检索结果-内蒙古大学图书馆

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Li, Yunchuan Wang, Ziwei Yang, Ruixin Zhao, Yan Zhou, Rui Zheng, Kai University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chengdu China Aalborg University Aalborg Denmark Cloud Database Innovation Lab of Cloud BU Huawei Technologies Co. Ltd. Chengdu China

ISBN: (纸本)9783031306365

Multi-key membership testing refers to checking whether a queried element exists in a given set of multi-key elements, which is a fundamental operation for computing systems and networking applications such as web search, mail systems, distributed databases, firewalls, and network routing. Most existing studies for membership testing are built on Bloom filter, a space-efficient and high-security probabilistic data structure. However, traditional Bloom filter always performs poorly in multi-key scenarios. Recently, a new variant of Bloom filter that has combined machine learning methods and Bloom filter, also known as Learned Bloom Filter (LBF), has drawn increasing attention for its significant improvements in reducing space occupation and False Positive Rate (FPR). More importantly, due to the introduction of the learned model, LBF can well address some problems of Bloom filter in multi-key scenarios. Because of this, we propose a Multi-key LBF (MLBF) data structure, which contains a value-interaction-based multi-key classifier and a multi-key Bloom filter. To reduce FPR, we further propose an Interval-based MLBF, which divides keys into specific intervals according to the data distribution. Extensive experiments based on two real datasets confirm the superiority of the proposed data structures in terms of FPR and query efficiency. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Online 8-Form Tai Chi Chuan Training and Evaluation System Based on Pose Estimation 24

Online 8-Form Tai Chi Chuan Training and Evaluation System B...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Wei, Chunchen Wen, Jingxin Bi, Ran Yang, Huabin Tao, Yanqing Fan, Yuhang He, Yulong Cheng, Didi Zhang, Yanru School of Computer Science and Engineering University of Electronic Science and Technology of China China Sichuan University Jinjiang College China School of Glasgow University of Electronic Science and Technology of China China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China China Chengdu Dishi Technology Co. Ltd. China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

ISBN: (纸本)9798350319934

Exercise at home has already been a common behavior in the current world, especially in the post-COVID-19 era, even some athletes need to do physical fitness at home to keep their state due to the quarantine. So, the importance of online physical training and evaluation is highly increasing. In this work, we build an online 8-form Tai Chi Chuan (TCC) training and evaluation system, which provides a platform for coaches and users to conduct TCC training and evaluation online. Coaches formulate an evaluation rule and upload coaching videos to the platform, then users watch videos online and submit their own recordings, finally, users will get a score of their recordings. To complete this task, we propose a video capture method to record users' sports exercise videos from different perspectives, construct a 3D pose estimation model to identify human pose from captured video, and propose an evaluation model which can judge users' performance and assign a score to each video. To test our proposed models, we make a dataset consisting of key pose frames of TCC, and the key pose frames are extracted from users' TCC exercise videos. We use the dataset to train our models and assign scores to key poses, then compare the results with scores given by professional TCC players. In addition, we add all key pose scores from every single user together and obtain the whole score of an exercise video. The experiment results show that the error between scores assigned by our models and scores given by professional players does not exceed 1.6 in most scoring of a whole exercise video, and Root Mean Square Error (RMSE) is about 0.75 in the scoring of each key pose. © 2022 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Twenty years of e-learning in health science: A bibliometric 7

Twenty years of e-learning in health science: A bibliometric

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Maulana, Fairuz Iqbal Febriantono, M. Aldiki Raharja, Dwi Risza Budi Khaeruddin Herasmara, Ridho Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Diploma III Electronic Technology Vocational Study Program University of Muhammadiyah Malang Indonesia Electrical Engineering Faculty of Science and Technology Raden Rahmat Islamic University Malang Indonesia

Education about health sciences has historically been limited in the curriculum of health professionals and largely inaccessible to the public. In practice, most of the health science education is still running conventionally. Supposedly with the advancement of technology and the use of the internet everywhere, learning such as e-learning can be important, especially in the health sector. Until this research was conducted, only 514 academic documents about e-learning in health sciences were found for 20 years from 2001 to 2020, obtained in searching on the Scopus database. This study presents a comprehensive overview of studies related to E-learning in the Health sciences sector. This study uses bibliometric analysis and indexed digital methods to map scientific publications throughout the world. This research employs the Scopus database to gather information, as well as the Scopus online analysis tool and Vosviewer to show the bibliometric network. The method consists with five stages: determining search keywords, initial search results, refinement of search results, initial compilation, and data analysis. Among the most published and indexed articles by Scopus, papers published by researchers in the United States have the highest number of publications (80), followed by United Kingdom (63) and Australia with 45 academic publications. The processed data shows the pattern and trend of increasing the number of international publications in E-learning in Health sciences field, which Scopus index. © 2022 Elsevier B.V.. All rights reserved.

