检索结果-内蒙古大学图书馆

Video Corpus Moment Retrieval with Query-specific Context Learning and Progressive Localization

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5659-5670页

作者： Zhang, Long Song, Peipei Duan, Zhangling Wang, Shuo Chang, Xiaojun Yang, Xun School of Information Science and Technology Hefei230026 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230026 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Department of Computer Vision Abu Dhabi United Arab Emirates University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition China

Video corpus moment retrieval (VCMR) aims to retrieve a moment from a large corpus of untrimmed videos corresponding to a given language query. However, existing methods often fall short due to their reliance on simple cross-modal attention mechanisms and one-stop localization, which fail to handle the complex multimodal information and large search space effectively. To address these challenges, we propose a novel VCMR method with Query-specific Context Learning and Progressive Localization (QCLPL). First, we construct query-specific multimodal contexts that capture complementary and consistent semantics across subtitles and frames, ensuring informative and efficient context building. We further introduce a semantic contrastive loss to refine these multimodal contexts, filtering out query-irrelevant information. Additionally, we introduce a progressive localization strategy that transforms the moment localization task into a two-stage process. By classifying frames into foreground and background regions, we present a simplified binary classification problem before boundary prediction, constrained by a region-aware loss. This progressive approach leverages region priors to improve subsequent moment localization. Extensive experiments on the TVR and DiDeMo datasets demonstrate that our method significantly outperforms existing approaches, setting a new state of the art for VCMR. © 1991-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Web-Based Tools Validation for Antimicrobial Resistance Prediction: An Empirical Comparative Analysis

引用

SN computer science 2024年第1期5卷 147页

作者： Routray, Sweta Padma Sahoo, Swayamprabha Nayak, Debasish Swapnesh Kumar Shah, Sejal Swarnkar, Tripti Center for Biotechnology Siksha ‘O’ Anusandhan Deemed to be University Bhubaneswar 751003 India Department of Computer Science and Engineering Institute of Technical Education and Research Siksha ‘O’ Anusandhan Deemed to be University Bhubaneswar 751030 India Department of Computer Science and Bioscience Faculty of Technology Marwadi University Gujarat Rajkot 360003 India Department of Computer Application Institute of Technical Education and Research Siksha ‘O’ Anusandhan Deemed to be University Bhubaneswar 751030 India

Antimicrobial resistance (AMR) is a serious threat to global public health, necessitating rapid and precise diagnostic tools. The prevalence of novel antibiotic resistance genes (ARGs) has increased due to microbial sequencing, resulting in the need to extract vital information from vast amounts of data. Although many AMR prediction tools exist, only a few are accurate and scalable. We examined 20 widely used AMR prediction tools and chose 4 web-based tools for antimicrobial resistance surveillance over standalone software due to their easy accessibility, portability, and centralized data management, eliminating the need for complex installation and maintenance. CGE (center for Genomic Epidemiology) provides bioinformatics tools and promotes open data sharing. At the same time, CARD (Comprehensive Antibiotic Resistance Database) is a valuable resource for antibiotic resistance gene information, collectively contributing to our understanding and management of antibiotic resistance. We highlighted web-based AMR prediction tools and performed a case study using the Pseudomonas aeruginosa complete plasmid sequence (CPS) to identify strengths and weaknesses in the system. Our study explored four web-based antibiotic resistance gene prediction tools: ResFinder, KmerResistance, ResFinderFG, and RGI. ResFinder excelled at finding acquired antimicrobial resistance genes as well as maintaining a database up to date. KmerResistance identified resistance genes using k-mer analysis. esFinderFG offered a unique perspective, excelling in detecting a broad range of resistant phenotypes, due to its inclusion of sequences discovered through functional metagenomics. RGI was versatile in detecting a wide range of resistance genes and provided extensive resistance mechanism information. researchers must understand the capabilities and trade-offs of these tools to make well-informed choices for efficient resistance gene identification and surveillance as the antibiotic resistance landsca

