li Qibin Yi Ce Cai Shuo Xiao Shenglun Xie Chao Zheng Yanqiu Zhang Chenwei Wang Wenjun Tan Zhiwei Guo Chaoyang Li Zhenghua An Gang Chen Yanqi Du Min Gao Ke Gong Dongya Guo Jiang He Jianjian He Bing Li Gang Li Xinqiao Li Jing Liang Xiaohua Liang Yaqing Liu Xiang Ma Rui Qiao Liming Song Xinying Song Xilei Sun Jin Wang Ping Wang Xiangyang Wen Hong Wu Yanbing Xu Sheng Yang Dali Zhang Fan Zhang Hongmei Zhang Peng Zhang Shu Zhang Zhen Zhang Shijie Zheng Keke Zhang Xingbo Han Haiyan Wu Hu Tai Hao Geng Gaopeng Lu Wei Xu Fanchao Lyu Hongbo Zhang Fangjun Lu Shuangnan Zhang Department of Astronomy Beijing Normal UniversityBeijing 100875China Key Laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China University of Chinese Academy of Sciences Beijing 100049China School of Physics and Optoelectronics Xiangtan UniversityXiangtan 411105China College of Physics Hebei Normal UniversityShijiazhuang 050024China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550001China School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550001China Institute of Astrophysics Central China Normal UniversityWuhan 430079China College of physics Sciences Technology Hebei UniversityBaoding 071002China Physics and Space Science College China West Normal UniversityNanchong 637002China School of Computing and Artificial Intelligence Southwest Jiaotong UniversityChengdu 611756China College of Electronic and information Engineering Tongji UniversityShanghai 201804China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai 201304China National Space Science Center Chinese Academy of SciencesBeijing 100190China School of Earth and Space Sciences University of Science and Technology of ChinaHefei 230026China Electronic Information School Wuhan UniversityWuhan 430072China Key Laboratory of Transportation Meteorology of China Meteorological Administration Nanjing Joint Institute for Atmospheric SciencesNanjing 210000China Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China

Fast and reliable localization of high-energy transients is crucial for characterizing the burst properties and guiding the follow-up *** based on the relative counts of different detectors has been widely used for all-sky gamma-ray *** are two major methods for this count distribution localization:χ^(2)minimization method and the Bayesian *** we propose a modified Bayesian method that could take advantage of both the accuracy of the Bayesian method and the simplicity of the χ^(2)*** comprehensive simulations,we find that our Bayesian method with Poisson likelihood is generally more applicable for various bursts than the χ^(2)method,especially for weak *** further proposed a location-spectrum iteration approach based on the Bayesian inference,which could alleviate the problems caused by the spectral difference between the burst and location *** method is very suitable for scenarios with limited computation resources or timesensitive applications,such as in-flight localization software,and low-latency localization for rapidly follow-up observations.

关键词： methods:data analysis methods:analytical (stars:)gamma-ray burst:general

来源：评论

学校读者我要写书评

暂无评论

CAM-Guided Translation for Unpaired Weakly-Supervised Medical Image Segmentation

CAM-Guided Translation for Unpaired Weakly-Supervised Medica...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuebin Xie Xiaochen He Baoyao Yang Fei Lyu Siqi Liu School of Computer Science and Technology Guangdong University of Technology Guangzhou China Department of Computer Science Hong Kong Baptist University Hong Kong China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Multi-modal learning has shown advantages in improving weakly-supervised medical image segmentation (WS- MIS). However, most current works are based on paired data, which is infeasible to collect in certain scenarios. Although modal translation can be used to generate paired data, it often leads to low-quality translations, such as local deformations or irrational textures, without prior knowledge. This paper proposes a discriminative-aware image translation method, which introduces class activation maps (CAMs) to localize discriminative areas, thus overcoming the lack of pixel-wise annotations in WS-MIS. In addition, we design a CAM-correlation constraint that facilitates multi-modal complementary information exchange to enhance the consistency between CAMs generated from different modalities. Experimental results show that our method outperforms recent weakly-supervised segmentation works when using unpaired multi-modal data.

关键词： Image segmentation Deformation Annotations Supervised learning Cams Information exchange Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

BMA for the BMA: Boosting Mobility Analysis for the Bangkok Metropolitan Administration via Automated Pedestrian Counting from CCTV

BMA for the BMA: Boosting Mobility Analysis for the Bangkok ...

引用

International Symposium on Soft computing and Intelligent Systems (SCIS)

作者： Poonnaphop Kujareanpaisal Rujira Mayhasap Pin Pin Tea-makorn Pavitra Jindahra Stefano Starita Nagul Cooharojananone Kanokwan Atchariyachanvanich Department of Mathematics and Computer Science Faculty of Science Chulalongkorn University Bangkok Thailand Data Analytics Center Sasin School of Management Bangkok Thailand School of Information Technology King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

The objective of detecting and counting people using the CCTV camera on the footpath is to facilitate and reduce the time required to count the number of people traveling in pedestrian areas without having to actually visit the area. This paper uses the head detection technique to solve the problem of overlapping objects, YOLOv8n for detection and BoT-SORT for object tracking. A program was developed to assist the Bangkok Metropolitan Administration in counting the number of people within the region of interest and visualizing the statistics. Users can view statistics in the form of visual charts to compare the maximum number of people in each period by importing the video into the program. Users can also view historical statistics from previously imported videos. This program enables users to monitor pedestrian traffic in each area, providing valuable insights for urban planning decisions.