关键词： Publishing

来源：评论

学校读者我要写书评

暂无评论

Temporal-guided Mixture-of-Experts for Zero-Shot Video Question Answering

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Qin, Yixin Zhao, Lei Gao, Lianli Zhang, Haonan Zeng, Pengpeng Shen, Heng Tao University of Electronic Science and Technology of China Center for Future Media School of Computer Science and Engineering Chengdu611731 China Sichuan Artificial Intelligence Research Institute Yibin644000 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China Tongji University Department of Information Engineering and Computer Science China

Video Question Answering (VideoQA) is a challenging task in the vision-language field. Due to the time-consuming and labor-intensive labeling process of the question-answer pairs, fully supervised methods are no longer suitable for the current increasing demand for data. This has led to the rise of zero-shot VideoQA, and some works propose to adapt large language models (LLMs) to assist zero-shot learning. Despite recent progress, the inadequacy of LLMs in comprehending temporal information in videos and the neglect of temporal differences, e.g., the different dynamic changes between scenes or objects, remain insufficiently addressed by existing attempts in zero-shot VideoQA. In light of these challenges, a novel Temporal-guided Mixture-of-Experts Network (T-MoENet) for zero-shot video question answering is proposed in this paper. Specifically, we apply a temporal module to imbue language models with the capacity to perceive temporal information. Then a temporal-guided mixture-of-experts module is proposed to further learn the temporal differences presented in different videos. It enables the model to effectively improve the capacity of generalization. Our proposed method achieves state-of-the-art performance on multiple zero-shot VideoQA benchmarks, notably improving accuracy by 5.6% on TGIF-FrameQA and 2.3% on MSRVTT-QA while remaining competitive with other methods in the fully supervised setting. The codes and models developed in this study will be made publicly available at https://***/qyx1121/T-MoENet. © 1991-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Discrete Decoder Based on Adaptive Pixel Clustering for Monocular Depth Estimation

SSRN

引用

SSRN 2024年

作者： Liu, Xuanxuan Tang, Shuai School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China

Monocular depth estimation (MDE) has long been a popular and challenging task. Currently, mainstream methods mainly include regression methods based on geometric constraints and ordinal regression methods based on discretized depth intervals. However, they both overlook the fact that depth values within objects often exhibit some degree of continuity, while depth values between objects exhibit varying degrees of discontinuity. Based on this, we propose a more general approach to monocular depth estimation called APCDepth. This method does not treat MDE as an ordinal regression task but rather as a continuous regression task to ensure the continuity of depth values within objects. To focus on the discontinuity of depth values between objects, we propose an Adaptive Pixel Clustering (APC) module to semantically discretize encoder deep features, and align the discretized feature maps to a larger resolution using our proposed Cross-Semantic Alignment (CSA) module. Additionally, to tackle the quadratic complexity issue introduced by Transformers as decoders in depth estimation, we propose a Deformable Feature Pyramid Network (DeFPN) with sparse attention for multi-scale feature fusion. Furthermore, experimental results on the KITTI and NYU datasets validate the effectiveness of APCDepth and demonstrate outstanding performance. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Development of yellow-light TiO2 integrated photonics

引用

Optics Letters 2025年第11期50卷 3489-3492页

作者： Chen, Zequn Tang, Yiheng Wei, Maoliang Li, Xiaojing Sun, Boshu Wu, Yingchun Zou, Sishuo Huang, Ji Si, Ke Gong, Wei Lin, Hongtao Li, Lan Institute of Advanced Technology Westlake Institute for Advanced Study Hangzhou310024 China Zhejiang Key Laboratory of 3D Micro Nano Fabrication and Characterization School of Engineering Westlake University Hangzhou310030 China The State Key Lab of Brain-Machine Intelligence College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China MOE Frontier Science Center for Brain Science & Brain-Machine Integration Zhejiang University Hangzhou310027 China Nanhu Brain-Computer Interface Institute Hangzhou311100 China College of Optical Science and Engineering Zhejiang University Hangzhou310027 China Westlake Institute for Optoelectronics Fuyang Zhejiang Hangzhou311421 China

Visible-light photonic integrated circuits (PICs) are rapidly emerging as a crucial technology to overcome the scaling challenges in quantum information processing and biosensing. Titanium dioxide (TiO2), with its high transparency in the visible range, is regarded as a promising material for facilitating the development of high-performance visible-light integrated systems. In this paper, we introduce a series of passive TiO2 integrated devices, which include waveguides, multimode interferometers (MMIs), and thermo-optic switches (TOSs), monolithically integrated for the first time to our knowledge at a working wavelength of 589 nm. A propagation loss of 5.46 ± 0.17 dB/cm demonstrates a significant improvement over previous reports on yellow-light TiO2 waveguides. This study marks the first fabrication of a TOS operating at 589 nm, featuring a TiO2 core and polymer cladding. Notably, it achieves a power consumption (Pπ) of 8.24 mW, which represents a threefold reduction compared to silicon nitride-based TOSs operating in the visible spectrum. These results offer new insight into the design and fabrication of visible waveguide-integrated devices, paving the way for future emerging applications, such as quantum information, sensors, and biomedical science. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Reduced-Complexity Erasure Decoding of Low-Rate Reed-Solomon Codes Based on LCH-FFT

Reduced-Complexity Erasure Decoding of Low-Rate Reed-Solomon...

