检索结果-内蒙古大学图书馆

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Xin Miao Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

Spatiotemporal action detection relies on the learning of video spatial and temporal information. The current state-of-the-art convolutional neural network-based action detectors have achieved remarkable results using 2D CNN or 3D CNN architectures. However, due to the complexity of the network structure and spatiotemporal information perception, these methods are usually used in a non-real-time, offline manner. The main challenge of spatiotemporal action detection is to design an effective detection network architecture and effectively perceive the fused spatiotemporal features. Aiming at the above problems, our paper proposes a real-time action detection method based on multi-scale spatiotemporal feature. Aiming at the problem that only 2D or 3D backbone network cannot effectively model spatiotemporal features, we extract spatiotemporal features by multi-branch feature extraction networks respectively. For the lack of descriptiveness of single-scale spatiotemporal features, a multi-scale spatiotemporal feature-aware attention network is proposed to learn long-term temporal dependencies and spatial context information. And the fusion between temporal and spatial features is guided by fusion attention to highlight more discriminative spatiotemporal feature representations. The proposed method achieves 82.59% and 78.30% accuracy on two spatiotemporal action datasets UCF101-24 and JHMDB-21, respectively and reaching 73 frames/s.

关键词： Solid modeling Computer vision Three-dimensional displays Machine learning Detectors network architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Gong-Si-Shaped Heterogeneous Circular-Polarization Array for 5G Application 5

A Gong-Si-Shaped Heterogeneous Circular-Polarization Array f...

引用

5th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2022

作者： Zhou, Wei Qi, Junwei Li, Yingsong Huang, Zhixiang Yang, Lixia College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

In this work, a Gong-Si-shaped circularly polarized (CP) array with power driver for 5G is proposed. The radiator of the constructed CP array consists of two Chinese-like characters ' and '' with the similar size and pronunciation of 'gong' and 'si', Two L-shaped feeding probes of the same size are connected to the designed power driver printed on the bottom layer of ground plate, and the array can radiate circular polarization electromagnetic waves by changing the positions of the L-shaped probes and the angle of the horizontal parts of the L-shaped probes. From the simulating and optimizing, it is finally obtained that the -15 dB bandwidth of modeled Gong-Si-like CP antenna lies in 2.49 - 2.81 GHz and the presented Gong-Si-like CP antenna has a axial bandwidth covering 2.36 - 2.82 GHz, which meets the n41 5G band implementing at 2.515 - 2.675 GHz. © 2022 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Learning Interaction Detection 24

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Lear...

引用

33rd ACM Web Conference, WWW 2024

作者： Ma, Haiping Yang, Yong Qin, Chuan Yu, Xiaoshan Yang, Shangshang Zhang, Xingyi Zhu, Hengshu Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin PBC School of Finance Tsinghua University Beijing China School of Artificial Intelligence Anhui University Anhui Hefei China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin Beijing China

ISBN: (纸本)9798400701719

Knowledge tracing (KT) is a crucial task in online learning, aimed at tracing and predicting each student's knowledge states throughout their learning process. Over the past decade, it has garnered widespread attention due to it provides the potential for more tailored and adaptive online learning experiences. Although most current KT methodologies emphasize optimizing network structures to enhance predictive accuracy for future student performance, they often neglect anomalous interactions in students' learning processes, which may arise from low data quality (i.e., inferior question quality) and abnormal student behaviors (i.e., guessing and mistakes). To this end, in this paper, we propose a novel framework, termed HD-KT, designed to enhance the robustness of existing KT methodologies with Hybrid learning interactions Denoising approach. Specifically, we introduce two detectors for anomalous learning interactions, namely knowledge state-guided anomaly detector and student profile-guided anomaly detector. In the first detection module, we design a sequential autoencoder to identify anomalous learning interactions by detecting atypical student knowledge states. In the second module, we incorporate an attention mechanism by modeling a student's long-term profile to capture irregular interactions. Extensive experiments on four real-world benchmark datasets have decisively shown our HD-KT markedly boosts the robustness of numerous prevailing KT models, consequently increasing the accuracy of future student performance predictions. Additionally, our case studies highlight the versatility of HD-KT in addressing diverse downstream tasks, such as exercise quality analysis and learning behavior-based student clustering. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Entity Alignment Algorithm Based on Ontology Enhancement and Multi-Feature Fusion

An Entity Alignment Algorithm Based on Ontology Enhancement ...

