检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chan, Shing Yuan, Hang Tong, Catherine Acquah, Aidan Schonfeldt, Abram Gershuny, Jonathan Doherty, Aiden Big Data Institute University of Oxford Oxford United Kingdom Nuffield Department of Population Health University of Oxford Oxford United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Social Research Institute University College London London United Kingdom

Existing activity tracker datasets for human activity recognition are typically obtained by having participants perform predefined activities in an enclosed environment under supervision. This results in small datasets with a limited number of activities and heterogeneity, lacking the mixed and nuanced movements normally found in free-living scenarios. As such, models trained on laboratory-style datasets may not generalise out of sample. To address this problem, we introduce a new dataset involving wrist-worn accelerometers, wearable cameras, and sleep diaries, enabling data collection for over 24 hours in a free-living setting. The result is CAPTURE-24, a large activity tracker dataset collected in the wild from 151 participants, amounting to 3883 hours of accelerometer data, of which 2562 hours are annotated. CAPTURE-24 is two to three orders of magnitude larger than existing publicly available datasets, which is critical to developing accurate human activity recognition models. © 2024, CC BY.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting

arXiv

引用

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Aware Knowledge Graph Embedding for Recommender Systems

Spatio-Temporal Aware Knowledge Graph Embedding for Recommen...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Liu Yang Xin Yin Jun Long Tingxuan Chen Jie Zhao Wenti Huang School of Computer Science and Engineering Central South University Changsha China School of Software Technology Zhejiang University Zhejiang China Big Data Institute Central South University Changsha China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

Knowledge Graphs (KGs) have been incorporated into recommender systems as side information to solve the clas-sical data-sparsity and cold-start problems, with explanations for recommended items. Traditional embedding-based recommender systems generally utilize abundant information from KGs directly to enrich the representation of items or users, but the influences of spatial and temporal dependencies are usually ignored among them. In this paper, we propose a Spatio-Temporal Aware Knowledge Graph Embedding (STAKGE) for recommender systems, which incorporates spatio-temporal information with bias when propagating potential preferences of users in knowl-edge graph embedding. Moreover, we construct a multi-source KG-based recommender dataset - YelpST, containing spatio-temporal information. The experiments on YelpST dataset show that our proposed approach can capture comprehensive spatio-temporal correlations and improve the prediction performance as compared to various state-of-the-art baselines.

关键词： Correlation Knowledge graphs Recommender systems

来源：评论

学校读者我要写书评

暂无评论

TPE for JPEG images with Dynamic M-ary Decomposition and Adaptive Threshold Constraints

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Ma, Yakun Chai, Xiuli Long, Guoqiang Gan, Zhihua Zhang, Yushu Henan University School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of Things Zhengzhou450046 China Henan University School of Software Intelligent Data Processing Engineering Research Center of Henan Province Institute of Intelligent Network System Kaifeng475004 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China

Traditional JPEG image encryption that prioritizes solely confidentiality fails to account for the pressing usability requirements of cloud-based environments, thus boosting the boom in thumbnail-preserving encryption (TPE) to balance image privacy and usability. However, existing TPE schemes for JPEG images face numerous challenges, such as insufficient security, inability to achieve lossless decryption, and high file extension. To address these challenges, we propose a TPE scheme based on dynamic M-ary decomposition and adaptive threshold constraints (TPE-MDTC). First, the valid ranges of quantized DC coefficients for JPEG images are determined. Then, a sum-preserving encryption method for quantized DC coefficients with compliance threshold constraints is designed using the bit-plane permutation to preserve thumbnails with high accuracy. Next, the introduction of dynamic M-ary decomposition effectively changes bit statistical characteristics preserved by bit-plane permutation, enhancing the ciphertext security. Finally, a quantized AC encryption method with RV (Run/Value) pair global permutation is proposed, effectively modifying the unit block features, thereby significantly improving the security and attack resistance of encrypted images. Experimental results show that the proposed TPE-MDTC scheme can reconstruct the original JPEG images without loss, and the generated ciphertext images exhibit significant advantages over previous schemes regarding file extension and security. © 1991-2012 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Enhanced IoT Wearable Device for Monitoring and Providing Feedback on Stuttering

A Machine Learning-Enhanced IoT Wearable Device for Monitori...