关键词： Antibiotic resistance genes (ARGs) Antimicrobial resistance (AMR) KmerResistance ResFinder ResfinderFG

来源：评论

学校读者我要写书评

暂无评论

A 16 nm 140 TOPS/W 5 μj/Inference Keyword Spotting Engine Based on 1D-BCNN

引用

IEEE Transactions on Circuits and Systems II: Express Briefs 2023年第12期70卷 4564-4568页

作者： Lin, Tay-Jyi Ting, Yi-Hsuan Hsu, Meng-Ze Lin, Kuan-Han Huang, Chung-Ming Tsai, Fu-Cheng Sheu, Shyh-Shyuan Chang, Shih-Chieh Yeh, Chingwei Wang, Jinn-Shyan SoC Research Center AIM-HI Department of Computer Science and Information Engineering Chiayi621 Taiwan SoC Research Center AIM-HI Department of Electrical Engineering Chiayi621 Taiwan Hsinchu300 Taiwan Hsinchu310 Taiwan

This brief presents an event-driven keyword spotting (KWS) system for reducing the significant but usually ignored energy dissipations on the 'always-on' A/D converter and microphone. 'Low energy per inference' and 'fast responsiveness' are new design goals of such KWS engine. A 7-layer 1-dimensional binarized convolutional neural network (1D-BCNN) was designed to achieve 95% inference accuracy for detecting 10 keywords, plus silence and unknown, from raw speech, and 64 32-element signed binary inner product units were allocated in the engine to deliver the 4,096 operations/cycle maximum throughput. The 16nm implementation consumes only 0.1mm2 silicon area and 5μJ /inference energy (including memory accesses), while achieving 1.72ms response time. The performance is comparable to state-of-the-art KWS designs without sacrificing number of detectable keywords or inference accuracy. © 2004-2012 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of depression based on audio and video:A review

引用

World Journal of Psychiatry 2024年第2期14卷 225-233页

作者： Meng-Meng Han Xing-Yun Li Xin-Yu Yi Yun-Shao Zheng Wei-Li Xia Ya-Fei Liu Qing-Xiang Wang Shandong Mental Health Center Shandong UniversityJinan 250014Shandong ProvinceChina Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and TechnologyQilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250353Shandong ProvinceChina Department of Ward Two Shandong Mental Health CenterShandong UniversityJinan 250014Shandong ProvinceChina

Depression is a common mental health *** current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression ***-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively *** physicians usually require extensive training and experience to capture changes in these *** in deep learning technology have provided technical support for capturing non-biological *** researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression *** article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.

关键词： Depression recognition Deep learning Automatic depression estimation System Audio processing Image processing Feature fusion Future development

来源：评论

学校读者我要写书评

暂无评论

A Survey of Artificial Hummingbird Algorithm and Its Variants: Statistical Analysis, Performance Evaluation, and Structural Reviewing

引用

Archives of Computational Methods in Engineering 2025年第1期32卷 269-310页

作者： Hosseinzadeh, Mehdi Rahmani, Amir Masoud Husari, Fatimatelbatoul Mahmoud Alsalami, Omar Mutab Marzougui, Mehrez Nguyen, Gia Nhu Lee, Sang-Woong Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Communication and Computer Engineering Faculty of Engineering Cihan University-Erbil Kurdistan Region Iraq Department of Electrical Engineering College of Engineering Taif University Taif21944 Saudi Arabia Department of Computer Engineering College of Computer Science King Khalid University Abha61413 Saudi Arabia School of Computer Science Duy Tan University Da Nang Viet Nam Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam13120 Korea Republic of

