检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Jinchen Huo Weidong Liu Yang Li Yan Cao College of Computer Science Inner Mongolia University China Institute of Scientific and Technical Information of China China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

As the largest source of technical information around the world, patents are regarded as an essential crystallization and carrier of knowledge and technological innovation. Patent transformation is conducive not only to enhancing economic efficiency, but also to improving productivity and the rational utilization of resources. There is an imbalance between high patent ownership and low transformation rates. We try to predict the occurrence of transformation events from the patent assignment. However, there are some challenges in predicting patent transformation: (1) how to capture transformation features of patents, especially combined with the transfer time factor. (2) how to predict patent transfer time effectively. To address these challenges, a Patent Transfer Time Forecasting Model (PTTFM) is proposed. The model includes: (1) extraction of time-varying features of patents. (2) the patent transfer time is forecast using a Neural Temporal Point Process. By testing the model on patents under different classifications, the experimental results are obtained to show that the proposed model is applicable to predict the timing of patent assignment within a certain time frame, especially one month. Our work may facilitate patent transformation while interpretability is ensured for transformation events.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition

Efficient Robust Principal Component Analysis via Block Kryl...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shun Fang Zhengqin Xu Shiqian Wu Shoulie Xie School of Information Science and Engineering Wuhan University of Science and Technology China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Signal Processing RF & Optical Dept. Institute for Infocomm Research A*STAR Singapore

Robust principal component analysis (RPCA) is widely studied in computer vision. Recently an adaptive rank estimate based RPCA has achieved top performance in low-level vision tasks without the prior rank, but both the rank estimate and RPCA optimization algorithm involve singular value decomposition, which requires extremely huge computational resource for large-scale matrices. To address these issues, an efficient RPCA (eRPCA) algorithm is proposed based on block Krylov iteration and CUR decomposition in this paper. Specifically, the Krylov iteration method is employed to approximate the eigenvalue decomposition in the rank estimation, which requires $O(ndrq+n(rq)^{2})$ for an $(n\times d)$ input matrix, in which $q$ is a parameter with a small value, $r$ is the target rank. Based on the estimated rank, CUR decomposition is adopted to replace SVD in updating low-rank matrix component, whose complexity reduces from $O(rnd)$ to $O(r^{2}n)$ per iteration. Experimental results verify the efficiency and effectiveness of the proposed eRPCA over the state-of-the-art methods in various low-level vision applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

arXiv

引用

arXiv 2022年

作者： Zhu, Hegui Gao, Zhan Wang, Jiayi Zhou, Yange Li, Chengqing The Department of Mathematics College of Sciences Northeastern University Liaoning Shenyang110819 China Key Laboratory of Intelligent Computing and Information Processing Xiangtan University Hunan Xiangtan411105 China

Traditional fine-grained image classification typically relies on large-scale training samples with annotated ground-truth. However, some sub-categories have few available samples in real-world applications, and current few-shot models still have difficulty in distinguishing subtle differences among fine-grained categories. To solve this challenge, we propose a novel few-shot fine-grained image classification network (FicNet) using multi-frequency neighborhood (MFN) and double-cross modulation (DCM). MFN focuses on both spatial domain and frequency domain to capture multi-frequency structural representations, which reduces the influence of appearance and background changes to the intra-class distance. DCM consists of bi-crisscross component and double 3D cross-attention component. It modulates the representations by considering global context information and inter-class relationship respectively, which enables the support and query samples respond to the same parts and accurately identify the subtle inter-class differences. The comprehensive experiments on three fine-grained benchmark datasets for two few-shot tasks verify that FicNet has excellent performance compared to the state-of-the-art methods. Especially, the experiments on two datasets, "Caltech-UCSD Birds" and "Stanford Cars", can obtain classification accuracy 93.17% and 95.36%, respectively. They are even higher than that the general fine-grained image classification methods can *** Codes 68T45 Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Transformer Network for Vehicle Detection

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Tian, Chunwei Liu, Kai Zhang, Bob Huang, Zhixiang Lin, Chia-Wen Zhang, David Harbin Institute of Technology School of Computer Science and Technology Harbin15001 China Macao Special Administrative Region of China PAMI Research Group University of Macau 999078 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu Taiwan School of Data Science Shenzhen518172 China

Stable consumer electronic systems can assist traffic better. Good traffic consumer electronic systems require collaborative work between traffic algorithms and hardware. However, performance of popular traffic algorithms containing vehicle detection methods based on deep networks via learning data relation rather than learning differences in different lighting and occlusions is limited. In this paper, we present a dynamic Transformer network for vehicle detection (DTNet). DTNet utilizes a dynamic convolution to guide a deep network to dynamically generate weights to enhance adaptability of an obtained detector. Taking into relations of different information account, a mixed attention mechanism based channel attention and Transformer is exploited to strengthen relations of channels and pixels to extract more salient information for vehicle detection. To overcome the drawback of difference in an image account, a translation-variant convolution relies on spatial location information to refine obtained structural information for vehicle detection. Experimental results illustrate that our DTNet is competitive for vehicle detection. Code of the proposed DTNet can be obtained at https://***/hellloxiaotian/DTNet. © 2025 IEEE.

关键词： Dynamic convolution Hybrid Attention Mechanism Transformer Vehicle Detection

来源：评论

学校读者我要写书评

暂无评论

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

arXiv

引用

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Parameterized Algorithms for Fixed-Order Book Drawing with Bounded Number of Crossings per Edge 14th

Parameterized Algorithms for Fixed-Order Book Drawing with B...

