检索结果-内蒙古大学图书馆

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Farbod Siahkali Seyed Amirmahdi Alavi Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Computer Science Islamic Azad University Central Tehran Branch Tehran Iran

ISBN: (纸本)9781665476249

In this paper, a new publicly available 1 web-Scraped Iranian Vehicle Dataset (SIVD) for simultaneous real-time vehicle tracking and recognition is proposed. The datasets provided for Iranian cars in the literature have two fundamental problems. First, the lack of images from different angles, and second, the small number of classes compared to the dispersion of car models in the real world. Therefore, for the purposes of this paper, Iranian vehicle images from car sales websites are collected, and the SIVD dataset is proposed which contains 29 classes and 36,705 images. This paper aims at developing a classification network for Iranian vehicle recognition and implement a real-time tracking system using the YOLOv5 network to perform real-time vehicle model recognition and tracking tasks simultaneously. The ResNet50 achieved an accuracy of 99.29%, the highest among the investigated classification networks. 1 https://***/Farbod-Siahkali/Iranian-Vehicle-Tracking-and-Recognition

关键词： Representation learning Image recognition Video tracking Machine learning algorithms Neural networks Real-time systems Automobiles

来源：评论

学校读者我要写书评

暂无评论

The Role of Expertise in Effectively Moderating Harmful Social Media Content 25

The Role of Expertise in Effectively Moderating Harmful Soci...

引用

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

作者： Abdelkadir, Nuredin Ali Yang, Tianling Kapania, Shivani Estefanos, Meron Gebrekidan, Fasica Berhane Zelalem, Zecharias Ali, Messai Berhe, Rishan Baker, Dylan Talat, Zeerak Miceli, Milagros Hanna, Alex Gebru, Timnit Computer Science and Engineering University of Minnesota MinneapolisMN United States The Distributed AI Research Institute MinneapolisMN United States Weizenbaum Institute Technische Universität Berlin Berlin Germany Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States The Distributed AI Research Institute Stockholm Sweden Independent Researcher Nairobi Kenya Freelance Journalist MontrealQC Canada Independent Researcher Stockholm Sweden Independent Researcher New YorkNY United States University of Edinburgh Edinburgh United Kingdom

ISBN: (纸本)9798400713941

Social media platforms played a significant role in spreading genocidal content in the 2020-2022 Tigray war, where the deadliest genocide of the 21st century was committed. While linguistic expertise is clearly needed to adequately moderate such content, we ask: What additional expertise is needed? Why and to what extent do experts disagree on what constitutes harmful content, and what is the best way to resolve these disagreements? What do social media platforms do instead? We examine these questions through a 4-month study with 7 experts labeling 340 X (formerly Twitter) posts, and by interviewing 15 commercial content moderators. We find in-depth cultural knowledge and dialects to be most important for accurate hate speech annotation - knowledge which social media platforms do not prioritize. Even amongst experts, disagreements are high (71%), dropping to 40% after deliberation meetings. Based on these results, we present 7 recommendations to improve hate speech annotation and moderation practices. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

An EEG Method to Identify Image Preference With an Explicit/Implicit Task Brain-computer Interface

引用

IEEE Transactions on Affective Computing 2025年

作者： Li, Yulei Li, Shuyi Qi, Hongzhi Tianjin University Academy of Medical Engineering and Translational Medicine Tianjin300072 China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin300092 China Tianjin Key Laboratory of Brain Science and Neuroengineering Tianjin300072 China

Accurately determining an individual's preference for images remains a major challenge in the field of emotional research. This study proposes a novel paradigm for identifying individual image preferences using electroencephalography (EEG) signals and brain-computer interface (BCI). The paradigm involves both explicit and implicit tasks, where participants perform a typical event-related potential-based brain-computer interface(ERP-BCI) operation and their subjective image preferences are identified, respectively. Two experiments with a total of 27 participants demonstrate that event-related potential (ERP) signals during explicit BCI tasks are significantly influenced by target image preferences, enabling high-accuracy image preference recognition. Online experiments selecting positive and negative preference images from a candidate pool show top-1 accuracy approaching 100% and top-3 accuracy exceeding 90%. These results indicate the effectiveness of the proposed EEG-based image preference recognition paradigm, laying the groundwork for preference analysis applications. © 2010-2012 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

I Can’t Share Code, but I need Translation - An Empirical Study on Code Translation through Federated LLM

arXiv

引用

arXiv 2025年

作者： Kumar, Jahnavi Janapati, Venkata Lakshmana Sasaank Tanguturi, Mokshith Reddy Chimalakonda, Sridhar Research in Intelligent Software & Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

