检索结果-内蒙古大学图书馆

2024 8th International Conference on Machine Vision and Information Technology, CMVIT 2024

作者： Wu, Yingbin Zhao, Peng Zhou, Mingquan Geng, Shengling Zhang, Dan School of Computer Science Qinghai Normal University Qinghai Xining China School of Mathematics and Information Technology Yuncheng University Shanxi Yuncheng China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining China

An edge detection technology based on the combination of non-downsampling contour wave transform (NSCT) and tensor voting is proposed, which aims to obtain more accurate and detailed edge information of buildings in remote sensing images. Firstly, NSCT is used for image decomposition to obtain the subband frequency information of different scales and angles. Then, position encoding is performed on these subband coefficients to obtain second-order symmetric tensors at the corresponding positions. Tensors of different scales and angles at the same position are weighted and summed to complete feature fusion. Finally, the edge features of the image are obtained based on tensor voting theory. The experimental results show that compared to common edge detection technologies, such as Canny, Fast Edge (Fast edge detection using structured forests) and HED (Holistically-Nested Edge Detection), our method can more accurately and intensively reflect the boundaries of buildings and the edge information of roofs, providing better support for the analysis of building types and architectural styles. Compared to the HED method, which is based on deep learning, our method improves PSNR and SSIM metrics by 0.98 and 0.03, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Bridging The Domain Gap Arising from Text Description Differences for Stable Text-To-Image Generation

Bridging The Domain Gap Arising from Text Description Differ...

引用

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

作者： Tian Tan Weimin Tan Xuhao Jiang Yueming Jiang Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

Generating high-quality images that conform to the semantics of captions has numerous potential applications. However, text-to-image generation is a challenging task due to its cross-modality nature. Current generative models are typically unstable, meaning that complex sentences can result in poor image quality. In this paper, we propose a novel model to bridge the domain gap arising from sentence complexity to achieve stable text-to-image generation. Our model includes two key modules, the attribute extraction module and the attribute fusion module. These modules can extract attributes from the captions and fuse them with image features to encourage the model to accurately understand the semantics. Our modules are plug-and-play and extensive experiments demonstrate that our approach outperforms the state-of-the-art GAN model. Our code and trained model are available at https://***/tantian21/stable-t2i-generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time 6-DoF Object Pose Estimation Network Based on 2D-3D Coordinate Correspondence 3rd

Real-Time 6-DoF Object Pose Estimation Network Based on 2D-3...

引用

3rd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2023

作者： Li, Shuai Chen, Jinlong Yang, Minghao Su, Jianhua Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guangxi Guilin541004 China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guangxi Guilin541004 China Beijing100190 China HuaiRou Beijing101400 China Beijing100190 China

ISBN: (纸本)9789819721993

Object 6D pose estimation is essential for a variety of applications, including autonomous driving, robotic manipulation, and automated harvesting. Due to the influence of different lighting conditions and occlusions, objects with different poses may exhibit significant variations in appearance in different views. This makes the estimation of the 6D pose of objects from a single RGB image a challenging task. This paper proposes a deep learning network capable of simultaneously detecting and estimating the 6D pose (3D rotation + 3D translation) of target objects. As establishing a large-scale dataset using real data is extremely challenging, this paper introduces an automatic collection scheme based on virtual data generated from real images. We conducted experiments on the generated astronaut dataset using our data collection scheme for 6D pose estimation. The experimental results show that the accuracy of 6D pose estimation based on the ADD metric is 96%. Therefore, this method has significant potential and can be extended to other downstream tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LinWA:Linear Weights Attention for Time Series Forecasting

LinWA:Linear Weights Attention for Time Series Forecasting

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qiang Li Jiwei Qin Dezhi Sun Fei Shi Daishun Cui Jiachen Xie School of Computer Science and Technology Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Transformer has achieved excellent results in the field of time series forecasting. However, some recent studies have pointed out that the existing Transformer models are ineffective in preserving the temporal order information. To solve this problem, we propose a Linear Weighted Attention mechanism (LinWA), a new, simple, and effective attention weights calculation method. Linwa calculates the linear weights and the attention weights, respectively, and combines them to reduce the proportion of the original attention weights to use the order information effectively and improve the forecasting performance. Additionally, we introduce an adaptive parameter adjustment mechanism to adjust the proportion between linear weights and attention weights dynamically. Experimental results on six publicly available datasets show that LinWA preserves temporal order well and improves performance on many Transformer models.

