检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hou, Danyang Pang, Liang Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural language query. Existing methods for VCMR typically rely on frame-aware video retrieval, calculating similarities between the query and video frames to rank videos based on maximum frame similarity. However, this approach overlooks the semantic structure embedded within the information between frames, namely, the event, a crucial element for human comprehension of videos. Motivated by this, we propose EventFormer, a model that explicitly utilizes events within videos as fundamental units for video retrieval. The model extracts event representations through event reasoning and hierarchical event encoding. The event reasoning module groups consecutive and visually similar frame representations into events, while the hierarchical event encoding encodes information at both the frame and event levels. We also introduce anchor multi-head self-attenion to encourage Transformer to capture the relevance of adjacent content in the video. The training of EventFormer is conducted by two-branch contrastive learning and dual optimization for two sub-tasks of VCMR. Extensive experiments on TVR, ANetCaps, and DiDeMo benchmarks show the effectiveness and efficiency of EventFormer in VCMR, achieving new state-of-the-art results. Additionally, the effectiveness of EventFormer is also validated on partially relevant video retrieval task. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Relational Variational Contrastive Learning for Next POI Recommendation

Multi-Relational Variational Contrastive Learning for Next P...

引用

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

作者： Lin Chen Peipei Wang Xiaohui Han Lijuan Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Next point-of-interest (POI) recommendation aims to predict the next interested POI to the user based on their historical check-in data in location-based social services. Most existing studies have attempted to model user visiting behaviors via sequence-based and graph-based models, and have achieved impressive performance. However, there is still room to explore the implicit transition preferences and contextual multiple semantic relationships among various POIs. To this end, we propose a novel graph-based Multi-Relational Variational Contrastive Learning (MRVCL) method for next POI recommendation, which captures local similarity associations and global contextual dependencies among POIs. Specifically, an order-free local-relational adaptive weighting module is designed to alleviate the problem of insufficient utilization of multi-hop neighbor information caused by the limit of neighbor order of nodes. We then develop a contextaware global-relational encoding module to capture implicit semantic sequential relationships. Finally, generative variational-contrastive learning is employed to construct a continuous representation of the latent features and reinforce the quality of representation learning. Extensive experiments on two real-world datasets validate that our MRVCL outperforms existing state-of-the-art methods on various evaluation metrics. To facilitate future research, our code and data are open-sourced at https://***/LinCH-en/MRVCL.

关键词： Representation learning Measurement Correlation Semantics Neural networks Contrastive learning Signal processing Transformers Encoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

On the -differential spectra of two classes of power functions over finite fields

引用

Applicable Algebra in Engineering, Communication and computing 2025年 1-30页

作者： Liu, Qian Huang, Zhiwei Chen, Zhixiong Jiang, Rong Zhang, Liupiao Key Laboratory of Information Security of Network Systems College of Computer and Data Science Fuzhou University Fuzhou China Hubei Key Laboratory of Applied Mathematics Faculty of Mathematics and Statistics Hubei University Wuhan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Fujian Key Laboratory of Financial Information Processing Putian University Putian China School of Computer Science and Technology Dongguan University of Technology Dongguan China

Recently, a new concept called multiplicative differential was introduced by Ellingsen et al. [7]. As an extension of the differential uniformity, it is theoretically appealing to determine the properties of c-differential uniformity and the corresponding c-differential spectrum. In this paper, based on certain quadratic character sums and two special elliptic curves over $$\mathbb {F}_p$$ , the $$(-1)$$ -differential spectra of the following two classes of power functions over $$\mathbb {F}_{p^n}$$ is completely determined: (1) $$f_1(x)=x^{\frac{p^n+3}{2}}$$ , where $$p>3$$ and $$p\equiv 3\pmod 4$$ ; (2) $$f_2(x)=x^{p^n-3}$$ , where $$p>3$$ . The obtained result shows that the $$(-1)$$ -differential spectra of $$f_1(x)$$ and $$f_2(x)$$ can be expressed explicitly in terms of n. Moreover, an upper bound of the c-differential uniformity of $$f_2(x)$$ is given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Optimization of Computational Fluid Dynamics Application code_saturne Based on Next Generation Sunway Supercomputer 14

Parallel Optimization of Computational Fluid Dynamics Applic...