引用

Computational Modelling, Simulation and Optimization (ICCMSO), International Conference on

作者： Hussain Suttarwala Ritesh Kumar Madhavi L. Deorankar Dikshendra Daulat Sarpate Pallavi Shingade Surender Kumar Sharma Vrushali More Uday Chandrakant Patkar Deepak K. Sharma Senior Software Engineer American Express Phoenix AZ USA Dept. of AI and Data Science Dr. Akhilesh Das Gupta Institute of Professional Studies New Delhi Delhi India Dept. of Electronics and Telecommunications Marathwada Mitramandal College of Engineering Pune Maharashtra India Dept. of AI and Data Science Zeal College of Engineering and Research Narhe Pune Maharashtra India Dept. of AI and Data Science D Y Patil College of Engineering Akurdi Pune India Dept. of Electrical Engineering Poornima University Jaipur India Dept. of AI and Data Science Genba Sopanrao Moze College of Engineering Balewadi Pune Maharashtra India Department of Computer Engineering Bharati Vidyapeeth’s College of Engineering Lavale Pune Dept. of AI and Data Science Savitribai Phule Pune University Pune Maharashtra India

ISBN: (数字)9798350361391

ISBN: (纸本)9798350361407

This study introduces an innovative IoT-enabled wearable device tailored for monitoring and providing feedback on stuttering, leveraging advanced machine learning algorithms to enhance precision and real-time responsiveness. The device integrates an array of hardware and software elements, including sensors, microcontrollers, and communication protocols, to accurately capture speech patterns and movements. Utilizing machine learning techniques such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), the device performs real-time analysis to identify stuttering instances. Detailed discussions cover the criteria for selecting machine learning models, the training and testing procedures, and the metrics used for performance evaluation. The prototype underwent extensive testing and validation, showcasing high accuracy, sensitivity, and specificity in differentiating stuttered from fluent speech. User feedback emphasized the ergonomic design, user-friendly interface, and real-time feedback features, highlighting its potential to significantly enhance stuttering therapy outcomes. Comparative analysis with existing solutions revealed the device’s superior performance, indicating strong potential for clinical application. The study discusses the implications for stuttering therapy, acknowledges the limitations, outlines future research directions, and underscores the device’s contributions to personalized and effective stuttering interventions. This research advances the field of assistive technologies in speech therapy and demonstrates the promise of IoT-based wearable devices integrated with machine learning for improving the quality of life for individuals with stuttering disorders.

关键词： Performance evaluation Machine learning algorithms Accuracy Medical treatment Prototypes Machine learning Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Perceptive self-supervised learning network for noisy image watermark removal

arXiv

引用

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

ABFS: Natural Robustness Testing for LLM-based NLP software

arXiv

引用

arXiv 2025年

作者： Xiao, Mingxuan Xiao, Yan Ji, Shunhui Li, Yunhe Xue, Lei Zhang, Pengcheng Key Laboratory of Water Big Data Technology of Ministry of Water Resources the College of Computer Science and Software Engineering Hohai University No. 8 Focheng West Road Jiangning District Nanjing211100 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University No.66 Gongchang Road Xinhu Street Guangming District Shenzhen528406 China

Owing to the exceptional performance of Large Language Models (LLMs) in Natural Language Processing (NLP) tasks, LLM-based NLP software has rapidly gained traction across various domains, such as financial analysis and content moderation. However, these applications frequently exhibit robustness deficiencies, where slight perturbations in input (prompt+example) may lead to erroneous outputs. Current robustness testing methods face two main limitations: (1) low testing effectiveness, limiting the applicability of LLM-based software in safety-critical scenarios, and (2) insufficient naturalness of test cases, reducing the practical value of testing outcomes. To address these issues, this paper proposes ABFS, a straightforward yet effective automated testing method that, for the first time, treats the input prompts and examples as a unified whole for robustness testing. Specifically, ABFS formulates the testing process as a combinatorial optimization problem, employing Best-First Search to identify successful test cases within the perturbation space and designing a novel Adaptive control strategy to enhance test case naturalness. We evaluate the robustness testing performance of ABFS on three datasets across five threat models. On Llama2-13b, the traditional StressTest achieves only a 13.273% success rate, while ABFS attains a success rate of 98.064%, supporting a more comprehensive robustness assessment before software deployment. Compared to baseline methods, ABFS introduces fewer modifications to the original input and consistently generates test cases with superior naturalness. Furthermore, test cases generated by ABFS exhibit stronger transferability and higher testing efficiency, significantly reducing testing costs. © 2025, CC BY-NC-ND.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing in Virtual Assistants Current Approaches and Challenges

Natural Language Processing in Virtual Assistants Current Ap...

