检索结果-内蒙古大学图书馆

Few-shot tire tracks recognition based on metric learning

Engineering Applications of Artificial Intelligence 2025年 156卷

作者： Zhai, Longlong He, Jinrong Li, Zhaokui Bi, Yingzhou College of Mathematics and Computer Science Yan'an University Yan'an716000 China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530100 China School of Computer Shenyang Aerospace University Shenyang110136 China

Tire tracks are crucial evidence for investigating and identifying traffic accident scenes. Intelligent recognition of tire track images enables rapid and precise identification of suspicious vehicles, assisting investigators in determining accident causes and liabilities. This enhances both the efficiency and accuracy of case resolution. However, tire track images are complex and diverse, significantly influenced by environmental factors such as lighting and road conditions. Moreover, the limited availability of tire track image samples poses a challenge for training deep learning models in practical applications. To address these challenges, particularly the limited generalization ability of few-shot metric learning models on unseen categories and their poor recognition rates in open-world environments, we propose a novel framework called TireNet for few-shot tire track recognition. First, we adopt a residual network integrated with coordinate attention as the backbone for feature extraction. Secondly, the context-aware features of the support set and the query set are extracted separately through attention-based bi-directional long short-term memory model. Subsequently, the cosine similarity between the features of the support set and the query set is calculated to determine the category of the query image. Finally, to address the class imbalance issue in the tire track image dataset, we utilize an improved Focal Loss for gradient updates. This enables the model to focus more on difficult samples during training, thereby enhancing the training efficiency, particularly in scenarios involving few-shot learning and open-world environments. To validate the proposed method, we constructed a tire track image dataset of 1700 samples, covering various environmental conditions, providing a rich resource for tire track recognition research. Experimental results demonstrate that the proposed method significantly outperforms few-shot image classification and classic machine

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Teacher-centric educational recommender systems in K12 practice: Usage and evaluation

引用

Heliyon 2025年第2期11卷 e42012页

作者： Bhatt, Sohum M. Verbert, Katrien Van Den Noortgate, Wim Faculty of Psychology and Educational Sciences and imec research group itec KU Leuven Belgium Human and Computer Interaction Group Department of Computer Science KU Leuven Belgium

Personalized learning is hard to apply in classroom practice due to the workload of teachers. Recommender systems can help teachers make choices and hence personalize the learning environment. However, few studies have investigated how teachers use recommender systems in their practice. Educational recommender systems also require more investigation into how teachers assess recommendations to provide better systems in the future. Therefore, this research aimed to provide a better insight into the practical application of a teacher-centric educational recommender system, conduct a user-centric evaluation of the recommender system, and present teacher beliefs on the use of educational recommender systems for personalized learning. Our results indicated that teachers similarly used the recommender system by creating new lessons rather than adapting suggested lessons. Their evaluations of the recommender system highlighted the importance of accuracy and utility. Diversity and serendipity were considered to be less important. Teachers perceived recommender systems as a first step to personalized learning and as a tool for simplifying such learning. However, the current system did not affect the quality of personalized learning. Based on these results, we propose to focus more on accuracy and utility as opposed to diversity and serendipity for teacher-centric recommender system evaluation. For personalized learning, we conclude that, according to teachers, recommender systems can lead to more effective personalization by allowing teachers to focus on student needs. © 2025 The Authors

关键词： Data science applications in education Elementary education Improving classroom teaching Secondary education

来源：评论

学校读者我要写书评

暂无评论

Designing Towards an Application to Find a Nurse 23rd

Designing Towards an Application to Find a Nurse

引用

23rd International Conference on human-computer interaction, HCII 2021

作者： Fournier, Hélène Katsuragawa, Keiko Singh, Karanpreet Bin Hannan, Nabil Kondratova, Irina Human-Computer Interaction Digital Technologies Research Centre National Research Council Canada MonctonNB Canada Human-Computer Interaction Digital Technologies Research Centre National Research Council Canada WaterlooON Canada Human-Computer Interaction Digital Technologies Research Centre National Research Council Canada FrederictonNB Canada Computer Science University of Waterloo WaterlooON Canada Computer Science University of New Brunswick FrederictonNB Canada

ISBN: (纸本)9783030786342

In this fast-paced technological era, the demand and the usage of applications which make our life easier have increased dramatically. This need has grown especially for the aging population who require help more than ever. Older adults (65+) need an effective way to communicate with a healthcare professional in case they require any advice about their health or schedule an in-person checkup. The current COVID-19 pandemic has accelerated the push for remote check-ins and virtual care especially for older adults who are medically or socially vulnerable. Remote health services are being promoted as a means of preserving the patient-health care provider relationship at times when in-person visits are not practical or feasible, especially during COVID-19 and in the future. This paper describes an application to support vulnerable older adults in their home, with more responsive home health care services which can potentially reduce the number of unnecessary trips to the hospital for non-emergency situations. The process of designing the application will be described, including workflow, storyboards, and key steps in the validation process. The paper will also discuss future research directions. © 2021, Her Majesty the Queen in Right of Canada.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions 25

User-Driven Value Alignment: Understanding Users' Perception...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI 2025