关键词： Visualization Pedestrians Head Surveillance Urban planning Transportation Cameras Personnel Object tracking Python

来源：评论

学校读者我要写书评

暂无评论

Can LVLMs Describe Videos like Humans? A Five-in-One Video Annotations Benchmark for Better Human-Machine Comparison

arXiv

引用

arXiv 2024年

作者： Hu, Shiyu Li, Xuchen Li, Xuzhao Zhang, Jing Wang, Yipei Zhao, Xin Cheong, Kang Hao School of Physical and Mathematical Sciences Nanyang Technological University Singapore Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Automation Beijing Institute of Technology China Institute of Automation Southeast University Bangladesh School of Computer and Communication Engineering University of Science and Technology Beijing China College of Computing and Data Science Nanyang Technological University Singapore

Large vision-language models (LVLMs) have made significant strides in addressing complex video tasks, sparking researchers’ interest in their human-like multimodal understanding capabilities. Video description serves as a fundamental task for evaluating video comprehension, necessitating a deep understanding of spatial and temporal dynamics, which presents challenges for both humans and machines. Thus, investigating whether LVLMs can describe videos as comprehensively as humans—through reasonable human-machine comparisons using video captioning as a proxy task—will enhance our understanding and application of these models. However, current benchmarks for video comprehension have notable limitations, including short video durations, brief annotations, and reliance on a single annotator’s perspective. These factors hinder a comprehensive assessment of LVLMs’ ability to understand complex, lengthy videos and prevent the establishment of a robust human baseline that accurately reflects human video comprehension capabilities. To address these issues, we propose a novel benchmark, FIOVA (Five In One Video Annotations), designed to evaluate the differences between LVLMs and human understanding more comprehensively. FIOVA includes 3,002 long video sequences (averaging 33.6 seconds) that cover diverse scenarios with complex spatiotemporal relationships. Each video is annotated by five distinct annotators, capturing a wide range of perspectives and resulting in captions that are 4 ∼ 15 times longer than existing benchmarks, thereby establishing a robust baseline that represents human understanding comprehensively for the first time in video description tasks. Using the FIOVA benchmark, we conducted an in-depth evaluation of six state-of-the-art LVLMs (VideoLLaMA2, LLaVA-NEXT-Video, Video-LLaVA, VideoChat2, Tarsier, and ShareGPT4Video), comparing their performance with humans. Results show that while current LVLMs demonstrate some perception and reasoning capabilities, they st

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Optimizing Potato Disease Detection in Pakistan with Machine Learning: A Comparative Analysis

Optimizing Potato Disease Detection in Pakistan with Machine...

引用

Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE), International Conference on

作者： Irfan Ahmed Manahal Khalil Safoora Ghulam Jabar Mahmood Khadija Batool Nibtal Khalid Pakiza Arshad Dept of Computer Science University of Sialkot Sialkot Pakistan State Key Laboratory of Blockchain and Data Security School of Cyber Science and Technology College of Computer Science & Technology Zhejiang University Hangzhou China Dept of Computer Science Int. Institute of Science Art & Technology Gujranwala Pakistan

ISBN: (数字)9798331504861

ISBN: (纸本)9798331504878

The agricultural sector of Pakistan depends heavily on the production of potatoes, however diseases like Bacterial Wilt, Late Blight, and Early Blight are posing a growing danger to this industry since they can negatively affect crop productivity and food security. Detecting these illnesses using traditional methods is time-consuming, labor-intensive, and sometimes it requires specialized knowledge which is not easy for farmers. The implementation of a machine learning (ML) framework for illness identification using the methods of K-Nearest Neighbours (KNN), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), Support Vector Machine (SVM), and Logistic Regression (LR) overcomes these challenges. This study utilizes data mining and preprocessing strategies to improve the accuracy of models and adaptability on a dataset of potato plants’ photos gathered across diverse areas in Pakistan. The models are assessed using performance criteria such computational efficiency, accuracy, precision, recall and F1-score. Random Forest model having 97% accuracy outperforms the other ML models in identifying plant disease. The suggested approach provides a practical, affordable, and effective way to identify diseases in a timely manner, allowing farmers to make informed decisions to lower crop losses. The aim of the study is to highlight how ML has the potential to transform Pakistani agriculture, enhancing food security and promoting long-term economic prosperity.

关键词： Support vector machines Productivity Adaptation models Accuracy Biological system modeling Computational modeling Crops Food security Random forests Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Market Size Estimation Model at the Product Level based on Text Mining Approach

Market Size Estimation Model at the Product Level based on T...

引用

IEEE International Conference on Big data

作者： Ye Lim Jung Hyoung Sun Yoo Ji Hui Kim Technology Commercialization Research Center Korea Institute of Science and Technology Information (KISTI) Seoul Republic of Korea Data and High Performance Computing Science University of Science and Technology Daejeon Republic of Korea Science and Technology Management Policy University of Science and Technology Daejeon Republic of Korea

Information on market size is fundamental for marketing and business decision-making. However, market size information is mostly available at the level of industry or broad categories, which include a large number of product groups. Since many companies require market size information at the segmented product level, especially for their own products, a methodology to estimate market size by specified product group (i.e., item) is required. This study proposes a market size estimation model based on the measurement of string similarity between product names. The market size of the target items is estimated by calculating the sales of individual products matched to the target item according to the measured string similarity. We tested the model by estimating the market size of 1,417 items from 165,056 individual enterprises’ product sales data. Eight types of string similarity measuring algorithms were applied, and among them, Cosine, Jaccard, and Jaro-Winkler algorithms showed the highest accuracy in matching the individual product names to the target item names. The market sizes estimated from the model showed a high correlation (Pearson correlation coefficient of 0.93) with those officially surveyed. Our approach can be utilized for intelligent market information systems to dynamically estimate market sizes requested by information users for diverse target products without pre-labeling or predetermined taxonomy on the products.

关键词：

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：