关键词： Adaptation models Attention mechanisms Time series analysis Neural networks Benchmark testing Transformers Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on Highly Secure Metaverse Based on Extended Reality Under Edge Computing 16th

Research on Highly Secure Metaverse Based on Extended Realit...

引用

16th EAI International Conference on Wireless Internet, WiCON 2023

作者： Fu, Jinrong Liu, Yiwen Yan, Haobo Yang, Yahui Peng, Ling Shi, Yuanquan Feng, Tao School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China School of Foreign Languages Huaihua University Huaihua418000 China

ISBN: (纸本)9783031580529

With the explosion of ChatGPT, the development of artificial intelligence technology ushered in another explosion. Similarly, with the rapid development of extended reality technology and Internet of Things technology, Metaverse will also usher in greater breakthroughs. However, in the development of the extended reality metaverse under edge computing, many security issues will arise. This paper focuses on data security, considering that data will be transmitted and processed between multiple devices and nodes instead of being concentrated in the cloud, which may bring To solve data security issues, relying on the integrated architecture of Metaverse educational applications based on edge computing (MEC), it provides an identity verification and access with higher security and scalability, better performance, and service requirements that meet the current environment Control mechanism solutions, while analyzing other problems that will arise during the development of the extended reality metaverse. Aiming at the security problem on the edge side, a signature authentication scheme is designed based on Elliptic Curve Cryptography (ECC) integrated blockchain encryption technology and the effectiveness of the method is proved. In order to promote the extended reality metaverse under edge computing, it provides a mirror for the application in the field of education under the condition of ensuring data security. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

C3LRSO: A Chinese Corpus for Complex Logical Reasoning in Sentence Ordering 31

C3LRSO: A Chinese Corpus for Complex Logical Reasoning in Se...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guo, Xiaotao Li, Jiang Su, Xiangdong Zhang, Fujun College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (纸本)9798891761964

Sentence ordering is the task of rearranging a set of unordered sentences into a coherent and logically consistent sequence. Recent work has primarily used pre-trained language models, achieving significant success in the task. However, existing sentence ordering corpora are predominantly in English, and comprehensive benchmark datasets for non-English languages are unavailable. Meanwhile, current datasets often insert specific markers into paragraphs, inadvertently making the logical sequence between sentences more apparent and reducing the models' ability to handle genuinely unordered sentences in real applications. To address these limitations, we develop C3LRSO, a high-quality Chinese sentence ordering dataset that overcomes the aforementioned shortcomings by providing genuinely unordered sentences without artificial segmentation cues. Furthermore, given the outstanding performance of large language models on NLP tasks, we evaluate these models on our dataset for this task. Additionally, we propose a simple yet effective parameter-free approach that outperforms existing methods on this task. Experiments demonstrate the challenging nature of the dataset and the strong performance of our proposed method. These findings highlight the potential for further research in sentence ordering and the development of more robust language models. Our dataset is freely available at https://***/JasonGuo1/C3LRSO. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance for Class Incremental Learning in Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Hao, Xuze Ni, Wenqian Jiang, Xuhao Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios, there’s a common need to continuously learn about new diseases, leading to the emerging field of class incremental learning (CIL) in the medical domain. Typically, CIL suffers from catastrophic forgetting when trained on new classes. This phenomenon is mainly caused by the imbalance between old and new classes, and it becomes even more challenging with imbalanced medical datasets. In this work, we introduce two simple yet effective plug-in methods to mitigate the adverse effects of the imbalance. First, we propose a CIL-balanced classification loss to mitigate the classifier bias toward majority classes via logit adjustment. Second, we propose a distribution margin loss that not only alleviates the inter-class overlap in embedding space but also enforces the intra-class compactness. We evaluate the effectiveness of our method with extensive experiments on three benchmark datasets (CCH5000, HAM10000, and EyePACS). The results demonstrate that our approach outperforms state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Log anomaly detection based on parallel fusion of CNN and GRU