In the last few decades, metaheuristic algorithms that use the laws of nature have been used dramatically in numerous and complex optimization problems. The artificial hummingbird algorithm (AHA) is one of the metaheuristic algorithms that was invented in 2022 based on the foraging and migration behavior of the hummingbird for modeling and solving optimization problems. The algorithm initially starts with an initial random population of solutions. It then uses iterative processes and hummingbird position updates to balance exploration and exploitation toward the most optimal solutions. This paper has a detailed and extensive review of the AHA algorithm considering the aspects of hybrid, improved, binary, multi-objective, and optimization problems. In addition, a wide range of applications of AHA in various fields such as feature selection, image processing, scheduling, Internet of Things, classification, clustering, financial and economic issues, forecasting, wireless sensor networks, and many engineering challenges are explored. The statistical and numerical results showed that the AHA algorithm with deep learning methods, Levy flight, and opposition-based learning had the best performance. Also, the AHA algorithm is most widely used in solving multimodal optimization problems and continuous functions. © The Author(s) under exclusive licence to International center for Numerical Methods in Engineering (CIMNE) 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

RP-SWSGD: Design of sliding window stochastic gradient descent method with user’s ratings pattern for recommender systems

引用

Multimedia Tools and Applications 2024年第14期83卷 41083-41120页

作者： Khan, Zeshan Aslam Raja, Hafiz Anis Chaudhary, Naveed Ishtiaq Iqbal, Sumbal Mehmood, Khizer Raja, Muhammad Asif Zahoor Department of Electrical and Computer Engineering International Islamic University Islamabad Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

To offer relevant and useful recommendations, the crucial role of recommender systems in e-commerce industry is to predict the users’ concern for various items by estimating items’ attributes and users’ preferences. The reliability of a recommender system is usually assessed through accuracy and speed of relevant recommendations for a variety of items. The matrix factorization-based stochastic gradient descent (SGD) methods proposed by researchers lack memory needed to capture the ratings history hidden in the previous iterations. Recently, sliding window-based SGD strategies designed for Recommender systems and Hammerstein nonlinear systems gained attention due to the improved performance in terms of convergence speed and estimated accuracy. The memory impact with regard to the historical information enhances the performance of sliding window-based SGD techniques. However, sliding window-based methods are deficient in capturing the ratings history based on the users’ rating patterns. Hence utilizing the same window length for the set of observed ratings rated by users. Therefore, we propose an improved sliding window-based SGD strategy to acquire historical information of the ratings with respect to a user’s rating patterns for efficient matrix factorization of recommender systems. The proposed strategy performs significantly by accomplishing fast convergence speed and accuracy for window sizes greater than 1. The accuracy of the suggested technique is verified for two benchmark datasets such as ML-100 K and Film-Trust. However, the authenticity of the proposed method as compared to the standard counterpart (window size = 1) is confirmed through Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The average improvements achieved by the proposed strategy in terms of RMSE and MAE over the baseline for ML-100 K dataset are 0.726% and 2.245% respectively. Whereas the proposed method accomplishes considerable average improvement of 7.89% and 9.41% for RMSE an

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

CNN-FastText Multi-Input (CFMI) Neural Networks for Social Media Clickbait Classification

引用

Recent Advances in computer science and Communications 2024年第6期17卷 13-24页

作者： Sharma, Chirag Singh, Gurneet Muttum, Pratibha Singh Mahajan, Shubham Department of Computer Science Lovely Professional University Phagwara India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Chandigarh University Mohali India Department of IT Ajeenkya DY Patil University Pune India

Introduction: User-generated video portals, such as YouTube, are facing the challenge of Clickbait. These are used to lure viewers and gain traffic on specific content. The real content inside the video deviates from its title. and a thumbnail. The consequence of this is poor user experience on the platform. Methods: The existing identification techniques either use pre-trained models or are restricted to text only. Other video metadata is not considered. To tackle this situation of clickbait, we propose a CNN-Fast Text Multi-Input (CFMI) Neural Network. The method employs a self-developed convolutional model, combined with different other video metadata. The thumbnail of any video plays a vital role in gathering user attention;hence, it should also be addressed. With greater expressiveness, it depicts and captures the parallels between the title and thumbnail and the video content. Results: This research also compares the proposed system with the previous works on various parameters. With the usage of the proposed network, the platforms can easily analyze the videos during the uploading stage. The future belongs to Post Quantum Cryptography (PWC), we reviewed various encryption standards in this paper. Conclusion: In Industry 4.0, every data bit is crucial and must be preserved carefully. This industry will surely benefit from the model as it will eliminate false and misleading videos from the platform. © 2024, Bentham science Publishers. All rights reserved.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A cross-species foundation model for single cells

