检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongtuo Liu Dan Xu Sucheng Ren Hanjie Wu Hongmin Cai Shengfeng He School of Computer Science South China University of Technology Institute of Informatics University of Amsterdam Department of Computer Science and Engineering Hong Kong University of Science and Technology School of Computing and Information Systems Singapore Management University

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a weakly-supervised manner. Based on the derived segmentation, we design a crowd-aware domain adaptation mechanism consisting of two crowd-aware adaptation modules, i.e., Crowd Region Transfer (CRT) and Crowd Density Alignment (CDA). The CRT module is designed to guide crowd features transfer across domains beyond background distractions. The CDA module dedicates to regularising target-domain crowd density generation by its own crowd density distribution. Our method outperforms previous approaches consistently in the widely-used adaptation scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

arXiv

引用

arXiv 2024年

作者： Li, Haopeng Deng, Andong Liu, Jun Rahmani, Hossein Guo, Yulan Schiele, Bernt Bennamoun, Mohammed Ke, Qiuhong School of Computing and Information Systems University of Melbourne Australia Center for Research in Computer Vision University of Central Florida United States Pillar Singapore University of Technology and Design Singapore School of Computing and Communications Lancaster University United Kingdom School of Electronics and Communication Engineering Sun Yat-sen University China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarland Informatics Campus Germany School of Physics Maths and Computing University of Western Australia Australia Department of Data Science & AI Monash University Australia

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning

arXiv

引用

arXiv 2024年

作者： Lv, Fengling Shang, Xinyi Zhou, Yang Zhang, Yiqun Li, Mengke Lu, Yang Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University China University College London United Kingdom A*STAR Institute of High Performance Computing Singapore School of Computer Science and Technology Guangdong University of Technology Guangzhou China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China

Personalized Federated Learning (PFL) aims to acquire customized models for each client without disclosing raw data by leveraging the collective knowledge of distributed clients. However, the data collected in real-world scenarios is likely to follow a long-tailed distribution. For example, in the medical domain, it is more common for the number of general health notes to be much larger than those specifically related to certain diseases. The presence of long-tailed data can significantly degrade the performance of PFL models. Additionally, due to the diverse environments in which each client operates, data heterogeneity is also a classic challenge in federated learning. In this paper, we explore the joint problem of global long-tailed distribution and data heterogeneity in PFL and propose a method called Expert Collaborative Learning (ECL) to tackle this problem. Specifically, each client has multiple experts, and each expert has a different training subset, which ensures that each class, especially the minority classes, receives sufficient training. Multiple experts collaborate synergistically to produce the final prediction output. Without special bells and whistles, the vanilla ECL outperforms other state-of-the-art PFL methods on several benchmark datasets under different degrees of data heterogeneity and long-tailed distribution. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent Traffic Control System for Identifying Traffic Congestion and Emergency Vehicle Detection in Malaysia 4th

A Novel Intelligent Traffic Control System for Identifying T...

引用

4th International Conference on Internet of Things, ICIoT 2023

作者： Omar, Mas Yakub, Fitri Niranjana, Govindan Azizan, Azizul Liana, Farah Suseela, G. Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia

ISBN: (纸本)9783031856655

Traffic congestion is a community-related issue in urban areas associated with the ease and comfort of road travel. This problem persists in Malaysia, owing to the fast expansion of urban areas caused by increased vehicle volume due to rapid human population growth. Amid traffic congestion, an emergency vehicle must travel smoothly to cater for emergency action to save human life. Existing traffic signal systems are unsuccessful at solving emergency vehicles stranded during traffic congestion since they are time-based, resulting in the worst travel times and energy loss. Therefore, this study is inspired to provide a novel IoT system utilising Raspberry Pi and Arduino that enables the emergency vehicle to act as the input to the traffic light to guide it through congested intersection roads that require immediate passing. The "Traffic Control Module," the system’s central control unit, controls the traffic signal colour-switching action to realise this study’s intelligent traffic control system objective. It promotes scalability in the design. However, the system faces some limitations potentially related to the system algorithm and hardware limitations regarding its performance on vehicle detection accuracy. The paper also discusses potential future improvements, which can enhance the system to serve the community better. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

How to Make IoT Sensitive to Privacy? An Approach Based on ODRL and IllustratedWith WoT TD

How to Make IoT Sensitive to Privacy? An Approach Based on O...

