检索结果-内蒙古大学图书馆

19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2023

作者： Sheng, Xinyi Gu, Jinguang Yan, Youcheng Xu, Fangfang Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan430065 China The Key Lab. of Rich-Media Knowledge Org. and Serv. of Digit. Publ. Content Inst. of Sci. and Tech. Info. of China Beijing100038 China

ISBN: (纸本)9798350304398

Extracting emergency events from a large amount of unstructured information is essential for improving early warning and emergency response. Existing event extraction methods for specialist fields often rely on well-designed syntactic dependencies or external knowledge graphs, which can provide high accuracy in their specialist fields. However, these approaches may have poor generalization capabilities and are difficult to apply directly to the emergency field. In addition, most existing methods ignore the interdependencies between event triggers and event arguments, which may be crucial semantic features for event extraction. To solve these problems, we propose a Chinese emergent event extraction method based on contrastive learning with event semantic features(CNEmergEE). Firstly, the proposed approach automatically expands the pre-trained model's vocabulary on a domain corpus. Then, continuing learning on the same corpus allows the model to complete domain adaptation. Finally, we use contrast learning to enable models to learn semantic representations of events. Experimental results on the CEC (Chinese Emergency Corpus) dataset show that our approach achieves better improvement. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm

arXiv

引用

arXiv 2025年

作者： Xie, Lunchen Lomurno, Eugenio Gambella, Matteo Ardagna, Danilo Roveri, Manual Matteucci, Matteo Shi, Qingjiang The School of Computer Science and Technology Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China Politecnico di Milano Milan Italy The DEIB Politecnico di Milano Milan Italy

Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation selection, and adaptability under varying resource limitations. We introduce ZO-DARTS++, a novel NAS method that effectively balances performance and resource constraints. By integrating a zeroth-order approximation for efficient gradient handling, employing a sparsemax function with temperature annealing for clearer and more interpretable architecture distributions, and adopting a size-variable search scheme for generating compact yet accurate architectures, ZO-DARTS++ establishes a new balance between model complexity and performance. In extensive tests on medical imaging datasets, ZO-DARTS++ improves the average accuracy by up to 1.8% over standard DARTS-based methods and shortens search time by approximately 38.6%. Additionally, its resource-constrained variants can reduce the number of parameters by more than 35% while maintaining competitive accuracy levels. Thus, ZO-DARTS++ offers a versatile and efficient framework for generating high-quality, resource-aware DL models suitable for real-world medical applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LRAE-UNet: Lightweight MRI Brain Tumor Automatic Segmentation Network

SSRN

引用

SSRN 2023年

作者： Wang, Yu Jiahao, Lin Minhua, Liu Beijing Key Laboratory of Big Data Technology for Food Safety School of Artificial Intelligence Beijing Technology and Business University Beijing China

The brain is the important part of central nervous system of the human being where brain tumor seriously threatens human health. For effective treatment, fully automatic brain tumor segmentation is a very significant and challenging work. The currently mainstream segmentation model U-Net makes the three-dimensional medical image discontinuous between the layers, which is unable to balance the information between sparse layers and the one in the dense layer. In this paper, a lightweight residual attention enhanced U-Net, called LRAE-UNet, for fully automatic brain tumor segmentation is proposed which main includes the lightweight residual module, the lightweight attention module, and the enhanced average pooling module. The lightweight residual module is used to solve the problem of gradient disappearance and network degradation when the number of network layers increases. The lightweight attention module can suppress the irrelevant areas and highlight the significant features of specific local areas. The enhanced average pooling module has a larger field of perception which can save computing resources. The experimental results on BraTsXXX database show that the mean accuracy of Dice scores reach 91.24%, 88.64%, and 88.32% respectively on the whole tumor, tumor core, and enhancing tumor segmentation, which proves that the proposed LRAE-UNet is feasible and effective for fully automatic segmentation of brain tumor © 2023, The Authors. All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