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Chen, Chao Lin, Sian-Jheng Li, Zhongwei Cai, Suihua Han, Yunghsiang S. Bai, Bo Xidian University State Key Laboratory of Isn Xi'an China Huawei Technologies Co. Ltd China Sun Yat-sen University School of Computer Science and and Engineering Guangzhou China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study China

ISBN: (纸本)9781665475549

This paper presents a new erasure decoding algorithm for low-rate Reed-Solomon codes (rate = 0.5) based on a recently proposed FFT known as LCH-FFT. The algorithm requires O(n log k) finite field operations, where n and k are the code's length and dimension, respectively. Experiments based on the Intel AVX2 Instructions show that notable improvements in the throughput are achieved compared with the best-known algorithm with complexity O(n log n) (also based on LCH-FFT), and new speed records are created. © 2023 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction

arXiv

引用

arXiv 2024年

作者： Wei, Dongxu Li, Zhiqi Liu, Peidong School of Engineering Westlake University China College of Computer Science and Technology Zhejiang University China Institute of Advanced Technology Westlake Institute for Advanced Study China

Prior works employing pixel-based Gaussian representation have demonstrated efficacy in feed-forward sparse-view reconstruction. However, such representation necessitates cross-view overlap for accurate depth estimation, and is challenged by object occlusions and frustum truncations. As a result, these methods require scene-centric data acquisition to maintain cross-view overlap and complete scene visibility to circumvent occlusions and truncations, which limits their applicability to scene-centric reconstruction. In contrast, in autonomous driving scenarios, a more practical paradigm is ego-centric reconstruction, which is characterized by minimal cross-view overlap and frequent occlusions and truncations. The limitations of pixel-based representation thus hinder the utility of prior works in this task. In light of this, this paper conducts an in-depth analysis of different representations, and introduces Omni-Gaussian representation with tailored network design to complement their strengths and mitigate their drawbacks. Experiments show that our method significantly surpasses state-of-the-art methods, pixelSplat and MVSplat, in ego-centric reconstruction, and achieves comparable performance to prior works in scene-centric reconstruction. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity

arXiv

引用

arXiv 2025年

作者： Chen, Xiaolu Huang, Chenghao Zhang, Yanru Wang, Hao School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Data Science and AI Faculty of IT Monash Energy Institute Monash University MelbourneVIC3800 Australia School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Shenzhen Institute for Advanced Study of UESTC Shenzhen China

The rapid expansion of distributed photovoltaic (PV) installations worldwide, many being behind-the-meter systems, has significantly challenged energy management and grid operations, as unobservable PV generation further complicates the supply-demand balance. Therefore, estimating this generation from net load, known as PV disaggregation, is critical. Given privacy concerns and the need for large training datasets, federated learning becomes a promising approach, but statistical heterogeneity, arising from geographical and behavioral variations among prosumers, poses new challenges to PV disaggregation. To overcome these challenges, a privacy-preserving distributed PV disaggregation framework is proposed using Personalized Federated Learning (PFL). The proposed method employs a two-level framework that combines local and global modeling. At the local level, a transformer-based PV disaggregation model is designed to generate solar irradiance embeddings for representing local PV conditions. A novel adaptive local aggregation mechanism is adopted to mitigate the impact of statistical heterogeneity on the local model, extracting a portion of global information that benefits the local model. At the global level, a central server aggregates information uploaded from multiple data centers, preserving privacy while enabling cross-center knowledge sharing. Experiments on real-world data demonstrate the effectiveness of this proposed framework, showing improved accuracy and robustness compared to benchmark methods. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New EVENODD+ Codes with More Flexible Parameters and Lower Complexity

New EVENODD+ Codes with More Flexible Parameters and Lower C...

引用

IEEE International Symposium on Information Theory

作者： Panyu Zhu Jingjie Lv Yunghsiang S. Han Linqi Song Hanxu Hou Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China School of Electrical Engineering & Intelligentization Dongguan University of Technology Department of Computer Science City University of Hong Kong

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

EVENODD+ codes are binary maximum distance separable (MDS) array codes for correcting double disk failures in RAID-6 with asymptotically optimal encoding/decoding/update complexities. However, the number of bits stored in each disk of EVENODD+ codes should be an odd number minus one. In this paper, we present a new construction of EVENODD+ codes that have more flexible parameters. The number of bits stored in each disk of our codes is an odd minus one times any positive integer. Moreover, our codes not only have asymptotically optimal encoding/decoding/update complexities but also have lower encoding/decoding/update complexities than the existing EVENODD+ codes.

关键词： Codes Complexity theory

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：