引用

14th International Conference on Combinatorial Optimization and Applications, COCOA 2020

作者： Liu, Yunlong Chen, Jie Huang, Jingui Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

ISBN: (纸本)9783030648428

Given a graph G= (V, E) and a fixed linear order of V, the problem fixed-order book drawing with bounded number of crossings per edge asks whether there is a k-page book drawing of G such that the maximum number of crossings per edge is upper-bounded by an integer b. This problem was posed by Bhore et al. (GD 2019;J. Graph Algorithms Appl. 2020) and thought to be interesting for further investigation. In this paper, we study the fixed-parameter tractable algorithms for this problem. More precisely, we show that this problem parameterized by both the bounded number b of crossings per edge and the vertex cover number τ of the graph admits an algorithm running in time (b+2)O(τ3)·|V|, and this problem parameterized by both the bounded number b of crossings per edge and the pathwidth κ of the vertex ordering admits an algorithm running in time (b+2)O(κ2)·|V|. Our results provide a specifical answer to Bhore et al.’s question. © 2020, Springer Nature Switzerland AG.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

A Short Flows Fast Transmission Algorithm Based on MPTCP Congestion Control 6th

A Short Flows Fast Transmission Algorithm Based on MPTCP Con...

引用

6th International Conference on Artificial Intelligence and Security, ICAIS 2020

作者： Zhong, Hua Dong, PingPing Tang, WenSheng Yang, Bo Xie, JingYun Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

ISBN: (纸本)9783030578831

With the development of cloud computing and big data technology, traffic in the network presents new features. Real-time online interactive applications are increasing, mainly including web services, instant messaging, online commerce, advertising systems. They have very stringent latency requirements. However, the data traffic generated by data backup, movie download, data mining require high bandwidth. When large and small flows are transmitted concurrently, a series of problems will arise. MPTCP treats long and short flows equally. In this way, packets of long flows will preempt bandwidth at the bottleneck link, fill the router’s whole queue buffer. This will cause the short flows transmission timeout. To solve these problems, we propose a novel algorithm named MPTCP-SPTA (MPTCP short flows fast transmission algorithm). The algorithm give high priority to short flows based on the congestion control algorithm, then introduce the Explicit Congestion Notification mechanism(ECN) in MPTCP. Through extensive network simulator (NS-3) simulations, we demonstrate that MPTCP-SPTA outperforms TCP and MPTCP in three typical network topology, which can significantly reduce the completion time of the small flow and effectively improving the total throughput of the network. © 2020, Springer Nature Switzerland AG.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Feiyu Wang Jian-Tao Zhou Xu Guo College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme’s safety and do simulation experiments to show that the scheme has practicality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extract Features from Lithium-Ion Battery Electrochemical Impedance Spectra and Estimate State of Health Based on Improved Convolutional Autoencoder-Temporal Convolutional Network

SSRN

引用

SSRN 2024年

作者： Wang, Kai Lou, Cheng Wang, Shi Li, Zhaoting School of Electrical Engineering Weihai Innovation Research Institute Qingdao University Qingdao266000 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Engineering Brown University ProvidenceRI02912 United States Shandong Suoxiang Intelligent Technology Co. Ltd Weifang261101 China

Predicting the State of Health (SOH) of batteries is crucial for understanding their remaining lifespan and formulating more effective maintenance and management strategies. Utilizing electrochemical impedance spectroscopy (EIS) to assess the health status of batteries offers advantages such as high precision, rapid response, non-invasiveness, and reliability for accurately forecasting the remaining lifespan of batteries. This study introduces an innovative deep learning technique that integrates an improved convolutional autoencoder (ICAE) with a temporal convolutional network (TCN) for extracting unsupervised features from 2D imagery derived from EIS data. This approach effectively captures battery feature information closely associated with its operational state. The unsupervised feature extraction process proposed in this work outperforms traditional supervised learning methods, enabling more accurate SOH predictions without reliance on pre-labeled data. Experimental results indicate that the deep learning methodology, employing the unsupervised feature extraction process, achieved a root mean square error (RMSE) of less than 2% in the SOH prediction task, and exhibited a prediction performance enhancement of 55.6% compared to the existing baseline model. © 2024, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

A Multi-level Approach to Learning Early Warning based on Cognitive Diagnosis and Learning Behaviors Analysis

A Multi-level Approach to Learning Early Warning based on Co...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hua Ma Wen Zhao Zixu Jiang Peiji Huang Wensheng Tang Hongyu Zhang Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China College of Information Science and Engineering Hunan Normal University Changsha China Tencent Cloud Computing (Changsha) Co. Ltd School of Business Central South University Changsha China

Learning early warning is of great significance for coping with students' learning risks. The existing research fails in modeling the fluctuation of students' learning states and providing the multi-level early warning for students at different levels. To address them, a new approach of learning early warning is proposed to predict at-risk students in e-learning environment by combining cognitive diagnosis with learning behaviors analysis. In this approach, the students' learning process is modeled from four dimensions, i.e., learning quality, learning engagement, latent learning state, and historical learning performance. The convolutional neural network and long short-term memory network are used to explore the students' latent learning features. Then, the Adaboost algorithm is applied to predict students' learning performance. Based on the predicted performance, the evaluation rules are designed to provide multi-level learning early warning for students. Finally, the experiments demonstrate that the proposed method could predict at-risk students efficiently and accurately.

关键词：

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：