检索结果-内蒙古大学图书馆

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Li, Hengzhi Cai, Shubin Ming, Zhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9783031446924

Legal judgment prediction aims to predict the judgment result based on the case fact description. It is an important application of natural language processing within the legal field. To enhance the impartiality and consistency of the judiciary, the Supreme People’s Court selects representative cases and categorizes them as guiding or typical cases. However, the current research is based on the unified training of large-scale datasets, and does not distinguish the value of different existing cases. To address these issues, this paper collects relevant guiding cases and typical cases, designs a legal judgment prediction method that incorporates matching guiding cases, and proposes a legal judgment prediction model called MAGIC (MAtching GuIding Cases), based on multi-feature fusion. The goal of this research is to improve the prediction performance of legal judgments by utilizing the value of high-quality cases. The experimental results on the CAIL2018 evaluation datasets demonstrate that the proposed method significantly improves the performance of legal judgment prediction models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion 39

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Yinghui Zhou, Qianyu Gong, Jingyu Zhu, Ye Dazeley, Richard Zhao, Xinkui Lu, Xuequan School of Information Technology Deakin University Australia Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology East China Normal University Shanghai China School of Software Technology Zhejiang University Ningbo China Department of Computer Science and Software Engineering The University of Western Australia Australia

ISBN: (纸本)157735897X

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer’s CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three key components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, i.e., point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with state-of-the-art methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Tracking of Pinus Radiata Catkins 1

引用

37th International Conference on Image and Vision Computing New Zealand, IVCNZ 2022

作者： Song, Eric Schofield, Sam Green, Richard Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

ISBN: (数字)9783031258251

ISBN: (纸本)9783031258244

Pinus Radiata trees form pollen-producing catkins that can be harvested for pharmaceutical uses. Unmanned Aerial Vehicles (UAVs) may be well suited to the task of autonomously harvesting these catkins. We propose a method to reliably detect and track P. Radiata catkins in three dimensions that can be used for real-time guidance of a UAV. The method applies the YOLOv5 deep learning algorithm to detect catkins in the X-Y plane. A novel optimisation of the MeanShift algorithm is utilised to assist existing contour detection algorithms in segmenting individual catkins in the Z plane. A Kanade-Lucas-Tomasi tracker was used with RANSAC for accurate frame-to-frame tracking. The method achieved a Mean Average Precision of 0.87 on images taken at a commercial pine pollen farm. The method detected the depth of catkins at distances of up to 1200 mm to an accuracy of 2 mm, or 8 mm for occluded catkins. Detected catkins can be reliably tracked at speeds of 1ms. An average frame rate of 22 frames per second was achieved on an Intel i5 CPU, with the Meanshift optimisation performing up to 41 times faster than existing implementations. These results indicate that the proposed method could be used to successfully assist in the automated harvesting of P. Radiata catkins. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Neocognitron Based on Multi-objective Optimization for Few-Shot Learning 1

引用

6th EAI International Conference on Robotics and Networks, EAI ROSENET 2022

作者： Pan, Hao Guo, Guiyu Shi, Daming College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9783031338267

ISBN: (纸本)9783031338250

In recent years, with the continuous development of deep learning, more and more network models have been proposed to solve practical problems. However, most models often need a large number of labeled samples to train the network to achieve better recognition results. Because a large number of samples need to be labeled, it is labor-intensive and prone to human error labels. For this reason, a large number of researchers have created the concept of few-shot learning, which entails that the model acquires new information from a limited amount of labeled samples in order to get improved recognition outcomes. In this chapter, we learn from the structure of the visual cortex of the human brain and propose new shape templates to improve the traditional neural network. First, we extract the global characteristics of the image to form a 0-1 mask. As the network hierarchy increases and the field of perception expands, the mask is cut to form shape templates. Then evolutionary computation selects some excellent shape templates, which provide a non-linear constraint for the convolution layer. Moreover, the convolution layer introduces inhibition signals for training, and a new function is proposed to make it more in line with the biomimetic principles of the human visual cortex. The results show that the proposed method can improve the accuracy of few-shot learning. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A dynamic and resource sharing virtual network mapping algorithm

引用

Digital Communications and Networks 2023年第5期9卷 1101-1112页

作者： Xiancui Xiao Xiangwei Zheng Ji Bian Cun Ji Xinchun Cui School of Information Science and Engineering Shandong Normal UniversityJinan250014China School of Information Engineering Shandong Management UniversityJinan250358China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250014China School of Computer Science and Technology Qufu Normal UniversityRizhao276800China