作者： Fan, Xianzhe Xiao, Qing Zhou, Xuhui Pei, Jiaxin Sap, Maarten Lu, Zhicong Shen, Hong Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Language Technologies Institute Carnegie Mellon University PittsburghPA United States Stanford University StanfordCA United States Department of Computer Science George Mason University FairfaxVA United States

ISBN: (纸本)9798400713941

Content Warning: This paper presents textual examples that may be offensive or *** language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking the initiative to address these harms and re-align AI companions. We introduce the concept of user-driven value alignment, where users actively identify, challenge, and attempt to correct AI outputs they perceive as harmful, aiming to guide the AI to better align with their values. We analyzed 77 social media posts about discriminatory AI statements and conducted semi-structured interviews with 20 experienced users. Our analysis revealed six common types of discriminatory statements perceived by users, how users make sense of those AI behaviors, and seven user-driven alignment strategies, such as gentle persuasion and anger expression. We discuss implications for supporting user-driven value alignment in future AI systems, where users and their communities have greater agency. © 2025 Copyright held by the owner/author(s).

关键词： User-Driven Value Alignment

来源：评论

学校读者我要写书评

暂无评论

AI-AR for Remote Visual Bridge Inspection by Drone 11

AI-AR for Remote Visual Bridge Inspection by Drone

引用

11th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2022

作者： Lapointe, Jean-Francois Sekkati, Hicham Allili, Mohand Said Hebbache, Loucif Amirkhani, Dariush Hammouche, Nadir Human-Computer Interaction Team Digital Technologies Research Centre National Research Council Canada Department of Computer Science and Engineering University of Quebec in Outaouais GatineauQCJ8X 3X7 Canada

Regular inspections of bridges and overpasses are required to ensure the safety of those infrastructures. This paper presents a system developed to do the remote visual inspection of concrete bridges and overpasses by combining drone, artificial intelligence and augmented reality technologies with the goal to assist bridge inspectors in conducting a remote visual inspection. It also reports on the results of a first field trial of this complex human-machine system. Deep learning networks can be trained to detect defects on independent images but the user interface must be adapted to track defects in a stream of images at a speed consistent with human vision to allow inspection. This first field trial allows for an initial estimate of a speed up factor of ten (10x) to conduct visual inspections. The developed system could lead to significant cost reduction to inspect the bridges and overpasses as well as significant reduction of downtimes for these transportation infrastructures. © 2022 International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Relectrode: A reconfigurable electrode for multi-purpose sensing based on microfluidics 21

Relectrode: A reconfigurable electrode for multi-purpose sen...

引用

2021 CHI Conference on human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021

作者： Sun, Wei Chen, Yanjun Zhan, Simon Han, Teng State Key Laboratory of Computer Science Beijing Key Lab of Human-Computer Interaction Institute of SoftwareChinese Academy of Sciences Beijing China

ISBN: (纸本)9781450380966

In this paper, we propose a reconfgurable electrode, RElectrode, using a microfuidic technique that can change the geometry and material properties of the electrode to satisfy the needs for sensing a variety of diferent types of user input through touch/touchless gestures, pressure, temperature, and distinguish between diferent types of objects or liquids. Unlike the existing approaches, which depend on the specifc-shaped electrode for particular sensing (e.g., coil for inductive sensing), RElectrode enables capacity, inductance, resistance/pressure, temperature, pH sensings all in a single package. We demonstrate the design and fabrication of the microfuidic structure of our RElectrode, evaluate its sensing performance through several studies, and provide some unique applications. RElectrode demonstrates technical feasibility and application values of integrating physical and biochemical properties of microfuidics into novel sensing interfaces. © 2021 ACM.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

How Users Who are Blind or Low Vision Play Mobile Games: Perceptions, Challenges, and Strategies 25

How Users Who are Blind or Low Vision Play Mobile Games: Per...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI 2025

作者： Ran, Zihe Li, Xiyu Xiao, Qing Fan, Xianzhe Li, Franklin Mingzhe Wang, Yanyun Lu, Zhicong Communication University of China Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Tsinghua University Beijing China College of Media Communication and Information University of Colorado Boulder BoulderCO United States Department of Computer Science George Mason University FairfaxVA United States

ISBN: (纸本)9798400713941

As blind and low-vision (BLV) players engage more deeply with games, accessibility features have become essential. While some research has explored tools and strategies to enhance game accessibility, the specific experiences of these players with mobile games remain underexamined. This study addresses this gap by investigating how BLV users experience mobile games with varying accessibility levels. Through interviews with 32 experienced BLV mobile players, we explore their perceptions, challenges, and strategies for engaging with mobile games. Our findings reveal that BLV players turn to mobile games to alleviate boredom, achieve a sense of accomplishment, and build social connections, but face barriers depending on the game's accessibility level. We also compare mobile games to other forms of gaming, highlighting the relative advantages of mobile games, such as the inherent accessibility of smartphones. This study contributes to understanding BLV mobile gaming experiences and provides insights for enhancing accessible mobile game design. © 2025 Copyright held by the owner/author(s).

