检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yu Chen Xinyuan Qian Zexu Pan Kainan Chen Haizhou Li School of Computer and Communication Engineering University of Science and Technology Beijing (USTB) China Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore Eigenspace GmbH Germany

The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of speakers. In this paper, we present a target speaker localization algorithm with a selective hearing mechanism. Given a reference speech of the target speaker, we first produce a speaker-dependent spectrogram mask to eliminate interfering speakers’ speech. Subsequently, a Long-Short-Term Memory (LSTM) network is employed to extract the target speaker’s location from the filtered spectrogram. Experiments validate the superiority of our proposed method over existing algorithms for different scale-invariant signal-to-noise ratios (SNR) conditions. Specifically, at SNR = -10 dB, our proposed network LocSelect achieves a mean absolute error (MAE) of 3.55° and an accuracy (ACC) of 87.40%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORCEMENT LEARNING FOR VIDEO SUMMARIZATION TASK

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORC...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Phaphuangwittayakul, Aniwat Guo, Yi Ying, Fangli Xu, Wentian Zheng, Zheng Department of Computer Science and Engineering East China University of Science and Technology China National Engineering Laboratory for Big Data Distribution and Exchange Technologies China Shanghai Engineering Research Center of Big Data and Internet Audience China

ISBN: (纸本)9781665438643

With the exponential growth of video data, video summarization techniques are urgently needed for reducing people's efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://***/phaphuang/DSR-RL. © 2021 IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Activity in Untrimmed Videos Using Dense Optical Flow and Deep Neural Network 5

Early Detection of Activity in Untrimmed Videos Using Dense ...

引用

5th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2021

作者： Poonkodi, M. Vadivu, G. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India Big Data Analytics School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9781665435246

computer Vision is playing aremarkable role right from essentials to entertainment and thus trying to turn computer as a 'seeing' machine. Having widespread applications in most of the real world domain like healthcare, surveillance., space and social media, yet it is still challenging to match human intelligence in understanding the underlying context. Recognition of a task performed by human is important to learn the happenings, but predicting it, from the activities' initial subset becomes an aid to overcome adversities in near future. Numerous algorithms and techniques are present, yet a gap exists due to the environment in which it is recorded, illumination condition,overlapping of men and materials on captured scenes *** lead to the requirement of high power computing devices for recognition, which is considerably *** this work, Dense OPnet (Dense optical flow and Convolution neural Net) is proposed which takes in the RGB input video, converted to dense optical flow frames and then fed to three layered CNN for recognition and early detection of an activity using N/2 frames of the total input video. This method is evaluated on two benchmark datasetlike J-HMDB21 and UCF50 giving an accuracy of 93.4% and 74.3% on recognition, 68.2% and 50.24% on early action detection respectively. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Research on the Method of Handling Missing ETC Transaction data 5th

Research on the Method of Handling Missing ETC Transaction D...

引用

5th International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2022

作者： Wu, Songyang Zou, Fumin Guo, Feng Cai, Qiqin Luo, Yongyu Fujian Key Laboratory of Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou350108 China College of Computer and Data Science Fuzhou University Fuzhou350108 China School of Mechanical Engineering and Automation Huaqiao University Xiamen361021 China

ISBN: (纸本)9789819908479

A model based on the random forest is constructed to repair the missing trade times in ETC transaction data. The driving speed and traffic volume characteristics of the vehicles in the ETC transaction data are analyzed, while the driving speed of the missed transaction vehicles, and the distance of the road section where they are located, are combined as input features to repair the missing transaction time. A one-day transaction data of a province is used to test. The analysis results show that the random forest model has a better restoration effect and has a smaller mean absolute error and root mean square error;its mean absolute error is 2.71 s, the highest accuracy among the compared methods, and the data are more accurate and complete after interpolation using the random forest model. This paper suggests that the research based on ETC transaction data should first adopt the processing method in this paper to repair the missing trade time in the transaction data to improve the integrity of the data used and ensure the validity and accuracy of the relevant calculation results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

TezNet: An Efficient Convolutional Neural Network for Optical Coherence Tomography Classification

TezNet: An Efficient Convolutional Neural Network for Optica...

