检索结果-内蒙古大学图书馆

Dual-Recommendation Disentanglement Network for View Fuzz in Action Recognition

IEEE Transactions on Image Processing 2023年 32卷 2719-2733页

作者： Liu, Wenxuan Zhong, Xian Zhou, Zhuo Jiang, Kui Wang, Zheng Lin, Chia-Wen Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan430070 China Peking University School of Electronics Engineering and Computer Science Beijing100091 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Wuhan University School of Computer Science Wuhan430072 China National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Multi-view action recognition aims to identify action categories from given clues. Existing studies ignore the negative influences of fuzzy views between view and action in disentangling, commonly arising the mistaken recognition results. To this end, we regard the observed image as the composition of the view and action components, and give full play to the advantages of multiple views via the adaptive cooperative representation among these two components, forming a Dual-Recommendation Disentanglement Network (DRDN) for multi-view action recognition. Specifically, 1) For the action, we leverage a multi-level Specific Information Recommendation (SIR) to enhance the interaction among intricate activities and views. SIR offers a more comprehensive representation of activities, measuring the trade-off between global and local information. 2) For the view, we utilize a Pyramid Dynamic Recommendation (PDR) to learn a complete and detailed global representation by transferring features from different views. It is explicitly restricted to resist the fuzzy noise influence, focusing on positive knowledge from other views. Our DRDN aims for complete action and view representation, where PDR directly guides action to disentangle with view features and SIR considers mutual exclusivity of view and action clues. Extensive experiments have indicated that the multi-view action recognition method DRDN we proposed achieves state-of-the-art performance over powerful competitors on several standard benchmarks. The code will be available at https://***/51cloud/DRDN. © 1992-2012 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Learner’s intention analysis to mitigate the cold start problem in personalized learning recommendation systems

引用

Multimedia Tools and Applications 2024年 1-55页

作者： Pal, Saurabh Pramanik, Pijush Kanti Dutta Choudhury, Prasenjit Department of Computer Science and Engineering School of Engineering Brainware University Kolkata India School of Computer Applications and Technology Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science & amp Engineering National Institute of Technology Durgapur West Bengal India

Understanding the learner’s requirements and status is important for recommending relevant and appropriate learning materials to the learner in personalized learning. For this purpose, the learning recommendation system must include the learner’s contextual and behavioral information. However, in the case of cold start problems, the system has no prior information about a new user. Moreover, the system cannot acquire the required information instantly because the automated and instantaneous acquisition of this information is not trivial. This hinders the personalized recommendation for a new learner. Engaging the learner in a questionnaire session may allow the learning system to acquire most of the required information. However, this makes the learner uninterested and disengaged with the system. To address this, we propose a recommendation system for personalized learning that mitigates the cold start problem by acquiring important information by analyzing the learner’s questions submitted to the learning system. By analyzing the meta-information of a question, we identified the learner’s exact requirements, domain and topic knowledge, and expected knowledge gain from the learning material. Ontology, BiLSTM, and context mapping are used for learner modelling and topic classification, and identifying suitable learning materials, respectively. Furthermore, MCDM techniques are used for ranking the learning materials. Our experimental assessment and validation suggest that the information acquired based on our proposed approach is sufficient for understanding a new learner’s needs and suitability and, accordingly, for recommending suitable personalized learning materials. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Dual Spatial-Temporal Feature Pyramid With Decoupled Temporal Mining for Video Semantic Segmentation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Hong, Yuanduo Pan, Huihui Sun, Weichao Wang, Yulei Bian, Ning Gao, Huijun Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China Department of Control Science and Engineering Tongji University Shanghai China Dongfeng Motor Corporation Wuhan China

Semantic segmentation plays a pivotal role in environmental perception for autonomous driving. Video semantic segmentation (VSS) further takes temporal information into consideration for better scene parsing and temporal consistency. Previous research on VSS is mostly dedicated to developing new techniques (e.g. optical flows, attention) to better mine temporal information. In this work, we contribute from a different angle by efficiently incorporating multi-scale temporal information. The dual spatial-temporal feature pyramid is proposed to enable the direct enhancement of multi-scale features for target frames and unlash the design of temporal information mining modules. It contains a spatial feature pyramid from a target frame and a spatial-temporal feature pyramid from multiple reference frames. Building on the dual feature pyramid, we further propose to decouple motional contexts and static contexts to fully leverage temporal information. Specifically, multi-scale motional contexts are mined with the introduced dedicated module and static contexts are enhanced by making temporally fused category-level representations interact with the target frame feature. The final segmentation maps are obtained by regarding the enhanced category-level representations as powerful feature classifiers to classify the target frame feature of rich motional contexts. Experimental results on two popular VSS benchmarks demonstrate that the proposed method with decent parameter and inference efficiency clearly outperforms previous advanced methods. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Surface reconstruction of Se-doped NiS_(2) enables high-efficiency oxygen evolution reaction