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

Tonic and Event-Related Phasic Transcutaneous Auricular Vagus Nerve Stimulation Alters Pupil Responses in the Change-Detection Task

引用

Neuromodulation 2025年第4期28卷 652-662页

作者： Chen, Jingxin Ke, Yufeng Ni, Guangjian Liu, Shuang Ming, Dong Academy of Medical Engineering and Translational Medicine Tianjin International Joint Research Centre for Neural Engineering Tianjin Key Laboratory of Brain Science and Neural Engineering Tianjin University Tianjin China Department of Biomedical Engineering College of Precision Instrument and Optoelectronics Engineering Tianjin University Tianjin China Haihe Laboratory of Brain-computer Interaction and Human-machine Integration Tianjin China

Background: Transcutaneous auricular vagus nerve stimulation (taVNS) has emerged as a potential modulator of cognitive behavior that activates the locus coeruleus-noradrenaline (LC-NA) system. Previous studies explored both phasic and tonic taVNS by investigating their impact on LC-NA markers such as pupil dilation and heart rate variability (HRV). Objective: Inconsistencies persist in the identification of reliable markers for assessing the effects of taVNS on noradrenergic activity. Furthermore, it remains unclear whether the effects of taVNS extend beyond pure vagal nerve responses, particularly in specific cognitive domains such as working memory. In the present study, we investigated the effects of taVNS on working memory capacity and LC-NA markers using a change-detection task. Materials and Methods: Twenty-two healthy, right-handed university students participated in a sham-controlled, randomized cross-over experiment with four sessions. We applied two types of phasic and event-related stimulation (Pre-event and Event-synchronous), tonic stimulation (Pre-task), and sham stimulation across different sessions. Pupil size and electrocardiogram data were recorded during the tasks. Results: taVNS did not significantly modulate behavioral performance on the change-detection task, specifically working memory capacity. However, both tonic and event-related phasic taVNS significantly influenced the pupillary response during the task. In addition, the Pre-task condition of the taVNS affected the low-frequency parameter of HRV. Conclusions: Our findings suggest that tonic and event-related phasic taVNS may modulate noradrenergic activity, as evidenced by pupil responses and HRV changes during the change-detection task. This study provides new evidence regarding the impact of taVNS on cognitive tasks, thus supporting the development of noninvasive neuromodulation interventions. © 2025 International Neuromodulation Society

关键词： Heart rate variability (HRV) LC-NA pupil response pupillometry taVNS

来源：评论

学校读者我要写书评

暂无评论

Let's Influence Algorithms Together: How Millions of Fans Build Collective Understanding of Algorithms and Organize Coordinated Algorithmic Actions 25

Let's Influence Algorithms Together: How Millions of Fans Bu...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI 2025

作者： Xiao, Qing Zheng, Yuhang Fan, Xianzhe Zhang, Bingbing Lu, Zhicong Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States University of Amsterdam Amsterdam Amsterdam Netherlands Tsinghua University Beijing China School of Journalism and Mass Communication University of Iowa iowa CityIA United States Department of Computer Science George Mason University FairfaxVA United States

ISBN: (纸本)9798400713941

Previous research pays attention to how users strategically understand and consciously interact with algorithms but mainly focuses on an individual level, making it difficult to explore how users within communities could develop a collective understanding of algorithms and organize collective algorithmic actions. Through a two-year ethnography of online fan activities, this study investigates 43 core fans who always organize large-scale fans collective actions and their corresponding general fan groups. This study aims to reveal how these core fans mobilize millions of general fans through collective algorithmic actions. These core fans reported the rhetorical strategies used to persuade general fans, the steps taken to build a collective understanding of algorithms, and the collaborative processes that adapt collective actions across platforms and cultures. Our findings highlight the key factors that enable computer-supported collective algorithmic actions and extend collective action research into the large-scale domain targeting algorithms. © 2025 Copyright held by the owner/author(s).

关键词： Algorithm Folk Theory of Algorithm Collective Understanding of Algorithm Collective Algorithmic Action Fandom Studies

来源：评论

学校读者我要写书评

暂无评论

Flow-aware synthesis: A generic motion model for video frame interpolation

引用

Computational Visual Media 2021年第3期7卷 393-405页

作者： Jinbo Xing Wenbo Hu Yuechen Zhang Tien-Tsin Wong Department of Computer Science and Engineering the Chinese University of Hong KongHong Kong SARChina Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina

A popular and challenging task in video research,frame interpolation aims to increase the frame rate of *** existing methods employ a fixed motion model,e.g.,linear,quadratic,or cubic,to estimate the intermediate warping ***,such fixed motion models cannot well represent the complicated non-linear motions in the real world or rendered ***,we present an adaptive flow prediction module to better approximate the complex motions in ***,interpolating just one intermediate frame between consecutive input frames may be insufficient for complicated non-linear *** enable multi-frame interpolation,we introduce the time as a control variable when interpolating frames between original ones in our generic adaptive flow prediction *** and quantitative experimental results show that our method can produce high-quality results and outperforms the existing stateof-the-art methods on popular public datasets.

关键词： flow-aware generic motion model video frame interpolation

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：