引用

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Muhid Qaiser Muhammad Sohail Abbas Asif Muhammad Khadija Haider Haroon Khan Department of Artificial Intelligence and Data Science National University of Computer and Emerging Sciences Islamabad Pakistan Department of Software Engineering National University of Computer and Emerging Sciences Islamabad Pakistan

ISBN: (数字)9798350355703

ISBN: (纸本)9798350355710

Retinal diseases such as Choroidal Neovascularization (CNV), Drusen, and Diabetic Macular Edema (DME) can severely impair vision and are challenging to reverse if detected late. Optical Coherence Tomography (OCT) serves as a non-invasive imaging modality to diagnose these conditions through cross-sectional retinal images. Current advancements in retinal disease detection predominantly focus on fine-tuning larger models to achieve high accuracy, often at the expense of substantial training time and data requirements. We introduce an innovative Convolutional Neural Network (CNN) named TezNet that is deeper and wider than existing custom CNNs for the dataset used in this research yet maintains a lightweight architecture with only 3.6 million parameters. This high efficiency is accomplished by leveraging depthwise and spatial separable convolutional techniques without employing preprocessing techniques or noise reduction filters. The data augmentation techniques generate diverse image qualities, ensuring robust predictions across various scenarios. By training exclusively on a single dataset, our model achieves rapid training times and optimal resource utilization, minimizing the risk of overfitting. This blend of advanced parameter optimization, minimal preprocessing, and strategic data augmentation underscores the potential of our CNN model for swift, precise, and resource-efficient retinal disease detection. TezNet model achieves a remarkable 96% accuracy, competing closely with state-of-the-art networks like ResNet50 (over 23M parameters), InceptionV3 (over 25M parameters), and ResNeXt (89M parameters).

关键词： Training Accuracy Computational modeling Optical coherence tomography Retina data augmentation data models Convolutional neural networks Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

A Secure Authentication Framework for Consumer Mobile Crowdsourcing Networks

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Aldosary, Abdallah Tanveer, Muhammad Ahmad, Musheer Maghrabi, Louai A. Ahmed, Emad A. Hussain, Amir El-Latif, Ahmed A. Abd Department of Computer Engineering Prince Sattam bin Abdulaziz University Riyadh Wadi Addwasir11991 Saudi Arabia University of Management and Technology Department of Computer Science Lahore54770 Pakistan Jamia Millia Islamia Department of Computer Engineering New Delhi110025 India University of Business and Technology College of Engineering Department of Software Engineering Jeddah Saudi Arabia South Valley University Faculty of Computers and Information Department of Computer Science Qena Egypt Edinburgh Napier University United Kingdom Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Faculty of Science Department of Mathematics and Computer Science Shebin El-Koom32511 Egypt

The Mobile crowdsourcing network (MCN) leverages collaborative intelligence to solve complex tasks through group cooperation. It comprises three main components: the end-user, the service provider, and the mobile user. The end-user requests crowd-sensing and computing services from the service provider, who handles task decomposition, distribution, re-composition, and recommendation. Mobile users perform the crowd sensing and computing tasks. Despite its benefits, MCN faces significant security and privacy challenges. Communications between the service provider and the end-user involve sensitive data, and mobile users and service providers communicate over open channels, making them vulnerable to security threats. To address these concerns, we propose a secure authentication framework for MCN, called SAF-MCN. This framework combines the lightweight cryptographic primitive ' ASCON' with elliptic curve cryptography. SAF-MCN allows the service provider to authenticate mobile users before they join the MCN. Once authenticated, a secure channel is established for encrypted communication over the public Internet. The security of SAFMCN is validated using both formal and informal methods, demonstrating its resilience against potential attacks. The use of Scyther further ensures the security of SAF-MCN. Comparative analysis shows that SAF-MCN is superior in terms of security features, computational efficiency, and communication cost. © 1975-2011 IEEE.