引用

细胞研究（英文版） 2024年第12期34卷 818-819页

作者： Korbinian Traeuble Matthias Heinig Institute of Computational Biology German Research Center for Environmental HealthHelmholtz Zentrum MünchenNeuherbergGermany Department of Computer Science TUM School of ComputationInformation and TechnologyTechnical University of MunichGarchingGermany Institute of Computational Biology German Research Center for Environmental HealthHelmholtz Zentrum MünchenNeuherbergGermany Department of Computer Science TUM School of ComputationInformation and TechnologyTechnical University of MunichGarchingGermany German Center for Cardiovascular Research partner site Munich Heart AllianceBerlinGermany

Foundation models in transcriptomics have gained attention due to their ability to generalize across tasks with limited labeled *** builds upon these models by incorporating prior biological knowledge and datasets from both human and mouse cells,enhancing its capacity for cross-species analysis and advancing the field of single-cell transcriptomics.

关键词： cells single model cross-species foundation

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Interaction with Virtual Agents: A Pick-up and Placement Case Study

Multi-modal Interaction with Virtual Agents: A Pick-up and P...

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Bazargani, Jalal Safari Choi, Soo-Mi Sejong University Department of Computer Science and Engineering and Convergence Engineering for Intelligent Drone Xr Research Center Seoul Korea Republic of

ISBN: (纸本)9798331514846

This paper presents a multi-modal human-agent interaction framework that integrates hand tracking, voice commands, user intention interpretation, and scene understanding using large language and vision models for object pick-up and placement tasks in VR. Scene understanding integrates object tags and ChatGPT-4V's object detection. User commands are processed via the LLaMA-3.2 model, which interprets user intention, identifies task and reference objects, and spatial relationships for task execution. An initial experiment with 15 participants showed that the multimodal approach achieved the fastest task completion times and highest user satisfaction. While hand-only interaction was comparable, voice-only interaction was significantly slower. © 2025 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis and Region Detection of CCD Image in Double Delay Three-Step Autocorrelator 4

Fault Diagnosis and Region Detection of CCD Image in Double ...

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Li, Suicheng He, Zizhou Shen, Wenwen Xia, Yanwen Ni, Zhigao Zhou, Xiaowei Institute of Computer Application CAEP Department of Computer Engineering and Science Sichuan Province China Research Center of Laser Fusion CAEP Department of Optical Instrument Sichuan Province China

ISBN: (纸本)9798350324303

With the development of national optical experimental facilities, countries worldwide have invested significant amounts of funding into constructing various facilities. Among them, the double delay three-step autocorrelator is an important instrument for measuring the ultrashort pulse laser waveform and is frequently used in laser experiments. Because electronic instruments are too slow to measure directly, we can only use CCD images to reconstruct the laser waveform. Therefore, CCD, in particular, plays a vital role in the closed-loop control system of double delay three-step autocorrelator, and CCD image quality and processing can directly affect the measurement results of the pulse laser. In this paper, we propose an image feature-based CCD fault diagnosis and effective region detection method for the double delay three-step autocorrelator. This fault diagnosis method first calculates the pixel sum of each row and analyzes the primary pixel distribution of each frame which could represents the main features of CCD image. Next, we design a fault diagnosis model to classify those features and pick out the suitable image. Finally, we analyze and process the above image and design a boundary detection algorithm to detect the effective region for further waveform recovery algorithm. In addition, to verify performance of the proposed method, we conduct a significant number of experiments. Through qualitative and quantitative analyses of the experimental results, we verify the effectiveness and robustness of the proposed method for CCD fault diagnosis. © 2023 IEEE.

关键词： Failure 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：