引用

Frontiers Technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Hao Song Yuxia Lei Kangli Zi Fuyuan Quan Tianhang Zhang Qi Li School of Computer Science Qufu Normal University Rizhao Shandong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Entity alignment plays a crucial role in the integration of knowledge graphs. However, current knowledge graphs often suffer from inconsistent construction standards, structural heterogeneity, and imprecise semantic representation of entities, which can lead to suboptimal embedding of structural information. Moreover, most existing entity alignment methods rely heavily on structural information, which limits alignment efficiency. To address these challenges, this paper presents Onto-IMF, an ontology-enhanced entity alignment method based on multi-feature fusion. This approach aims to enhance the semantic representation of entities by incorporating ontology information, thereby reducing structural discrepancies among heterogeneous graphs and improving the embedding of structural information. The multi-feature fusion entity alignment leverages diverse semantic features, including relations, attributes, and entity names, to achieve more accurate alignment. Experimental results on various DBP15K subsets indicate that the proposed method achieves Hits@l scores of 86.6%, 93.0%, and 97.7%, respectively, representing an average improvement of 7.9 % over the best-performing baseline models.

关键词： Accuracy Semantics Knowledge graphs Contrastive learning Ontologies Data models Standards

来源：评论

学校读者我要写书评

暂无评论

Leveraging Knowledge Distillation for Improved Event Extraction in QA Models

Leveraging Knowledge Distillation for Improved Event Extract...

引用

Frontiers Technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Peiyao Zhou Zhikui Hu Kangli Zi Dawei Zhang School of Computer Science Jiangsu University of Science and Technology Zhenjiang China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Event extraction is an important task in natural language processing, and it is widely utilized in intelligence domains such as business and military for information extraction. Recently, many works have successfully transformed document-level event extraction into Question-answering (QA) tasks with remarkable results. This approach embeds event argument information within the questions, introducing prior knowledge into the process. Jin et al. highlighted the importance of high-quality QA pairs for practical QA tasks, emphasizing that constructing these pairs remains a key challenge[1]. In this study, we propose a Prompt-based question generation method to automatically generate questions containing event arguments, which converts event extraction into a QA task. We introduce an event ontology-based information retrieval module to enhance answer accuracy and select the most relevant document segments as input text. Additionally, we employ knowledge distillation to build the QA model, transferring knowledge from a large pre-trained model to a more compact and efficient one, improving the student model's performance. Experiments show that our model performs strongly in mainstream benchmarks, with 4.8 improvements on WikiEvents.

关键词： Accuracy Benchmark testing information retrieval Question generation Question answering (information retrieval) Data mining Business

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection and Defense Based on FLAD and SDN

DDoS Detection and Defense Based on FLAD and SDN

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Jie Dong Wenyu Fang Wanling Zheng Jinkun Liu Yanhua Liu College of Computer and Data Science Fuzhou University Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

In order to achieve more efficient and accurate DDoS detection while ensuring data privacy, this paper proposes a DDoS detection method based on FLAD. Firstly, this paper uses the FLAD algorithm to train a global DDoS detection model without leaving local traffic data, protecting the privacy and security of traffic data between different hosts, and improving aggregation efficiency by dynamically adjusting the aggregation weights to adapt to different sub-dataset increments. Secondly, a DDoS traffic detection method based on the integration of LSTM and CNN is proposed, which extracts and analyzes the temporal correlation of traffic data by calculating the statistical characteristics of traffic data within a time period, to achieve real-time detection of traffic feature data. Again, combined with the concept of SDN, real-time defense against DDoS based on ODL-API is implemented, and precise matching of DDoS detection results with network entity information is achieved, realizing the technology of real-time and precise issuance of multiple flow rules, effectively blocking DDoS malicious attack traffic, protecting important entities in the topology, and maintaining stable traffic in the topology. This paper focuses on solving the detection problem of DDoS traffic data increments and uneven data distribution through the FLAD algorithm. Experimental results show that the proposed method improves the accuracy of DDoS attack detection by more than 4% and the F1 Score by more than 7% compared to the FedAvg aggregation algorithm.

关键词： Training Data privacy network topology Denial-of-service attack Feature extraction Real-time systems Topology Labeling Computer crime Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Introduction and Analysis of M-TSLand: A Multi-Temporal and Multi-Scale Remote Sensing Farmland Dataset 23

Introduction and Analysis of M-TSLand: A Multi-Temporal and ...

引用

6th International Conference on Big Data Technologies, ICBDT 2023

作者： Zang, Junyuan Zhang, Yuqian Xu, Tao Han, Mingzhi Xiao, Chenxin School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China NO.1 Geological Team of Shandong Provincial Bureau of Geology and Mineral Resources Jinan250001 China

ISBN: (纸本)9798400707667

Farmland is an important resource for human survival and development. intelligent segmentation of farmland using remote sensing is an effective measure to protect farmland. (1) However, farmland present different states during different seasons, such as appearing green in winter or spring and appearing yellow in autumn, which pose challenges for segmentation models. (2) Segmentation of remote sensing imagery at different resolutions also poses challenges. To address this issue, this paper proposes a multi-temporal and multi-scale remote sensing farmland dataset(M-TSLand). This dataset were constructed based on 1m and 2m resolutions, respectively, and images were extracted from different seasons. To validate the effectiveness of the dataset, we used some mainstream segmentation models such as SegNext, DeepLabV3+, etc., and achieved mIoU of 67.65%, 66.09%, which provide a research basis for the generalization of the model as well as a high accuracy rate. © 2023 ACM.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection

arXiv

引用

arXiv 2024年

作者： Zhou, Pengfei Min, Weiqing Song, Jiajun Zhang, Yang Jiang, Shuqiang The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China The Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou215124 China