Owing to the rapid evolution of technologies and project requirements, organizations need to upgrade the code base in their software projects to a new version of the programming language or even translating to an entirely new one. However, code translation is resource-intensive and requires expertise in both the source and target languages. While researchers have made progress in automating translations between legacy and modern languages, recent work has increasingly turned to pre-trained Large Language Models (LLMs) to translate efficiently. Given the proprietary nature of code, organizations prefer finetuning LLMs locally rather than relying on external APIs. This is one of the first empirical studies that proposes a Federated LLM-based approach for code translation. The proposed approach enables clients to jointly train a code translator without sharing sensitive data. This study demonstrates that participants can collaboratively develop a FedLLM for efficient code translation (particularly C# to Java and vice-versa) with superior results (more than 40% improvement in CodeLLaMA’s CodeBLEU score) compared to individual client models. Our findings indicate that FedLLM offers a collaborative approach to code translation and could serve as a promising direction for future research in this field. © 2025, CC BY.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Sonic Delights: Exploring the Design of Food as An Auditory-Gustatory Interface 25

Sonic Delights: Exploring the Design of Food as An Auditory-...

引用

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

作者： Deng, Jialin Li, Yinyi Wang, Hongyue Fang, Ziqi Mueller, Florian School of Computer Science University of Bristol Bristol United Kingdom Exertion Games Lab Department of Human-Centred Computing Monash University MelbourneVIC Australia Royal College of Art London United Kingdom Imperial College London London United Kingdom

ISBN: (纸本)9798400713941

While interest in blending sound with culinary experiences has grown in human-Food interaction (HFI), the significance of food's material properties in shaping sound-related interactions has largely been overlooked. This paper explores the opportunity to enrich the HFI experience by treating food not merely as passive nourishment but as an integral material in computational architecture with input/output capabilities. We introduce "Sonic Delights,"where food is a comestible auditory-gustatory interface to enable users to interact with and consume digital sound. This concept redefines food as a conduit for interactive auditory engagement, shedding light on the untapped multisensory possibilities of merging taste with digital sound. An associated study allowed us to articulate design insights for forthcoming HFI endeavors that seek to weave food into multisensory design, aiming to further the integration of digital interactivity with the culinary arts. © 2025 Copyright held by the owner/author(s).

关键词： Edible Interface

来源：评论

学校读者我要写书评

暂无评论

Real-Time Facial Expression Recognition using Facial Landmarks and Neural Networks

arXiv

引用

arXiv 2022年

作者： Haghpanah, Mohammad Amin Saeedizade, Ehsan Masouleh, Mehdi Tale Kalhor, Ahmad Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Computer Science and Engineering University of Nevada Reno United States

This paper presents a lightweight algorithm for feature extraction, classification of seven different emotions, and facial expression recognition in a real-time manner based on static images of the human face. In this regard, a Multi-Layer Perceptron (MLP) neural network is trained based on the foregoing algorithm. In order to classify human faces, first, some pre-processing is applied to the input image, which can localize and cut out faces from it. In the next step, a facial landmark detection library is used, which can detect the landmarks of each face. Then, the human face is split into upper and lower faces, which enables the extraction of the desired features from each part. In the proposed model, both geometric and texture-based feature types are taken into account. After the feature extraction phase, a normalized vector of features is created. A 3-layer MLP is trained using these feature vectors, leading to 96% accuracy on the test set. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

It's the Same Conflict Every Time, on Repeat.

It's the Same Conflict Every Time, on Repeat.

引用

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

作者： Chin Derix, Eleanor Leong, Tuck Wah Prior, Julia Interaction Design + Human Practice Lab University of Technology Sydney Australia Uts Australia School of Computer Science University of Technology Sydney Australia

ISBN: (纸本)9781450380959

Family technology use can create or amplify conflict in parents' relationships - we found four key factors that contribute to this issue. We conducted a probe and interview study with eight sets of parents, to explore how and why technology use might cause conflict in their relationships. This paper presents data from two particular sets of parents to illustrate our findings. In doing so, it complements existing work that primarily focuses on parent-child relationships, and contributes to a more complete understanding of how family technology use can affect family dynamics. We also suggest directions for further work to address this issue of conflict between parents, associated with their family's use of technology. © 2021 ACM.

关键词： computer programming

来源：评论

学校读者我要写书评

暂无评论

MAIDS: Malicious Agent Identification-based Data Security Model for Cloud Environments

arXiv

引用

arXiv 2024年

作者： Gupta, Kishu Saxena, Deepika Gupta, Rishabh Singh, Ashutosh Kumar Department of Computer Science & Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan Department of Computer Science & Engineering University of Aizu Fukushima Aizuwakamatsu Japan Department of Computer Science The University of Economics and Human Sciences Warsaw01043 Poland Department of Computer Applications SRM Institute of Science & Technology Delhi-NCR Campus Modinagar Uttar Pradesh Ghaziabad201204 India Department of Computer Science & Engineering Indian Institute of Information Technology Madhya Pradesh Bhopal462003 India