引用

14th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2023

作者： Liu, Anjun Liao, Yin Xu, Xihao Chen, YanYan Zhong, Hongjun Wu, Jianming Kong, Bo Raikov, Alexander Guo, Meng Jinan Institute of Supercomputing Technology Jinan Key Laboratory of High Performance Industrial Software Jinan China Zhejiang Yuansuan Technology Co. Ltd Jinan Supercomputing-Zhejiang Yuansuan Industrial Simulation System Joint Laboratory Hangzhou China Qilu University of Technology Shandong Academy of Sciences Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Key Laboratory of Computing Power Network and Information Security China Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Shandong Jinan China

ISBN: (纸本)9798350371024

code_saturne is an open-source general large-scale computational fluid dynamics software independently developed by Electricite de France since 1997. Due to its high computing performance, code_saturne has been widely used in the nuclear industry, heavy fuel and biomass combustion, particle tracking and other computational fluid dynamics fields. In this work, we implemented code_saturne on the new generation Sunway supercomputer (SW26010pro) at the first time. By applying the data value-taking technology of double cache, combined with Sunway shared memory technology, we have adapted the data structure and Modular programming of code_saturne conducively to the new generation Sunway supercomputer (SW26010pro) and accelerated the software hotspots the software hotspots by 1-2 times. After optimizing and porting, this software has successfully served in the numerical simulation of the lateral flow of fuel assemblies in the nuclear industry. © 2023 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

A Modified CSO Based on Complementary Learning

A Modified CSO Based on Complementary Learning

引用

第34届中国控制与决策会议

作者： Wei Li Zhou Lei Lei Wang School of Computer Science and Engineering Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology

Competitive swarm optimization algorithm(CSO) is an effective optimization ***,the population is easy to converge to the local optimal area in dealing with complex *** improve the performance of the CSO algorithm,this paper proposes a modified CSO base on complementary learning(CSO-CL).First,an optional archive is introduced to provide valuable information of evolutionary ***,the complementary learning strategies are designed,which not only enhance the ability of the algorithm to jump out of the local optimum,but also ensure a better balance between the exploration and the ***,the linear population size reduction strategy is used to improve the convergence speed of the proposed *** comparing with three state-of-the-art metaheuristic algorithms on the CEC2014 benchmark functions,it is proved that the proposed algorithm is competitive and effective.

关键词： Competitive Swarm Optimizer Evolutionary Computation Optional Archive

来源：评论

学校读者我要写书评

暂无评论

Memory-guided two-stream spatio-temporal coding network based for video anomaly detection 23

Memory-guided two-stream spatio-temporal coding network base...

引用

Proceedings of the 2023 International Conference on Information Education and Artificial Intelligence

作者： Bonan Li Hong Zhang Xingang Wang Rui Cao Jinyan Zhou China Radio and Television Shandong Network Co Ltd China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (纸本)9798400716157

In the paper, we propose a memory-guided dual-stream spatio-temporal encoder network (MSTAE) based on the U-Net network as the backbone, the spatial stream uses the time displacement module to obtain the spatial features of the video, and the temporal stream is aggregated across frames to obtain the temporal features of the video, meanwhile, the coordinate attention module is introduced to improve the U-Net network and enhance the dynamic entity representation capability. In order to reduce the prediction error, the memory module is used to record the prototype patterns of normal data to reduce the problem of small error between the prediction anomaly and its true value due to the excessive generalisation ability of the deep network. We conducted extensive experiments on three publicly available standard datasets (Ped2, Avenue and ShanghaiTech datasets). The experiments demonstrate that the research model outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SF-DETR: A Road Small Target Detection Model Based on RTDETR

SF-DETR: A Road Small Target Detection Model Based on RTDETR

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jianhua Gao Jiazheng Man Chunlin Zhao Xiaoming Wu Xiangzhi Liu Huomin Dong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Shandong Shanke Intelligent Technology Co. Ltd

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

As a part of computer vision, object detection is crucial for traffic management, emergency response, autonomous driving vehicles, and smart cities. Despite significant progress in object detection, detecting small objects remains challenging due to their low resolution, which results in little visual information, difficulty in extracting discriminative features, and susceptibility to interference from environmental factors. To address these challenges, we propose SF-DETR, a new model designed specifically for scenarios with small targets. Firstly, We designed a new backbone network that uses partial channel self-attention to replace the backbone network of RTDETR, which can capture both local and global contextual information for extracting and enhancing input features, thereby enhancing the perception of small targets. Secondly, in order to enhance the feature representation ability of the model and better preserve the details of small objects, we proposed Feature Enhancement and Refinement (FER) module, which incorporates a bidirectional fusion mechanism between high-resolution and low-resolution features, allowing for more comprehensive information transfer between features and further improving the effect of multi-scale feature fusion. Finally, we introduce an efficient IoU method (PIoU) which simplifies the computation, speeds up the convergence, and improves the detection accuracy. SF-DETR significantly improves the detection of small targets, outperforming widely used models on various metrics, while significantly reducing model parameters and computational costs compared to RT-DETR. Compared to RTDETR-R34, our model has improved the mAP@50 and mAP@0.5:0.95 by 3.3% and 2.4% respectively on the Visdrone2019 test set.

