检索结果-内蒙古大学图书馆

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE 2021年第4期9卷 8-34页

作者： Han, Wei Chen, Jia Wang, Lizhe Feng, Ruyi Li, Fengpeng Wu, Lin Tian, Tian Yan, Jining School of Computer Science China University of Geosciences Wuhan China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of the Ministry of Education China University of Geosciences Wuhan China

Object detection that focuses on locating objects of interest and categorizing them has long played a critical role in the development of remote sensing imagery. Following significant improvements in Earth observation technologies, the objects in high-resolution remote sensing (HRRS) images show additional detailed information and more complex patterns. Some applications, such as urban monitoring, military reconnaissance, and national security, have urgent needs in terms of identifying small-scale (small) and weak-feature-response (weak) objects. However, these kinds of objects usually take up the small proportion of an image that has enough of its own variations in color, shape, and texture so that the objects’ features are easily affected by weather, illumination, and occlusion. These characteristics of small, weak objects make their detection a more challenging task than generic object detection. This article comprehensively reviews the existing challenges and corresponding technologies for addressing that task and its specific problems.

关键词： Object detection Remote sensing Annotations Task analysis Shape Earth Benchmark testing

Acoustic Analysis of Long and Short Vowels of Eastern Yugur Language for Low Resource Speech Synthesis

学校读者我要写书评

暂无评论

Acoustic Analysis of Long and Short Vowels of Eastern Yugur ...

Language Technology and Digital Humanities (LTDH), International Conference on

作者： Shiliang Lyu Hanyun Qi Yuwen Min Qianqian Ma Key Laboratory of Minzu Language and Cultures Intelligent Information Processing Northwest Minzu University Gansu Province Key Laboratory of Linguistic and Cultural Computing Ministry of Education Northwest Minzu University

ISBN: (数字)9798350380187

ISBN: (纸本)9798350380194

The articulation of long and short vowels is not only a change in duration, but also includes changes in the shape of the oral cavity to comprehensively affect the timbre. Since the low-resource phonetic data is very limited, especially the pronunciation of long and short vowels will be affected by the surrounding phonemes or syllables, which makes it difficult for the speech synthesis model to adequately learn and capture the differences of vowels, thus affecting the accuracy and naturalness of the synthesis of long and short vowels. The eastern Yugur language in China belongs to the Mongolian group of the Altaic language family, with an endangered language and limited phonetic resource data. If this endangered language is extinct, it can be restored through speech synthesis. In this article, we analyze the acoustics of long and short vowels in the Eastern Yugur language, and find out the differences in the distribution of acoustic parameters, as well as the differences in the parameters of males and females, so as to provide a reference for the synthesis of the Eastern Yugur language.

关键词： Time-frequency analysis Shape Resonant frequency Training data Phonetics Rhythm Resonance Acoustics Speech synthesis Timbre

Enhancing Online Teaching Effectiveness Through Hand-Raising Detection 4

学校读者我要写书评

暂无评论

Enhancing Online Teaching Effectiveness Through Hand-Raising...

4th International Conference on information Science and Education, ICISE-IE 2023

作者： Zhu, Xiaoke Dong, Zhiwei Chen, Xiaopan Shi, Yufeng Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China

ISBN: (纸本)9798350394610

After the outbreak of the COVID-19 pandemic, online teaching has gradually emerged as an indispensable component of education. Despite its convenience, online education lacks the immediate interactive experience inherent in traditional classrooms. This paper presents a meticulously designed DS-YOLOv8 network model, specifically tailored for real-time recognition of students raising their hands under cameras. On our proprietary dataset, this network model exhibits exceptional accuracy in hand-raising detection, showcasing a 1.3% improvement in the AP50 index compared to the baseline YOLOv8 model. Our focus lies on the application of hand-raising detection within online classrooms with an objective to provide enhanced support for teachers by promptly identifying students raising their hands and thereby improving teaching efficiency while enriching the interactive experience of students in virtual learning environments. © 2023 IEEE.

关键词： Students

A Multi-level Approach to Learning Early Warning based on Cognitive Diagnosis and Learning Behaviors Analysis 26

学校读者我要写书评

暂无评论

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

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

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

ISBN: (纸本)9798350331684

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. © 2023 IEEE.

关键词： Students

Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Mingzhao Su, Shangchao Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world sce narios with labeled data on the server and unlabeled data on the clients. However, existing methods face several challenges such as communication costs, data heterogeneity, and training pressure on client devices. To address these challenges, we introduce the powerful diffusion models (DM) into semi-FL and propose FedDISC, a Federated Diffusion-Inspired Semi supervised Co-training method. Specifically, we first extract prototypes of the labeled server data and use these prototypes to predict pseudo-labels of the client data. For each category we compute the cluster centroids and domain-specific repre sentations to signify the semantic and stylistic information of their distributions. After adding noise, these representations are sent back to the server, which uses the pre-trained DM to generate synthetic datasets complying with the client distribu tions and train a global model on it. With the assistance of vast knowledge within DM, the synthetic datasets have comparable quality and diversity to the client images, subsequently en abling the training of global models that achieve performance equivalent to or even surpassing the ceiling of supervised cen tralized training. FedDISC works within one communication round, does not require any local training, and involves very minimal information uploading, greatly enhancing its prac ticality. Extensive experiments on three large-scale datasets demonstrate that FedDISC effectively addresses the semi-FL problem on non-IID clients and outperforms the compared SOTA methods. Sufficient visualization experiments also illus trate that the synthetic dataset generated by FedDISC exhibits comparable diversity and quality to the original client dataset with a neglectable possibility of leaking privacy-sensitive in formation of the clients. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Chinese Text recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Haiyang Wang, Xiaocong Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text recognition (CTR). Particularly, the characteristic of large categories poses challenges in dealing with zero-shot and few-shot Chinese characters. In this paper, inspired by the way humans recognize Chinese texts, we propose a two-stage framework for CTR. Firstly, we pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS). This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. Subsequently, the learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition through image-IDS matching. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on both Chinese character recognition (CCR) and CTR. The experimental results demonstrate that the proposed method performs best in CCR and outperforms previous methods in most scenarios of the CTR benchmark. It is worth noting that the proposed method can recognize zero-shot Chinese characters in text images without fine-tuning, whereas previous methods require fine-tuning when new classes appear. The code is available at https://***/FudanVI/FudanOCR/tree/main/image-ids-CTR. Copyright © 2023, The Authors. All rights reserved.