引用

18th International Conference on Software Technologies, ICSOFT 2023

作者： Maamar, Zakaria Benna, Amel Xu, Yang Serhani, Mohamed Adel Li, Minglin Huang, Huiru Benadjel, Wassim Sitouah, Nacereddine College of Computing and IT University of Doha for Science and Technology Doha Qatar Department of Multimedia and Information Systems CERIST Algiers Algeria School of Computer Science Fudan University Shanghai China College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Computer Science Faculty USTHB Algiers Algeria Department of Electronics Information and Bioengineering Polytechnic University of Milan Milan Italy

ISBN: (纸本)9789897586651

Despite the multiple advantages of the Internet-of-Things (IoT), many users are still skeptical considering IoT as another disruptive information and communication technology that is "silently" invading their privacy with the risk of having their habits, preferences, and choices exposed publicly. To mitigate this silent invasion, this paper looks into innovative ways of making IoT sensitive to privacy by first, allowing users to explicitly express what is permitted, forbidden, and obliged over their personal data using the Open Digital Rights Language (ODRL), and second, adjusting things’ specifications like theWeb-of-Things Thing Description (WoT TD), so that things would act according to these users’ permissions, prohibitions, and obligations. A system implementing and demonstrating the blend of ODRL with WoT TD is presented based on a case study capturing privacy concerns in a center for elderly people. © 2023 by SCITEPRESS-Science and technology Publications, Lda.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Predicting Mushroom Edibility with Effective Classification and Efficient Feature Selection Techniques

Predicting Mushroom Edibility with Effective Classification ...

引用

International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)

作者： Md. Samin Morshed Faisal Bin Ashraf Muhammad Usama Islam Md. Shafiur Raihan Shafi Department of Computer Science and Engineering Islamic University of Technology Department of CSE BRAC University School of Computing and Informatics UL Lafayette Department of CSE Southeast University

Machine learning in agriculture has added a new dimension to research field through providing actionable insights for better crop yield. In our work, we have explored various types of mushrooms and utilized efficient feature selection techniques coupled with effective machine learning based classification methods to classify the edibility of mushrooms automatically. Through experimentation with nine distinct machine learning methods and twenty selected features, the result shows that our best model (k-NN) performed significantly better with an accuracy of 99% and F-1 score of 99% in comparison to other machine learning methods. Our research work provided us with valuable actionable insights to devise further scopes in research in the field of mushroom edibility predicting through machine learning.

关键词： Support vector machines Machine learning Signal processing Feature extraction Agriculture Reproducibility of results Robots

来源：评论

学校读者我要写书评

暂无评论

Graph Learning: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第2期2卷 109-127页

作者： Xia, Feng Sun, Ke Yu, Shuo Aziz, Abdul Wan, Liangtian Pan, Shirui Liu, Huan School of Engineering IT and Physical Sciences Federation University Australia BallaratVIC3353 Australia School of Software Dalian University of Technology Dalian116620 China Faculty of Information Technology Monash University MelbourneVIC3800 Australia School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in differe

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

UniDSeg: unified cross-domain 3D semantic segmentation via visual foundation models prior 24

UniDSeg: unified cross-domain 3D semantic segmentation via v...

引用

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

作者： Yao Wu Mingwei Xing Yachao Zhang Xiaotong Luo Yuan Xie Yanyun Qu School of Informatics Xiamen University Institute of Artificial Intelligence Xiamen University School of Computer Science and Technology East China Normal University and Chongqing Institute of East China Normal University School of Informatics Xiamen University and Institute of Artificial Intelligence Xiamen University and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University