RPR-Net: A Point Cloud-Based Rotation-Aware Large Scale Place Recognition Network 1

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Fan, Zhaoxin Song, Zhenbo Zhang, Wenping Liu, Hongyan He, Jun Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Department of Management Science and Engineering Tsinghua University Beijing100084 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (数字)9783031250569

ISBN: (纸本)9783031250552

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three steps. First, we design three kinds of novel Rotation-Invariant Features (RIFs), which are low-level features that can hold the rotation-invariant property. Second, using these RIFs, we design an attentive module to learn rotation-invariant kernels. Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process. By doing so, high-level scene-specific rotation-invariant features can be learned. We call the above process an Attentive Rotation-Invariant Convolution (ARIConv). To achieve the place recognition goal, we build RPR-Net, which takes ARIConv as a basic unit to construct a dense network architecture. Then, powerful global descriptors used for retrieval-based place recognition can be sufficiently extracted from RPR-Net. Experimental results on prevalent datasets show that our method achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

BIFURCATIONS AND INVARIANT SETS FOR A FAMILY OF REPLICATOR MAPS FROM EVOLUTIONARY GAMES

arXiv

引用

arXiv 2024年

作者： Kryzhevich, Sergey Zhang, Yiwei Chmara, Magdalena Institute of Applied Mathematics Faculty of Applied Physics and Mathematics Gdansk University of Technology Gdansk80-233 Poland School of Mathematical Sciences and Big Data Anhui University of Science and Technology Anhui Huainan232001 China

We study the dynamics of a family of replicator maps, depending on two parameters. Such studies are motivated by the analysis of the dynamics of evolutionary games under selections. From the dynamics viewpoint, we prove the existence of hyperbolic chaos for the considered map. Moreover, we also give a partial solution of an open problem formulated in [7]: to describe all the one-dimensional maps with all the periodic orbits having the same mean *** Codes 37E05 Copyright © 2024, The Authors. All rights reserved.

关键词： Bifurcation (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Locating what you need: towards adapting diffusion models to OOD concepts in-the-wild 24

Locating what you need: towards adapting diffusion models to...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jianan Yang Chenchao Gao Zhiqing Xiao Junbo Zhao Sai Wu Gang Chen Haobo Wang College of Computer Science and Technology Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security International School of Information Science and Engineering Dalian University of Technology and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security School of Software Technology Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9798331314385

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LORA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hashing-Based Multi-Modal Semantic Communication

Hashing-Based Multi-Modal Semantic Communication

引用

IEEE Conference on Wireless Communications and Networking

作者： Yibo Zhu Hongyu Gu Jiangtian Nie Jianhang Tang Jiangming Jin Yang Zhang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China School of Computer Science and Engineering Nanyang Technological University Singapore State Key Laboratory of Public Big Data Guizhou University China TuSimple

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

The advanced sixth-generation (6G) wireless network is considered as an indispensable part of the Metaverse, where a substantial volume of communication content is transmitted through multiple modalities, placing significant transmission loads on communication channels. In this paper, we propose a framework for multi-modal semantic communication using hashing-based semantic extraction approach to produce optimal binary signatures (hash codes). Instead of directly using coarse-grained feature fusion methods, we capture deep semantics in self-attention manner, achieving fine-grained multi-modal feature fusion thereby strengthening the representation ability of hash codes. To enhance adaptability in practical situations, we then design a modality-completion module to address missing modalities in data, accommodating scenarios with both single-modal and cross-modal data. We evaluate the proposed semantic extraction framework on two popular multi-modal datasets, comparing it with the latest hashing methods and then demonstrate the effectiveness in various channel conditions.