引用

Journal of Energy Chemistry 2023年第9期84卷 173-180页

作者： Mengxin Chen Yuanyuan Zhang Ran Wang Bin Zhang Bo Song Yanchao Guan Siwei Li Ping Xu MIIT Key Laboratory of Critical Materials Technology for New Energy Conversion and Storage School of Chemistry and Chemical EngineeringHarbin Institute of TechnologyHarbin 150001HeilongjiangChina National Key Laboratory of Science and Technology on Advanced Composites in Special Environments Harbin Institute of TechnologyHarbin 150001HeilongjiangChina Key Laboratory of Micro-systems and Micro-structures Manufacturing Ministry of EducationHarbin Institute of TechnologyHarbin 150001HeilongjiangChina Institute of Industrial Catalysis School of Chemical Engineering and TechnologyXi’an Jiaotong UniversityXi’an 710049ShaanxiChina

Surface reconstruction of electrocatalysts has been widely witnessed during the electrochemical ***,NiS_(2),NiSe_(2), and Se doped NiS_(2)(Se-NiS_(2)) are fabricated for oxygen evolution reaction(OER) through a mild sulfuration and/or selenylation process of Ni(OH)_(2) supported on carbon cloth(CC).Through careful in-situ Raman spectroscopy and ex-situ X-ray photoelectron spectroscopy,surface reconstruction of NiS_(2),NiSe_(2),and Se-NiS_(2) during the OER process has been revealed.A potentialdependent study shows that Se-NiS_(2) undergoes surface evolution at lower potentials and requires the lowest potential for conversion to NiOOH as a highly OER-active species,accompanied by the leaching of SO_(4)^(2-) and SeO_(4)^(2-) that can again be adsorbed on the catalyst surface to enhance the catalytic *** functional theory(DFT) calculations confirm that Se-NiS_(2) is more susceptible to surface oxidation through the OER ***,Se-NiS_(2) exhibits outstanding OER activity and stability in alkaline conditions,requiring an overpotential of 343 mV at a current density of 50 mA cm^(-2).A novel insight is provided by our work in understanding the surface reconstruction and electrocatalytic mechanism of Ni-based chalcogenides.

关键词： Oxygen evolution reaction Se-NiS_(2) In-situ Raman spectroscopy Anion leaching Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Appearance and motion-based unusual crowd events detection using multiple moving objects

引用

Multimedia Tools and Applications 2024年第42期83卷 90177-90189页

作者： Babu, K. Atlas, L. Godlin Sreeji, S. Arjun, K.P. Rasmi, A. Senthilvel, P. Gururama Computational Intelligence SRM Institute of Science & Technology Chengalpet Kattankulathur603203 India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gitam University Karnataka Bengaluru India Information Science and Engineering RRIT Bangalore India Saveetha University Chennai602 105 India

Unusual crowd analysis is an important problem in surveillance video due to their features cannot be extracted efficiently on the crowd scenes. To overcome this challenge, this paper introduced the appearance and motion based unusual events detection method by using multiple moving objects. This method includes appearance and motion based computation, and moving objects trajectory analysis. By using these all techniques, the unusual crowds and their activities can be obtained by analyzing moving objects size and the distance among multiple moving objects. Two benchmark datasets such as PETS 2009 and UMN are used for the experimental results. Also, several existing algorithms are compared with the proposed method to evaluate the effectiveness of the proposed work. The comparative analysis results proved that the proposed method achieved best accuracy for unusual crowd events. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： And trajectory analysis Appearance based analysis Distance based analysis Unusual crowd events detection

来源：评论

学校读者我要写书评

暂无评论

Role of Artificial Intelligence and Deep Learning in Skin Disease Prediction: A Systematic Review and Meta-analysis

引用

Annals of Data science 2024年第6期11卷 2109-2139页

作者： Nancy, V. Auxilia Osvin Prabhavathy, P. Arya, Meenakshi S. Computer Science and Engineering College of Engineering and Technology SRM Institute of Science and Technology Vadapalani Tamil Nadu Chennai India Institute of Transportation IOWA State University IowaIA United States

