检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 448-457页

作者： Yang, Jing Huang, Chengxuan Yang, Xiangli Yang, Laurence T. Gao, Yuan Liu, Cong Zhengzhou University School of Computer Science and Artificial Intelligence Zhengzhou570001 China Duke University Graduate School Department of Computer Science DurhamNC27708 United States Dublin Institute of Technology School of Tourism and Hospitality Management Dublin9P3C+W7 Ireland Hainan University School of Computer Science and Technology Haikou570228 China St. Francis Xavier University Department of Computer Science AntigonishNSB2G 2W5 Canada Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China

Knowledge guidance is crucial for bridging the gap between high-level artificial intelligence (AI) ethics principles and the practical implementation of responsible AI systems. Diverging from static knowledge inference and temporal interpolation, the task of temporal knowledge extrapolation, which entails predicting future facts based on the evolution of historical facts, poses formidable challenges that remain largely unsolved. In existing temporal extrapolation methods, the structural learning of concurrent facts is primarily addressed by utilizing relation-aware graph neural networks. However, the temporal validity of facts leads to the sparsity of temporal subgraphs, where inherent coarse-level learning mechanisms hinder the capture of nuanced and scarce local semantics. Thus, this article proposes a fine-grained tensor graph attention network (F-GAT) that promotes representation learning of concurrent facts on sparse subgraphs by effectively distinguishing the significance of entities and relations within triplets and acquiring self-attention across diverse triplet contexts. Based on F-GAT, this article proposes a recurrent evolution network [recurrent evolution graph attention network (RE-GAT)] for temporal knowledge extrapolation. RE-GAT employed gated recurrent units to iteratively capture the sequential patterns between adjacent temporal facts, while simultaneously learning enriched embedding through the dual influence of historical factors and structural factors. The competitive results achieved by comparing the entity and relationship prediction performance of the proposed RE-GAT model with advanced methods on six public benchmarks demonstrate the effectiveness of RE-GAT for temporal extrapolation. © 2020 IEEE.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Anomaly Detection Based on DGBi-SA Model

引用

Engineering Letters 2025年第3期33卷 612-619页

作者： Wang, Xin Dai, Hong Huang, Zheng Han, Yue University of Science and Technology Liaoning Liaoning CO Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning CO Anshan114051 China

Network traffic anomaly detection plays a crucial role in today's network security and performance management. In response to the challenges in current network traffic data processing, such as insufficient structuring and dynamics, the paper proposes a network traffic anomaly detection approach based on DGBi-SA model, which integrates Dynamic Graph Convolutional Networks (DyGCN), Bi-directional Long Short-Term Memory (Bi-LSTM), and the Self-Attention mechanism. To solve the problem of insufficient structuring, the model employs DyGCN to capture network traffic's dynamic graph structural characteristics proficiently. Simultaneously, combining Bi-LSTM and the Self-Attention mechanism enhances the model's ability to capture temporal and spatial dependencies. The main objective of the research in the paper is to improve the accuracy and detection efficiency of network traffic prediction, thereby achieving effective detection and timely response to abnormal behaviors in complex network environments. Through a sequence of experiments conducted on the CICIDS-2017 dataset, the paper verifies that the DGBi-SA model can effectively solve the above problems. The experimental results indicate that the model outperforms existing methods in key performance indicators such as AUC, precision, recall, and F1 score, thereby proving that the DGBi-SA model has important application value and scientific significance in network traffic anomaly detection. © 2025, International Association of Engineers. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

DAU-Net: A medical image segmentation network combining the Hadamard product and dual scale attention gate

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 2753-2767页

作者： Zhang, Xiaoyan He, Mengmeng Li, Hongan School of Computer Science and Technology Xi’an University of Science and Technology Xi’an710054 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Medical image segmentation has an important application value in the modern medical field, it can help doctors accurately locate and analyze the tissue structure, lesion areas, and organ boundaries in the image, which provides key information support for clinical diagnosis and treatment, but there are still a large number of problems in the accuracy of the segmentation, so in this paper, we propose a medical image segmentation network combining the Hadamard product and dual-scale attention gate (DAU-Net). First, the Hadamard product is introduced in the structure of the fifth layer of the codec for element-by-element multiplication, which can generate feature representations with more representational capabilities. Second, in the jump connection module, we propose a dual scale attention gating (DSAG), which can highlight more valuable features and achieve more efficient jump connections. Finally, in the decoder feature structure, the final segmentation result is obtained by aggregating the feature information provided by each part, and decoding is achieved by up-sampling operation. Through experiments on two public datasets, Luna and Isic2017, DAU-Net is able to extract feature information more efficiently using different modules and has better segmentation results compared to classical segmentation models such as U-Net and U-Net++, and also verifies the effectiveness of the model. © 2024 American Institute of Mathematical sciences. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Personalized Federated Learning via Contrastive-Augmented Local Memorization Retrieval