关键词： Visualization Accuracy Target recognition Smart cities Computational modeling Roads Object detection Feature extraction Computational efficiency Data mining

来源：评论

学校读者我要写书评

暂无评论

HEN:a novel hybrid explainable neural network based framework for robust network intrusion detection

引用

Science China(Information Sciences) 2024年第7期67卷 72-90页

作者： Wei WEI Sijin CHEN Cen CHEN Heshi WANG Jing LIU Zhongyao CHENG Xiaofeng ZOU School of Computer Science and Engineering Xi'an University of TechnologyShaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Technology Wuhan University of Science and Technology School of Future Technology South China University of Technology Shenzhen Research Institute of Hunan University School of Computer Science Hunan University of Technology and Business Institute for Infocomm Research (I2R) Agency for Science Technology and Reseach (A*STAR)

With the rapid development of network technology and the automation process for 5G, cyberattacks have become increasingly complex and threatening. In response to these threats, researchers have developed various network intrusion detection systems(NIDS) to monitor network traffic. However, the incessant emergence of new attack techniques and the lack of system interpretability pose challenges to improving the detection performance of NIDS. To address these issues, this paper proposes a hybrid explainable neural network-based framework that improves both the interpretability of our model and the performance in detecting new attacks through the innovative application of the explainable artificial intelligence(XAI)method. We effectively introduce the Shapley additive explanations(SHAP) method to explain a light gradient boosting machine(Light GBM) model. Additionally, we propose an autoencoder long-term short-term memory(AE-LSTM) network to reconstruct SHAP values previously generated. Furthermore, we define a threshold based on reconstruction errors observed during the training phase. Any network flow that surpasses the specified threshold is classified as an attack flow. This approach enhances the framework's ability to accurately identify attacks. We achieve an accuracy of 92.65%, a recall of 95.26%, a precision of 92.57%,and an F1-score of 93.90% on the dataset NSL-KDD. Experimental results demonstrate that our approach generates detection performance on par with state-of-the-art methods.

关键词： explainable artificial intelligence light gradient boosting machine machine learning network intrusion detection Shapley additive explanation hybrid explainable neural network (HEN)

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

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

作者： Libo Qin Fuxuan Wei Qiguang Chen Jingxuan Zhou Shijue Huang Jiasheng Si Wenpeng Lu Wanxiang Che School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

关键词： Large language models Signal processing Benchmark testing Multitasking Filling Acoustics Speech processing Information exchange Standards

来源：评论

学校读者我要写书评

暂无评论

HyperPipe: Bridging Heterogeneous GPUs for Accelerated Large-Scale Model Training

HyperPipe: Bridging Heterogeneous GPUs for Accelerated Large...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Fulai Liul Chuantao Li Zhigang Zhao Chunxiao Wang Jidong Huo Jintao Li Lianhui Xiao Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

To enhance the performance of pre-trained foundation models in various natural language processing tasks, the scale of these models has been steadily increasing in recent years, driven by advancements high-performance computing hardware. However, the presence of diverse computing devices in data centers and the varying computational demands of different tasks make it challenging for a single type of high-performance G PU to suffice for the large-scale training of foundation models' and lower-performance GPUs often remain underutilized. Therefore, optimizing resource a llocati on and improving training efficiency have become a critical challenge. To address these issues, this study proposes a hybrid parallel training framework for heterogeneous computing devices, named HyperPipe. This framework automatically selects the optimal hybrid parallel strategy based on the performance characteristics of the devices, thereby achieving efficient resource utilization and acceleration training to meet the computational demands of large-scale FMs. Experimental results demonstrate that in a heterogeneous computing environment, training large models like GPT-3-1.3B with HyperPipe achieves significant acceleration, delivering speed-ups ranging from 1.6 x to 2.8 x compared to previous methods.

关键词： Training Performance evaluation Tensors Foundation models Computational modeling Heuristic algorithms Parallel processing Heterogeneous networks Resource management Optimization

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：