With the vigorous development of cloud computing, most organizations have shifted their data and applications to the cloud environment for storage, computation, and sharing purposes. During storage and data sharing across the participating entities, a malicious agent may gain access to outsourced data from the cloud environment. A malicious agent is an entity that deliberately breaches the data. This information accessed might be misused or revealed to unauthorized parties. Therefore, data protection and prediction of malicious agents have become a demanding task that needs to be addressed appropriately. To deal with this crucial and challenging issue, this paper presents a Malicious Agent Identification-based Data Security (MAIDS) Model which utilizes XGBoost machine learning classification algorithm for securing data allocation and communication among different participating entities in the cloud system. The proposed model explores and computes intended multiple security parameters associated with online data communication or transactions. Correspondingly, a security-focused knowledge database is produced for developing the XGBoost Classifier-based Malicious Agent Prediction (XC-MAP) unit. Unlike the existing approaches, which only identify malicious agents after data leaks, MAIDS proactively identifies malicious agents by examining their eligibility for respective data access. In this way, the model provides a comprehensive solution to safeguard crucial data from both intentional and non-intentional breaches, by granting data to authorized agents only by evaluating the agent’s behavior and predicting the malicious agent before granting data. The performance of the proposed model is thoroughly evaluated by accomplishing extensive experiments, and the results signify that the MAIDS model predicts the malicious agents with high accuracy, precision, recall, and F1-scores up to 95.55%, 95.30%, 95.50%, and 95.20%, respectively. This enormously enhances the system’s sec

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Extremely Lightweight Skin Segmentation Networks to Improve Remote Photoplethysmography Measurement 14th

Extremely Lightweight Skin Segmentation Networks to Improve ...

引用

14th International Conference on Intelligent human computer interaction, IHCI 2022

作者： Lee, Kunyoung You, Hojoon Oh, Jaemu Lee, Eui Chul Department of Computer Science Graduate School Sangmyung University Seoul Korea Republic of Department of AI and Informatics Graduate School Sangmyung University Seoul Korea Republic of Department of Human-Centered Artificial Intelligence Sangmyung University Seoul Korea Republic of

ISBN: (纸本)9783031271984

Recently, remote photoplethysmography (rPPG) has been studied and developed not only in a controlled environment but also in a wild environment such as telemedicine and driver monitoring. Although photoplethysmography (PPG) can be measured through a contact sensor, pulse signal can be obtained by remote measuring minute color changes on the skin surface using a camera. This pulse signal is called rPPG and has an advantage of sensing cardiac activity without a contact sensor. The processing pipeline of rPPG can be simply defined as region of interest selection (ROI), pulse signal extraction, signal processing. During this process, in ROI selection, skin segmentation is performed because only the skin pixel region is related to the rPPG signal. We propose extremely lightweight skin segmentation network (ELSNet) for applying deep learning to skin segmentation to measure reliable signals. Our method improved the success rate within 5BPM of heart rate estimation by about 6%, and in the talking environment, an average performance improvement of 9.5% was confirmed. In addition, it was confirmed that MAPE was improved by an average of 20%. The ELSNet shows 167 FPS throughput on Intel i9 CPU. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Yin, Zhaoxia Zhu, Shaowei Su, Hang Peng, Jianteng Lyu, Wanli Luo, Bin East China Normal University School of Communication & Electronic Engineering Shanghai China Anhui University China Tsinghua University Department of Computer Science and Technology Beijing100084 China OPPO Intellisense and Interaction Research Department China

Deep Neural Networks (DNNs) have recently made significant strides in various fields;however, they are susceptible to adversarial examples-crafted inputs with imperceptible perturbations that can mislead these networks. Notably, even when adversaries lack access to the complete model parameters, they can still generate adversarial examples targeting a range of DNN-based task systems. Various defense mechanisms have been proposed, such as feature compression and gradient masking. Nevertheless, extensive research indicates that these methods often address only specific attacks, rendering them ineffective against novel and unknown attack strategies. Recent studies have highlighted the efficacy of identifying adversarial examples in the frequency domain;however, these approaches are limited to frequency-based analysis. In this study, we experimentally observe that adversarial examples possess significant characteristics in local regions. Specifically, adversarial perturbations exhibit localized randomness, whereas the high-frequency information in normal examples is both locally coherent and semantically relevant. This critical distinction enables effectively distinguishing adversarial examples from normal ones. To leverage this insight, we aim to enhance the high-frequency features of input examples to amplify their feature disparities. We propose an image enhancement method utilizing local histogram equalization. Our experimental results demonstrate that this method substantially improves detector performance without modifying the existing detection models. Furthermore, this technique can be seamlessly integrated with task models, effectively reducing deployment costs in practical applications. © 2004-2012 IEEE.

关键词： Frequency domain analysis

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：