Towards Personalized Federated Learning via Contrastive-Augm...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Peifeng Chen, Jiahui School of Computer Science and Technology Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Federated learning (FL) enables clients to collaboratively train statistical models while maintaining the privacy of their local data. However, traditional FL methods often suffer performance degradation due to data heterogeneity across clients. To mitigate this issue, we propose an efficient personalized federated learning (pFL) framework, FedCLR. In this framework. we first propose contrastive-augmented representation learning at the local level to build a global model capable of providing more discriminative feature representations. During inference, FedCLR utilizes this global model in conjunction with local memorization retrieval mechanism to achieve better personalization performance. Comprehensive experiments conducted on public datasets and various heterogeneous data environments demonstrate that FedCLR significantly outperforms recent state-of-the-art pFL methods in terms of accuracy. © 2025 IEEE.

关键词： contrastive learning federated learning local memorization Non-IID data personalization

来源：评论

学校读者我要写书评

暂无评论

Incremental Data Stream Classification with Adaptive Multi-Task Multi-View Learning

引用

Big Data Mining and Analytics 2024年第1期7卷 87-106页

作者： Jun Wang Maiwang Shi Xiao Zhang Yan Li Yunsheng Yuan Chengei Yang Dongxiao Yu School of Computer Science and Technology Shandong UniversityQingdao 266237China School of Software Shandong UniversityJinan 250101China

With the enhancement of data collection capabilities,massive streaming data have been accumulated in numerous application ***,the issue of classifying data streams based on mobile sensors can be formalized as a multi-task multi-view learning problem with a specific task comprising multiple views with shared features collected from multiple *** incremental learning methods are often single-task single-view,which cannot learn shared representations between relevant tasks and *** adaptive multi-task multi-view incremental learning framework for data stream classification called MTMVIS is proposed to address the above challenges,utilizing the idea of multi-task multi-view ***,the attention mechanism is first used to align different sensor data of different *** addition,MTMVIS uses adaptive Fisher regularization from the perspective of multi-task multi-view learning to overcome catastrophic forgetting in incremental *** reveal that the proposed framework outperforms state-of-the-art methods based on the experiments on two different datasets with other baselines.

关键词： data stream classification mobile sensors multi-task multi-view learning incremental learning

来源：评论

学校读者我要写书评

暂无评论

Qwen-IG: A Qwen-based Instruction Generation Model for LLM Fine-tuning 24

Qwen-IG: A Qwen-based Instruction Generation Model for LLM F...

引用

13th International Conference on Computing and Pattern Recognition, ICCPR 2024

作者： Zhang, Lu Liu, Yu Luo, Yitian Gao, Feng Gu, Jinguang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (纸本)9798400717482

The quality of instructions is crucial for LLM (large language model) fine-tuning. The most compelling data for instruction tuning exhibit not only high complexity, low perplexity, high faithfulness, and high answer relevancy, but also diversity, naturalness, coherence, and understandability. However, traditional QAG (question and answer generation) and LLMs face challenges regarding instruction complexity, answer relevancy and diversity. To overcome these issues, we have developed the Qwen-IG instruction generation model for LLM fine-tuning. Firstly, we collect high-quality instruction sets, such as alpaca, GPT4-LLM, and TigerBot, and utilize them to build a train set for LLM fine-tuning. Secondly, Qwen is trained with the train set just generated through three approaches, namely C2IO (context to instruction and output), C2I2O (context to instruction to output), and C2O2I (context to output to instruction). Finally, we employ the eight metrics mentioned above to evaluate the effectiveness of Qwen-IG in the task of generating instructions. The experimental results demonstrate Qwen-IG has increased at least 9.6% on complexity, 23% on answer relevancy and 17% on diversity. © 2024 Copyright held by the owner/author(s).

关键词： Instruction Generation

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Learning Intensity and Optical Flow From High-Speed Spike Stream

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5126-5139页

作者： Zhu, Lin Yan, Weiquan Chang, Yi Tian, Yonghong Huang, Hua Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China Peng Cheng Laboratory Shenzhen518055 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Peking University School of Computer Science Beijing100081 China Beijing Normal University School of Artificial Intelligence Beijing100875 China

Bio-inspired vision sensors, which emulate the human retina by recording light intensity as binary spikes, have gained increasing interest in recent years. Among them, the spike camera is capable of perceiving fine textures by simulating a small retinal region called the fovea and producing high temporal resolution (20,000 Hz) spatiotemporal spike streams. To bridge the gap between binary spike streams and human vision in high-speed scenes, reconstructing intensity and optical flow from high temporal resolution spikes is particularly important. In this paper, we present a hybrid SNN-ANN network designed for simultaneous intensity and optical flow learning from spike streams. To adaptively extract spatial and temporal features from continuous spike streams, we propose a spiking neuron module with dense connections that efficiently processes both short-term and long-term spike data, while maintaining low power consumption characteristics. Subsequently, we introduce two decoders for optical flow and intensity estimation that complement each other. A temporal-aware warping module, based on flow features, is specifically designed to align the temporal features of the intensity decoder, thereby reducing motion artifacts. Concurrently, improved intensity features contribute to more accurate flow feature predictions, resulting in a mutually beneficial relationship within our network. To evaluate the effectiveness of our proposed network, we conduct experiments on both simulated and real spike datasets. Our network outperforms existing state-of-the-art spike-based reconstruction and optical flow estimation methods, demonstrating its potential for advancing the field of bio-inspired vision sensors. © 1991-2012 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