Skin is a most essential and extraordinary part of the human structure. Exposure to chemicals such as nitrates, sunlight, arsenic, and UV rays due to pollution and depletion of the ozone layer is causing various skin diseases to spread rapidly. Digital healthcare offers many opportunities to reduce time, and human error, and improve clinical outcomes. However, the automatic recognition of skin disease is a major challenge due to high visual similarity between different skin diseases, low contrast, and large inter variation. Early detection of skin cancer can prevent death. Thus, Artificial intelligence (AI) and Machine Learning (ML) helps the physicians to improve clinical judgment or change manual perception. For skin cancer diagnostics, the ML/AI algorithm can outperform or match professional dermatologists in multiple studies. Different pre-trained architectures such as ResNet152, AlexNet, VGGNet, etc. are used for fusing different skin disease features such as texture, color, etc. and they are also utilized for conducting segmentation tasks. The variations in reflection, lesion size, shape, illumination, etc. often make automatic skin disease classification a complex task. ISIC 2019 and HAM 10000 are the widely used public datasets for skin disease prediction. More technical paper on skin cancer diagnosis is compared in this study. This report examines the majority of technical papers published between 2018 and October 2022 in order to appreciate current trends in the disciplines of skin cancer prediction. A study that combined clinical patient data with deep learning models (DL) increased the accuracy of predicting skin cancer. This article presents a visually attractive and well-organized summary of the current study findings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A wood pulp sponge cleaning wipe as a high-performance bioanode material in microbial electrochemical systems for its vast biomass carrying capacity,large capacitance,and small charge transfer resistance

引用

Journal of Materials science & technology 2024年第14期181卷 1-10页

作者： Pinpin Yang Yaqian Gao Weihua He Jingkun An Jia Liu Nan Li Yujie Feng School of Environmental Science and Engineering Academy of Ecology and EnvironmentTianjin University300072 TianjinChina State Key Laboratory of Urban Water Resource and Environment School of EnvironmentHarbin Institute of TechnologyHarbin 150090China

Microbial electrochemical systems are a promising green and sustainable technology that can transform waste into *** conversion efficiency and lowering system costs,particularly for elec-trodes,are the primary directions that promote practical *** sponges made from wood pulp have been industrially mass-produced in various application scenarios due to their porosity and green *** this study,the three-dimensional(3D)porous cellulose sponges carbon(CSC)was obtained by directly carbonizing cellulose sponges at different temperatures(600,700,800,900,1000,and 1100℃).It has been successfully used as a high-performance anode in microbial fuel cells(MFCs).The carbonization temperature significantly impacted the materials’specific surface area,con-ductivity,and *** greater the anode material’s carbonization temperature,the lower the charge transfer resistance and the higher the maximum power density(CSC-1100,4.1±0.1 W m^(-2)).The CSC-700's maximum power density(3.62±0.11 W m^(-2))was the highest power density reported to date among lignocellulose-based anodes with relatively low energy *** pleated multilayer porous surface promotes microbial adhesion and can build thicker biofilms with the highest biomass of 2661±117μg cm^(-2)(CSC-1100)and containing 86%electrogenic bacteria(Geobacter).To investigate the effect of conducting polymers on the material’s surface,we introduced polyaniline and *** found that the CSC-1000/PPy bioanodes produced a maximum power density(4.18±0.05 W m^(-2)),slightly higher than of without polypyrrole-modified(CSC-1000,3.99±0.06 W m^(-2)),indicating that the CSCs anode surface had excellent electron transfer efficiency and could achieve the same amount of energy as the polypyrrole *** study introduced a promising method for fabricating high-performance anodes using low-cost,industrialized,and sustainable materials.

关键词： Polyaniline Polypyrrol Capacitance anode Electrogenic biofilms Extracellular electron transfer

来源：评论

学校读者我要写书评

暂无评论

Lightweight Adaptive Learning Algorithm for Energy-Latency Tradeoff in IoMT-Enabled Edge Computing 17

Lightweight Adaptive Learning Algorithm for Energy-Latency T...