Log anomaly detection based on parallel fusion of CNN and GR...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Cheng Li Jiaqing Mo Gang Zhou Guangming Li Xinjiang Key Laboratory of Signal Detection and Processing School of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

With the development of deep learning and big data technology, system log anomaly detection technology has received widespread attention. Although many methods have achieved good results in anomaly detection in logs, it remains an extremely difficult task mining the rich dependencies hidden within log data from both global and local perspectives. In this paper, we propose a multi-scale parallel fusion network based on GRU and CNN, which more comprehensively captures the overall dependencies of log data. Specifically, we employ BERT to semantize the preprocessed log sequences, subsequently feeding the semantic vectors into the neural networks of a dual-branch CNN and a variant GRU. This approach enables the capture of both local and global features of the log sequences. Finally, we parallelly fuse the outputs of the dual-branch CNN and variant GRU. We conduct extensive experiments and evaluate three well-known benchmark datasets, BGL, Thunderbird, and Spirit. The results show that our method is better than other methods.

关键词： Deep learning Fuses Neural networks Semantics Network architecture Big Data Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection in SAR images via Gaussian Flow Class-Balanced Differential Aggregation

Few-Shot Object Detection in SAR images via Gaussian Flow Cl...

引用

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Po Zhao Jie Chen Chaochen Zhang Ke Ma Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electronics and Information Engineering Anhui University Hefei China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Currently, few-shot object detection (FSOD) methods for synthetic aperture radar (SAR) images are severely understudied. The high confidentiality and scarcity of SAR data, coupled with the susceptibility of targets in SAR images to significant changes in orientation, make existing models sensitive to variations in novel class examples. This sensitivity leads to challenges in extracting class prototypes and accurately estimating class centers for novel classes. To solve the above issues, we propose a few-shot object detection algorithm for SAR images via Gaussian Flow Class-Balanced Differential Aggregation. Specifically, we first design a class-balanced difference feature aggregation module to solve the problems of difficult class distribution estimation and inaccurate class center estimation of novel classes in SAR images. Second, the contextual information perception module is designed to extract the most representative support features into fine-grained prototypes and aggregate them with the query features using the matching paradigm to solve the imbalance between foreground targets and background in SAR images. Finally, experimental results on MSAR-AIR dataset indicate that our model realizes the best detection properties on SAR images compared to existing models.

关键词： Representation learning Sensitivity Prototypes Estimation Object detection Interference Feature extraction Radar polarimetry Data models Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Multiband Kick Drum Separation with Genre-Guided Optimization 10th

Multiband Kick Drum Separation with Genre-Guided Optimizati...

引用

10th Conference on Sound and Music Technology, CSMT 2023

作者： Li, Si Jiang, Yuanfeng Wang, Zhaowen Qian, Jiale Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China Department of Music AI and Information Technology Central Conservatory of Music Beijing100091 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

Kick drum plays an important role in electronic music. When hearing an excellent kick drum sound from a reference music track, music production beginners always feel confused about how it will sound if we solo the kick track and why it sounds perfect in a specific song. Reproducing the kick of a music track is not easy even for professional producers and arrangers. To investigate the ability of artificial intelligence in separating kick-drum sounds, in this paper we propose an end-to-end system which is capable of separating multi-genre high-quality electronic kick drum clips from mixed song tracks. Unlike most of the previous music source separation tasks, we only focus on the electronic kick drum rather than the whole percussion track. First, we design a multiband data representation approach for non-pitched percussions such as kick drums, then adopt a multi-discriminator module trained on a multi-genre kick drum corpus to further optimize the separated kick sound. To the authors’ knowledge, this study marks the first attempt at kick drum separation with stylistic optimization. Objective and subjective evaluations demonstrate that joint multiband representation and genre-guided optimisation can form a high-performance framework, showing a promising solution to the kick drum separation task. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Source separation

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：