关键词： Character recognition

Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Ri He, Ruian Jiang, Xuhao Zhou, Shili Tan, Weimin Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow improvement is limited. In this paper, we develop a Context-Aware Iteration Policy Network for efficient optical flow estimation, which determines the optimal number of iterations per sample. The policy network achieves this by learning contextual information to realize whether flow improvement is bottlenecked or minimal. On the one hand, we use iteration embedding and historical hidden cell, which include previous iterations information, to convey how flow has changed from previous iterations. On the other hand, we use the incremental loss to make the policy network implicitly perceive the magnitude of optical flow improvement in the subsequent iteration. Furthermore, the computational complexity in our dynamic network is controllable, allowing us to satisfy various resource preferences with a single trained model. Our policy network can be easily integrated into state-of-the-art optical flow networks. Extensive experiments show that our method maintains performance while reducing FLOPs by about 40%/20% for the Sintel/KITTI datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical flows

Design and practice of virtual simulation of industrial Internet 4

学校读者我要写书评

暂无评论

Design and practice of virtual simulation of industrial Inte...

4th International Conference on Advances in Computer Technology, information Science and Communications, CTISC 2022

作者： Wu, Qingjin Zeng, Taisheng Zhu, Daxin Cai, Danlin Quanzhou Normal University Laboratory and Equipment Management Office Quanzhou China Quanzhou Normal University School of Mathematics and Computer Science Fujian Provincial Key Laboratory of Data Intensive Computing Quanzhou China Quanzhou Normal University Fujian Provincial Key Laboratory of Data Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Quanzhou China Quanzhou Normal University School of Mathematics and Computer Science Key Laboratory of Intelligent Computing and Information Quanzhou China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

In the cultivating new engineering talents of information discipline, people tend to adopt virtual simulation to simulate production line scenes of enterprises' intelligent manufacturing so as to solve the problem that students fail to go deep into the production lines of industrial fields for scene practice and that they can not collect, analyze and optimize data in the real intelligent manufacturing production lines. The innovative talent training methods which combine regional industries can be used to improve students' ability to analyze, design, debug, operate, maintain and optimize the intelligent manufacturing big data and to master methods and ideas for solving complex engineering problems with big data technology. They can also provide beneficial experience references for the training of new engineering talents of information discipline. © 2022 IEEE.

关键词： Big data

Active Learning with Core-Set Sampling and Scale-Sensitive Loss for 3D Object Detection

学校读者我要写书评

暂无评论

Active Learning with Core-Set Sampling and Scale-Sensitive L...

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

作者： Dejun Zhang Xiaowei Lin Benxin Yi Yiqi Wu Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Information Systems Technology and Design Pillar Singapore University of Technology and Design

Deep learning-based 3D object detectors often require large-scale labeled 3D datasets, which can be expensive to annotate. To tackle this issue, we introduce a core-set sampling strategy within an active learning framework, selecting highly informative data from a data pool to reduce reliance on such datasets. Additionally, we introduce a scale-sensitive loss function into the 3D object detector to mitigate the disparities in the influence of small and large objects on model learning, thereby enhancing the accuracy of small object detection. Our experiments on the KITTI dataset demonstrate that our method achieves comparable results to the baseline using only 20% of the data. Notably, our approach outperforms the baseline in small object detection, with an 8% accuracy improvement for pedestrians and a 4% improvement for cyclists. The source code of the proposed method is available at https://***/djzgroup/al-cs-ssl.

关键词：

One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Mingzhao Su, Shangchao Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

In recent years, One-shot Federated Learning (OSFL) methods based on Diffusion Models (DMs) have garnered increasing attention due to their remarkable performance. However, most of these methods require the deployment of foundation models on client devices, which significantly raises the computational requirements and reduces their adaptability to heterogeneous client models compared to traditional FL methods. In this paper, we propose FedLMG, a heterogeneous one-shot Federated learning method with Local Model-Guided diffusion models. Briefly speaking, in FedLMG, clients do not need access to any foundation models but only train and upload their local models, which is consistent with traditional FL methods. On the clients, we employ classification loss and BN loss to capture the broad category features and detailed contextual features of the client distributions. On the server, based on the uploaded client models, we utilize backpropagation to guide the server’s DM in generating synthetic datasets that comply with the client distributions, which are then used to train the aggregated model. By using the locally trained client models as a medium to transfer client knowledge, our method significantly reduces the computational requirements on client devices and effectively adapts to scenarios with heterogeneous clients. Extensive quantitation and visualization experiments on three large-scale real-world datasets, along with theoretical analysis, demonstrate that the synthetic datasets generated by FedLMG exhibit comparable quality and diversity to the client datasets, which leads to an aggregated model that outperforms all compared methods and even the performance ceiling, further elucidating the significant potential of utilizing DMs in FL. Copyright © 2023, The Authors. All rights reserved.

关键词： Federated learning