引用

17th International Conference on Machine Vision, ICMV 2024

作者： Yadav, Rahul Shafiq, Muhammad Kumar, Mohit Wei, Li Elaziz, Mohamed Abd College of Computer Science and Technology Harbin Engineering University Harbin China Cyberspace Institute of Advance Technology Guangzhou University Guangzhou China Department of Information Technology National Institute of Technology Jalandhar India Department of Mathematics Faculty of Science Zagazig University Zagazig Egypt

ISBN: (纸本)9781510688278

Smart Healthcare is witnessing widespread implementation of Internet-of-Medical-Things (IoMT) devices. These devices play a crucial role in collecting vast amounts of data from various smart healthcare applications, which are then processed to facilitate informed decision-making. Edge computing has emerged as a valuable platform offering computational resources to handle this data collection efficiently. However, a critical challenge arises from the inappropriate and inefficient classical approaches to fair resource allocation in these energy-intensive, short battery life and delay-intolerant portable devices. To address this issue, this paper presents a Lightweight Adaptive Learning Offloading Algorithm designed to optimize energy and latency in an edge computing environment. The proposed algorithm formulates the problem as a combined minimization of latency and energy costs while satisfying constraints related to limited battery capacity and service latency deadlines. To achieve this, the algorithm employs the adaptation parameters (α, β, γ), and the tradeoff target (C′) is configured based on the specific task requirements. Experimental results demonstrate the advantages of the proposed scheme, including energy savings and minimized latency in an edge environment. To validate the effectiveness of the proposed scheme under a realistic scenario using the iFogSim2 simulator. © 2025 SPIE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

MFR-CNN: A modified faster R-CNN approach based on bounding box and reliable score for cloth image retrieval

引用

Multimedia Tools and Applications 2024年 1-29页

作者： Kaur, Navneet Pandey, Shreelekha Kalra, Nidhi Department of Computer Science and Engineering Thapar Institute of Engineering & ampTechnology Punjab Patiala147004 India School of Computer Science and Engineering RV University South Karnataka Bangalore560059 India

Today, machine learning is used in a broad variety of applications. Convolution neural networks (CNN), in particular, are widely used to analyze visual data. The fashion industry is catching up to the growing usage of machine learning in a variety of fields throughout the world. The proposed model named MFR-CNN, which is a modified Faster R-CNN approach, has been presented in this manuscript. The effectiveness of an algorithm is validated on cloth attributes by established datasets such as the Deep Fashion dataset and the Fashion Landmark dataset, alongside a new dataset created for the same manually. The proposed model detects clothes using bounding boxes and further classifies them. Apart from this, retrieval functionality has also been added. The effectiveness of the proposed model is evident through the learning rate analysis done for the modules present in the same. On the metrics of accuracy, execution time, and total loss, the model proposed here is contrast with existing techniques named R-CNN, Fast R-CNN, and Faster R-CNN. It is found that MFR-CNN is 50% more accurate in contrast to R-CNN. Also, the accuracy of MFR-CNN is 30% and 7% more accurate than the Fast R-CNN and Faster R-CNN, respectively. Moreover, MFR-CNN is quite effective in contrast to other approaches as it takes less time for execution. It consumes 33 seconds less in contrast to R-CNN. Also, the time taken by the MFR-CNN is 17 seconds and 3 seconds less in comparison to Fast R-CNN and Faster R-CNN, respectively. From the experimental results it is being inferred that the MFR-CNN approach for detecting and classifying clothes is both efficient and effective. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

DDA: Distillation-Driven Acceleration of the Reverse Diffusion Process for Stochastic Multi-Ship Trajectory Prediction

DDA: Distillation-Driven Acceleration of the Reverse Diffusi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Kun Han, Qilong Yao, Jingzheng Wu, Changmao Zhang, Yuntao College of Computer Science and Technology Harbin Engineering University Harbin China Yantai Research Institute Harbin Engineering University Yantai China Institute of Software Chinese Academy of Sciences Beijing China College of Shipbuilding Engineering Harbin Engineering University Harbin China

ISBN: (纸本)9798350368741

Modeling stochastic multi-ship trajectories is vital for maritime safety and interaction efficiency. Recent researches show that diffusion models excel in trajectory prediction, surpassing GANs and VAEs in generation quality, diversity and stability. However, their slow sampling speed remains a major limitation, as producing high-quality trajectories typically requires hundreds of denoising steps. We introduce DDA, a novel method that accelerates multi-ship trajectory generation by distilling the reverse diffusion process, progressively reducing sampling steps by half while minimizing quality loss. We use CVAE-based encoder to map multimodal inputs into state embeddings in the latent space, and use distillation diffusion in the latent space to more quickly and better represent multi-ship trajectories. The diffusion model uses Transformer-based core, and we incorporate SO(2) invariance and equivariance to enhance model representation. Validation on real-world AIS datasets shows that the student model retains high-quality trajectory generation while sampling speed is approximately 30 times faster. © 2025 IEEE.

关键词： Accelerating Sampling AIS Diffusion Model Progressive Distillation VAE

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：