关键词： 6G mobile communication Codes Metaverse Wireless networks Semantics Communication channels Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Trust Evaluation Model of Social Internet of Things Based on Multi-relationships

Trust Evaluation Model of Social Internet of Things Based on...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Fan, Fan Zhang, Hongbin Zhao, Dongmei Wang, Yanxia Liu, Bin Liu, Jian Hebei University of Science and Technology School of Information Science and Engineering Shijiazhuang China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang China Hebei Geological Workers' University Shijiazhuang China Hebei University of Science and Technology School of Economics and Management Research Center of Big Data and Social Computing Shijiazhuang China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Trust plays a vital role in ensuring the security of the Social Internet of Things. Due to the increased mobility of intelligent devices, there are frequent interactions between machines and changes in social relationships. It leads to a possible data sparsity problem in the Social Internet of Things. Therefore, it is presented that the trust evaluation model is based on various social relationships. The model considers the impact of multiple dynamically changing social relationships between nodes on trust. The implicit social relationship is mined based on the stated social relationship and potential attributes connecting nodes. It addresses the scarcity issue and the slow start of the Social Internet of Things. Simulations on the Santander Smart Cities dataset demonstrate that the approach improves the accuracy and convergence of trust evaluation in both sparse and regular networks. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Noisy Correspondence Rectification via Asymmetric Similarity Learning 39

Noisy Correspondence Rectification via Asymmetric Similarity...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yunbo Wu, YuJie Dai, Zhien Tian, Can Long, Jun Chen, Jianhai Big Data Institute Central South University China School of Computer Science and Engineering Central South University China School of Automation Central South University China School of Computer Science and Cyber Engineering Guangzhou University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)157735897X

Cross-modal matching shows enormous potential to recognize objects across different sensory modalities, which is fundamental to numerous visual-language tasks like image-text retrieval and visual captioning. Existing works generally rely on massive and well-aligned data pairs for model training. Unfortunately, multimodal datasets are extremely difficult to annotate and collect. As an alternative, the co-occurred data pairs collected from the internet have been widely exploited to train a cross-modal matching model. However, the cheaply-collected dataset unavoidably contains mismatched pairs (i.e., noisy correspondence), which are detrimental to the matching model. In this paper, we propose an alternative method termed noisy correspondence rectification via Asymmetric Similarity Learning (ASL), and it allows for dealing with insufficient learning of positive and negative pairs caused by the popular triplet-based symmetric learning fashion. Specifically, the learning of positive or negative pairs within a triplet is conducted in an asymmetric fashion, and the self-paced weighting boundary is imposed on positive pairs to mitigate the effect of noise. Meanwhile, the optimization of negative samples will not be affected in the process of punishing potentially-noisy positive samples. To verify the effectiveness of our proposed approach, a series of experiments are conducted on three widely-used benchmarks (i.e., Flick30k, MS-COCO and CC152k), and the results show superior performance compared to the state-of-the-art methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MSK: A Grade Mining Method for Second-Class Based on MeanShift and K-means 3

MSK: A Grade Mining Method for Second-Class Based on MeanShi...

引用

3rd IEEE International Conference on Computer science and Educational Informatization, CSEI 2021

作者： Dong, Yao Dong, Yongfeng Shi, Jin Deng, Yahan Pang, Shaoyuan Hebei University of Technology Hebei Key Laboratory of Big Data Computing School of Artificial Intelligence Tianjin China

ISBN: (纸本)9781728184739

With the advent of the era of big data, more and more data are accumulated by the second class in colleges and universities, and how to effectively analyze and use them has become the research focus. A novel clustering algorithm named MeanShift-K-means (MSK) is proposed to assess the scores and get the relationship between scores and graduation. Firstly, the MeanShift vector is calculated by Gaussian kernel function, Then MeanShift algorithm is used to obtain the initial clustering center points in K-Means, instead of random selection. Secondly, the improved K-means algorithm was applied to assess the second class in a university. The results show that the MSK algorithm has better clustering effect than the traditional Kmeans algorithm and Canopy-K-means algorithm, which is more helpful to recommend activities for college students and to provide predictive guidance and decision-making basis for administrators. © 2021 IEEE.

关键词： data mining

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：