引用

Neural Computing and Applications 2024年第22期36卷 13799-13814页

作者： Zhang, Yubo Huang, Qingming Zheng, Liying School of Computer Science and Technology Harbin Engineering University 145 Nantong Street Heilongjiang Harbin150001 China School of Computer Science and Technology University of Chinese Academy of Sciences Huairou District Beijing100019 China

The tracking performance of Multi-Object Tracking (MOT) has recently been improved by using discriminative appearance and motion features. However, dense crowds and occlusions significantly reduce the reliability of these features, resulting in unsatisfied tracking performance. Thus, we design an end-to-end MOT model based on Graph Convolutional Neural Networks (GCNNs) which fuses four classes of features that characterize objects from their appearances, motions, appearance interactions, and motion interactions. Specifically, a Re-Identification (Re-ID) module is used to extract more discriminative appearance features. The appearance features from object tracklets are then averaged to simplify the proposed tracker. Then, we design two GCNNs to better distinguish objects. One is for extracting interactive appearance features, and the other is for interactive motion features. A fusion module then fuses those features, getting the global feature similarity based on which an association component calculates the MOT matching results. Finally, we semantically visualize relevant structures with the GNNExplainer for insight into the proposed tracker. The evaluation results on MOT16 and MOT17 benchmarks show that our model outperforms the state-of-the-art online tracking methods in terms of Multi-Object Tracking Accuracy and Identification F1 score which is consistent with the results from the GNNExplainer. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Modal Feature Optimization Network with Prompt for Multimodal Sentiment Analysis 31

Modal Feature Optimization Network with Prompt for Multimoda...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Xiangmin Wei, Wei Zou, Shihao Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China China

ISBN: (纸本)9798891761964

Multimodal sentiment analysis(MSA) is mostly used to understand human emotional states through multimodal. However, due to the fact that the effective information carried by multimodal is not balanced, the modality containing less effective information cannot fully play the complementary role between modalities. Therefore, the goal of this paper is to fully explore the effective information in modalities and further optimize the under-optimized modal *** this end, we propose a novel Modal Feature Optimization Network (MFON) with a Modal Prompt Attention (MPA) mechanism for MSA. Specifically, we first determine which modalities are under-optimized in MSA, and then use relevant prompt information to focus the model on these features. This allows the model to focus more on the features of the modalities that need optimization, improving the utilization of each modality's feature representation and facilitating initial information aggregation across modalities. Subsequently, we design an intra-modal knowledge distillation strategy for under-optimized modalities. This approach preserves the integrity of the modal features. Furthermore, we implement inter-modal contrastive learning to better extract related features across modalities, thereby optimizing the entire network. Finally, sentiment prediction is carried out through the effective fusion of multimodal information. Extensive experimental results on public benchmark datasets demonstrate that our proposed method outperforms existing state-ofthe-art models. © 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

Adaptive Dynamic VSLAM: Refining Semantic-Geometric Fusion and Static Background Inpainting 27th

Adaptive Dynamic VSLAM: Refining Semantic-Geometric Fusion a...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mu, Qi Guo, Baizhang Guo, Shuai Li, Zhanli School of Computer Science and Technology Xi’an University of Science and Technology Xi’an710054 China

ISBN: (纸本)9783031781124

To tackle the challenges of adaptability and precision in VSLAM for dynamic environments, we propose a joint refined semantic-geometric approach that improves SLAM’s performance across various dynamic settings. Our method integrates semantic segmentation networks with morphological processing to extract stable boundary features from potential dynamic objects accurately. By restoring depth information and applying geometric constraints that account for camera motion, we facilitate the precise identification and removal of dynamic objects. Additionally, we exploit static scene information to inpaint the background areas occluded by dynamic objects, thus enabling complete scene reconstruction. Quantitative evaluation using dynamic sequences from the TUM dataset reveals a significant reduction in RMSE for both high and low dynamic sequences compared to ORB-SLAM2, DynaSLAM, Yolo-SLAM and Blitz-SLAM. Specifically, there is 95.23%–32.30% decrease in RMSE for high dynamic sequences and 44.7%–5.52% decrease for low dynamic sequences, respectively. These results demonstrate the method’s enhanced adaptability and localization accuracy across different levels of dynamic scenes. Furthermore, the dense reconstruction maps derived from the Static Background Inpainting process offer more complete static scene information than original maps, providing adequate technical support for autonomous localization and mapping of robots in dynamic environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

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：