Food computing brings various perspectives to computer vision like vision-based food analysis for nutrition and health. As a fundamental task in food computing, food detection needs Zero-Shot Detection (ZSD) on novel unseen food objects to support real-world scenarios, such as intelligent kitchens and smart restaurants. Therefore, we first benchmark the task of Zero-Shot Food Detection (ZSFD) by introducing FOWA dataset with rich attribute annotations. Unlike ZSD, fine-grained problems in ZSFD like inter-class similarity make synthesized features inseparable. The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories. To address these problems, we propose a novel framework ZSFDet to tackle fine-grained problems by exploiting the interaction between complex attributes. Specifically, we model the correlation between food categories and attributes in ZSFDet by multi-source graphs to provide prior knowledge for distinguishing fine-grained features. Within ZSFDet, Knowledge-Enhanced Feature Synthesizer (KEFS) learns knowledge representation from multiple sources (e.g., ingredients correlation from knowledge graph) via the multi-source graph fusion. Conditioned on the fusion of semantic knowledge representation, the region feature diffusion model in KEFS can generate fine-grained features for training the effective zero-shot detector. Extensive evaluations demonstrate the superior performance of our method ZSFDet on FOWA and the widely-used food dataset UECFOOD-256, with significant improvements by 1.8% and 3.7% ZSD mAP compared with the strong baseline RRFS. Further experiments on PASCAL VOC and MS COCO prove that enhancement of the semantic knowledge can also improve the performance on general ZSD. Code and dataset are available at https://***/LanceZPF/KEFS. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

THREE-PRECISION ITERATIVE REFINEMENT WITH PARAMETER REGULARIZATION AND PREDICTION FOR SOLVING LARGE SPARSE LINEAR SYSTEMS

arXiv

引用

arXiv 2025年

作者： Ge, Jifeng Zhang, Juan Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan KeyLaboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This study presents a novel mixed-precision iterative refinement algorithm, GADI-IR, within the general alternating-direction implicit (GADI) framework, designed for efficiently solving large-scale sparse linear systems. By employing low-precision arithmetic, particularly half-precision (FP16), for computationally intensive inner iterations, the method achieves substantial acceleration while maintaining high numerical accuracy. key challenges such as overflow in half-precision and convergence issues for low precision are addressed through careful backward error analysis and the application of a regularization parameter α. Furthermore, the integration of low-precision arithmetic into the parameter prediction process, using Gaussian Process Regression (GPR), significantly reduces computational time without degrading performance. The method is particularly effective for large-scale linear systems arising from discretized partial differential equations and other high-dimensional problems, where both accuracy and efficiency are critical. Numerical experiments demonstrate that the use of mixed-precision strategies not only accelerates computation but also ensures robust convergence, making the approach advantageous for various applications. The results highlight the potential of leveraging lower-precision arithmetic to achieve superior computational efficiency in high-performance computing. © 2025, CC BY.

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Automatic Text Summarization Model for Judgment Documents 8th

A Hybrid Automatic Text Summarization Model for Judgment Doc...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Ouyang, Jianquan Huang, Wenpeng Liu, Tianming Key Laboratory of Intelligent Computing Information Processing Ministry of Education School of Computer Science and School of Cyberspace Science Xiangtan University Xiangtan China Department of Computer Science The University of Georgia AthensGA United States

ISBN: (纸本)9783031067662

Judgment documents are the final carrier of judicial trial activities, and they are an indispensable component for assisting sentencing decision-making and standardizing the scale of judgment. At present, the number of public judgment documents in China has reached 120 million, and it does not stop there, which brings a significant challenge for users to obtain useful information. To solve this problem, this paper proposes a hybrid automatic text summarization model for judgment documents. The method is divided into two stages. The first stage is, through extracting abstract technology, to extract key sentences from the original text to form a set of them. In the second stage, the set of key sentences extracted in the previous stage will be copied or rewritten to generate the final summary using the sequence generation model. The ROUGE indexes of this method in the automatic summarization experiment of judgment documents are 59.79, 37.71, and 52.67, which are 5.26, 7.25, and 10.41 higher than the benchmark model UniLM, respectively. The method proposed in this paper can effectively be applied in the automatic summarization service of judgment documents and solve the problem of information overload thereof and, finally, provide a new way for users to gain smooth access to judgment documents and information. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

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：