引用

science, Technology, engineering and Management (ICSTEM), International Conference on

作者： Gautam Solaimalai J. Maria Shanthi Sampath Kumar S Priyanka Khabiya K. Geetha Gokul Talele US. Bank Software Engineering Manager Georgia United States of America Department of Artificial Intelligence and Machine Learning J B. Institute of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Computer Science Engineering Mandsaur University Mandsaur Madhya Pradesh India Department of Computer Science G. T.N Arts College Dindigul Tamil Nadu India Department of Data Science Organization name Accenture Pune Maharashtra India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

The proliferation of virtual sidekicks in colorful disciplines has prodded a swell of interest in advancing Natural Language Processing(NLP) ways to enhance their effectiveness. This paper provides a comprehensive review of the current approaches and challenges encountered in integrating NLP into virtual sidekicks. It begins by outlining the foundational generalities of NLP and its vital part in enabling mortal- suchlike relations with virtual sidekicks. latterly, it delves into a discussion of the different methodologies employed in NLP for understanding and generating mortal language, ranging from rule-grounded systems to deep literacy models. likewise, the paper highlights the crucial challenges such as nebulosity resolution, environment understanding, and handling different verbal variations that stymie the flawless functioning of virtual sidekicks. By synthesizing perceptivity from recent exploration trials, this paper offers precious perspectives on the state-of-the-art NLP ways and directions for unborn exploration to overcome the challenges and propel the development of further intelligent and intuitive virtual sidekicks.

关键词： Reviews Virtual assistants Propulsion Natural language processing Distance measurement

来源：评论

学校读者我要写书评

暂无评论

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection 39

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Dist...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Lin, Yang Guo, Hang Wang, Jinbao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition System via Facial Expressions and Speech Using Machine Learning and Deep Learning Techniques

引用

SN computer science 2023年第4期4卷 363页

作者： Chaudhari, Aayushi Bhatt, Chintan Nguyen, Thanh Thi Patel, Nisarg Chavda, Kirtan Sarda, Kalind U & P U. Patel Department of Computer Engineering Chandubhai S. Patel Institute of Technology Charotar University of Science And Technology (CHARUSAT) Gujarat Changa 388421 India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Knowledge Corridor Gujarat Gandhinagar 382007 India School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Victoria 3216 Australia Bishop University 2600 College St Sherbrooke J1M 1Z7 QC Canada Crest Data Systems Private Limited Gandhinagar Highway Makarba Gujarat Ahmedabad 380051 India Programmer Analyst Meditab Software Pvt Ltd Kalasagar Mall Ghatlodiya Gujarat Ahmedabad 380061 India

Patients in hospitals frequently exhibit psychological issues such as sadness, pessimism, eccentricity, and anxiety. However, hospitals normally lack tools and facilities to continuously monitor the psychological health of patients. It is desirable to identify depression in patients so that it can be managed by instantly providing better therapy. This can be possible by advances in machine learning for image processing with notable applications in the domain of emotion recognition using facial expressions. In this paper, we have proposed two different methods, i.e. facial expression detection and voice analysis, to predict emotions. For facial expression recognition, we have used two approaches, one is the use of Gabor filters for feature extraction with support vector machine for classification and another is using convolutional neural network (CNN). For voice analysis, we extracted mel-frequency cepstral coefficients from speech data and, based on those features, predicted the emotions of the speech using a CNN model. Experimental results show that our proposed emotion recognition methods obtained high accuracy and thus could be potentially deployed to real-world applications. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CNN Deep learning Expressions Facial emotion Machine learning Speech SVM

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：