ISBN: (纸本)9798331314385

3D semantic segmentation using an adapting model trained from a source domain with or without accessing unlabeled target-domain data is the fundamental task in computer vision, containing domain adaptation and domain generalization. The essence of simultaneously solving cross-domain tasks is to enhance the generalizability of the encoder. In light of this, we propose a groundbreaking universal method with the help of off-the-shelf Visual Foundation Models (VFMs) to boost the adaptability and generalizability of cross-domain 3D semantic segmentation, dubbed UniDSeg. Our method explores the VFMs prior and how to harness them, aiming to inherit the recognition ability of VFMs. Specifically, this method introduces layer-wise learnable blocks to the VFMs, which hinges on alternately learning two representations during training: (i) Learning visual prompt. The 3D-to-2D transitional prior and task-shared knowledge is captured from the prompt space, and then (ii) Learning deep query. Spatial Tunability is constructed to the representation of distinct instances driven by prompts in the query space. Integrating these representations into a cross-modal learning framework, UniDSeg efficiently mitigates the domain gap between 2D and 3D modalities, achieving unified cross-domain 3D semantic segmentation. Extensive experiments demonstrate the effectiveness of our method across widely recognized tasks and datasets, all achieving superior performance over state-of-the-art methods. Remarkably, UniDSeg achieves 57.5%/54.4% mIoU on "A2D2/sKITTI" for domain adaptive/generalized tasks. Code is available at https://***/Barcaaaa/UniDSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diversity, Equity, and Inclusion in computing Science: Culture is the Key, Curriculum Contributes 2024

Diversity, Equity, and Inclusion in Computing Science: Cultu...

引用

29th Working Group Reports on Innovation and technology in Computer Science Education, ITiCSE WGR 2024

作者： Toti, Giulia Lindner, Peggy Gao, Alice Baghban Karimi, Ouldooz Engineer, Rutwa Hur, Jinyoung Mcneill, Fiona Reckinger, Shanon Robinson, Rebecca Sollazzo, Anna Wicentowski, Richard Department of Computer Science University of British Columbia VancouverBC Canada Department of Information Science Technology University of Houston HoustonTX United States Department of Computer Science University of Toronto TorontoON Canada School of Computing Science Simon Fraser University SurreyBC Canada Department of Mathematical and Computational Sciences University of Toronto Mississauga MississaugaON Canada Department of Computer Science University of Illinois Urbana-Champaign Urbana-ChampaignIL United States School of Informatics University of Edinburgh Edinburgh United Kingdom Department of Computer Science University of Illinois Chicago ChicagoIL United States Department of Human Centred Computing Monash University ClaytonVIC Australia School of Computing Science University of Glasgow United Kingdom Computer Science Department Swarthmore College SwarthmorePA United States

ISBN: (纸本)9798400712081

Undergraduate computer science programs worldwide struggle to attract and retain underrepresented students for many reasons. Culture, stereotype threats, uneven gender and racial representations, lack of role models, and uncertain career prospects for minority groups are among the many reasons behind this situation. Many computer science programs are trying to change course through strategies to foster equity, diversity, and inclusion (EDI), aimed at improving outreach, recruitment, admissions, and retention of underrepresented students. EDI approaches may also include modifications to the undergraduate computer science curriculum. However, if not properly planned, these modifications risk amplifying existing stereotypes rather than producing positive change [38]. In this study, through an extensive literature review, a rigorous curriculum analysis of 49 computer science programs across the globe, and qualitative and quantitative analysis of surveys and interviews bringing in the voices of 613 students and 30 educators participating from around the world, we explore equity, diversity, and inclusion in the computer science curriculum. We highlight the role of inclusive content and course design, discuss program flexibility, and the impact of inclusive courses and program design in attracting and retaining historically marginalized students. Finally, we provide concrete steps to make computing science undergraduate curricula more appealing to a diverse audience. © 2024 Copyright held by the owner/author(s).

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Active Learning-Based Mobile Malware Detection Utilizing Auto-Labeling and Data Drift Detection

Active Learning-Based Mobile Malware Detection Utilizing Aut...

引用

Cyber Security and Resilience (CSR), IEEE International Conference on

作者： Zhe Deng Arthur Hubert Sadok Ben Yahia Hayretdin Bahsi Department of Software Science Tallinn University of Technology Estonia Interdisciplinary Centre for Security Reliability and Trust (SnT) University of Luxembourg Luxembourg School of Informatics Computing and Cyber Systems Northern Arizona University USA

ISBN: (数字)9798350375367

ISBN: (纸本)9798350375374

Machine learning-based detection methods have demonstrated high performance in mobile malware detection. However, changes in mobile malware over time induce a sig-nificant challenge for malware detection systems running in operational environments. The development of non-stationary models to address concept drift in the threat landscape has garnered significant research interest. Auto-labeling is using automated algorithms to assign labels to data without manual intervention. This study explores the method for introducing auto-labeling in active learning with data drift detection. It achieves satisfying results for the lowest possible cost while succeeding in adapting to changes in the data for a long period.

关键词： Training Adaptation models Costs Training data Prediction methods Manuals Prediction algorithms

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：