关键词： ASCON Authenticated Encryption Authentication Mobile Crowdsourcing Network Scyther Security

来源：评论

学校读者我要写书评

暂无评论

Towards Visual Taxonomy Expansion

arXiv

引用

arXiv 2023年

作者： Zhu, Tinghui Liu, Jingping Liang, Jiaqing Jiang, Haiyun Xiao, Yanghua Wang, Zongyu Xie, Rui Xian, Yunsen Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Information Science and Engineering East China University of Science and Technology Shanghai China Meituan Shanghai China

Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen terms and the "Prototypical Hypernym Problem." In this paper, we propose Visual Taxonomy Expansion (VTE), introducing visual features into the taxonomy expansion task. We propose a textual hypernymy learning task and a visual prototype learning task to cluster textual and visual semantics. In addition to the tasks on respective modalities, we introduce a hyper-proto constraint that integrates textual and visual semantics to produce fine-grained visual semantics. Our method is evaluated on two datasets, where we obtain compelling results. Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8.75 %. Additionally, our approach performs better than ChatGPT on the Chinese taxonomy dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

MASS FLOW DETECTION TECHNOLOGY FOR SEED AND FERTILISER PARTICLES AND ITS APPLICATION IN UAV-BASED SPREADING

引用

INMATEH - Agricultural engineering 2025年第1期75卷 584-599页

作者： Wang, Yanshuang Song, Cancan Gao, Yongqi Lan, Yubin Wang, Guobin Ming, Rui College of Agricultural Engineering and Food Science Shandong University of Technology Zibo China Shandong University of Technology Sub-center of National Center for International Collaboration Research on Precision Agricultural Aviation Pesticide Spraying Technology Zibo China Research of Institute of Ecological Unmanned Farm Shandong University of Technology Zibo China School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China

The processes of sowing and fertiliser application represent a significant aspect of agricultural production. In order to achieve efficient and precise seeding and fertiliser application, mass flow detection of seed and fertiliser particles can facilitate real-time monitoring and precise decision-making for intelligent seeding and fertiliser application. However, the diversity of seed and fertiliser particle types and particle flow modes presents a challenge for existing detection methods, particularly in meeting the varying operational requirements, especially for particle mass flow detection in low-altitude and high-speed sowing operations of agricultural drones. In such cases, the overlap and flow rate will have a significant impact on the detection results due to the large displacement and the continuous high-throughput dense phase of the particle flow. This paper provides a summary of the existing seed and fertiliser particle mass flow detection techniques and their underlying working principles. It compares the direct detection based on mass with the indirect detection methods based on velocity and concentration, and analyses their respective advantages, disadvantages and applicability. It also explores the possibility of optimising the existing detection methods for the specific needs of agricultural UAVs and considers the potential introduction of cutting-edge science and technology in order to develop an efficient, accurate and convenient detection system to meet the growing market demand. © (2025), (INMA Bucharest). All Rights Reserved.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5731-5748页

作者： Sun, Geng Xiao, Jian Li, Jiahui Wang, Jiacheng Kang, Jiawen Niyato, Dusit Mao, Shiwen the College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China the College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore the School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore the School of Automation Guangdong University of Technology Guangzhou510641 China the Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

—Unmanned aerial vehicles (UAVs) have emerged as the potential aerial base stations (BSs) to improve terrestrial communications. However, the limited onboard energy and antenna power of a UAV restrict its communication range and transmission capability. To address these limitations, this work employs collaborative beamforming through a UAV-enabled virtual antenna array to improve transmission performance from the UAV to terrestrial mobile users, under interference from non-associated BSs and dynamic channel conditions. Specifically, we introduce a memory-based random walk model to more accurately depict the mobility patterns of terrestrial mobile users. Following this, we formulate a multi-objective optimization problem (MOP) focused on maximizing the transmission rate while minimizing the flight energy consumption of the UAV swarm. Given the NP-hard nature of the formulated MOP and the highly dynamic environment, we transform this problem into a multi-objective Markov decision process and propose an improved evolutionary multi-objective reinforcement learning algorithm. Specifically, this algorithm introduces an evolutionary learning approach to obtain the approximate Pareto set for the formulated MOP. Moreover, the algorithm incorporates a long short-term memory network and hyper-sphere-based task selection method to discern the movement patterns of terrestrial mobile users and improve the diversity of the obtained Pareto set. Simulation results demonstrate that the proposed method effectively generates a diverse range of non-dominated policies and outperforms existing methods. Additional simulations demonstrate the scalability and robustness of the proposed CB-based method under different system parameters and various unexpected circumstances. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Markov processes

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：