Network virtualization can effectively establish dedicated virtual networks to implement various network ***,the existing research works have some shortcomings,for example,although computing resource properties of individual nodes are considered,node storage properties and the network topology properties are usually ignored in Virtual Network(VN)modelling,which leads to the inaccurate measurement of node availability and *** addition,most static virtual network mapping methods allocate fixed resources to users during the entire life cycle,and the users’actual resource requirements vary with the workload,which results in resource allocation *** on the above analysis,in this paper,we propose a dynamic resource sharing virtual network mapping algorithm named NMA-PRS-VNE,first,we construct a new,more realistic network framework in which the properties of nodes include computing resources,storage resources and topology *** the node mapping process,three properties of the node are used to measure its mapping ***,we consider the resources of adjacent nodes and links instead of the traditional method of measuring the availability and priority of nodes by considering only the resource properties,so as to more accurately select the physical mapping nodes that meet the constraints and conditions and improve the success rate of subsequent link ***,we divide the resource requirements of Virtual Network Requests(VNRs)into basic subrequirements and variable sub-variable requirements to complete dynamic resource *** former represents monopolizing resource requirements by the VNRs,while the latter represents shared resources by many VNRs with the probability of occupying resources,where we keep a balance between resource sharing and collision among users by calculating the collision *** results show that the proposed NMAPRS-VNE can increase the average acceptance rate and network revenu

关键词： Network virtualization VNRs Network frameworks Dynamic resource allocation Resource sharing

来源：评论

学校读者我要写书评

暂无评论

FFFN: Fashion Feature Fusion Network by Co-Attention Model for Fashion Recommendation 48

FFFN: Fashion Feature Fusion Network by Co-Attention Model f...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Lin, Zhantu Zhang, Xiaoyan Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9781728163277

Fashion complementary recommendation has always been crucial in the field of recommendation. In previous work, researchers did not pay attention to the connection and combinability between multi-dimensional image features of fashion items. To effectively utilize the advantages of high-level and low-level features in images, we propose a Fashion Feature Fusion Network (FFFN) to solve the fashion complementary recommended tasks, which extracts and combines the features of different dimensions in the neural network into a fusion feature. Then, we input the fused image features and the category text features of fashion items into the co-attention module to realize the guidance of the text attention information to the image attention information. Experimental results on different datasets show that our model has advantages compared to the state-of-the-art methods. © 2023 IEEE.

关键词： Co-attention Fashion complementary recommendation Feature fusion

来源：评论

学校读者我要写书评

暂无评论

A Cyber counterintelligence competence framework: Developing the job roles 22

A Cyber counterintelligence competence framework: Developing...

引用

22nd European Conference on Cyber Warfare and Security, ECCWS 2023

作者： Sithole, Thenjiwe Toit, Jaco Du Von Solms, Sebastian H. Academy of Computer Science and Software Engineering University of Johannesburg South Africa

ISBN: (纸本)9781914587702

In recent years, there have been intensifying cyber risks and volumes of cyber incidents prompting a significant shift in the cyber threat landscape. Both nation-state and non-state actors are increasingly resolute and innovative in their techniques and operations globally. These intensifying cyber risks and incidents suggest that cyber capability is inversely proportional to cyber risks, threats and attacks. Therefore, this confirms an emergent and critical need to adopt and invest in intelligence strategies, predominantly cyber counterintelligence (CCI), which is a multi-disciplinary and proactive measure to mitigate risks and counter cyber threats and cyber-Attacks. Concurrent with the adoption of CCI is an appreciation that requisite job roles must be defined and developed. Notwithstanding the traction that CCI is gaining, we found no work on a clear categorisation for the CCI job roles in the academic or industry literature surveyed. Furthermore, from a cybersecurity perspective, it is unclear which job roles constitute the CCI field. This paper stems from and expands on the authors prior research on developing a CCI Competence Framework. The proposed CCI Competence Framework consists of four critical elements deemed essential for CCI workforce development. In order of progression, the Framework s elements are: CCI Dimensions (passive-defensive, active-defensive, passive-offensive, active-offensive), CCI Functional Areas (detection, deterrence, deception, neutralisation), CCI Job Roles (associated with each respective Functional Area), and Tasks and Competences (allocated to each job role). Pivoting on prior research on CCI Dimensions and CCI Functional Areas, this paper advances a proposition on associated Job Roles in a manner that is both intelligible and categorised. To this end, the paper advances a five-step process that evaluates and examines Counterintelligence and Cybersecurity Job Roles and functions to derive a combination of new or existing Job Role

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Dirty page prediction by machine learning methods based on temporal and spatial locality 26

Dirty page prediction by machine learning methods based on t...

引用

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

作者： Lu, Yahui Jiang, Yu Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350331684

The memory dirty page prediction technology can effectively predict whether a memory page will be modified (dirty) at the next moment, and is widely used in virtual machine migration, container migration and other fields. In this paper, we propose a machine-learning based method for memory dirty page prediction. The method exploits the temporal and spatial locality principle of memory changes, collects dirty records of pages over a period of time, and uses supervised learning methods for training and predicting the dirty page. We also discuss the influence of data contradiction and data repetition in memory page dataset. The experiments with different memory change frequency dataset show that compared with the traditional time series methods, our machine-learning based method has better performance. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation with Active Exploration and Self-Attention Based Inter-Class Variation Transfer for Image Segmentation 48

Knowledge Distillation with Active Exploration and Self-Atte...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Yifan Li, Shaojie Yang, Xuan Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9781728163277

Knowledge distillation (KD) aims to distill the knowledge from a more extensive deep neural network into a small net-work without losing validity. This paper proposes a novel approach with active exploration and passive transfer (AEPT) and self-attention-based inter-class feature variation (AIFV) distillation for the cardiac image segmentation task. The AEPT encourages the student model to learn undiscovered knowledge/features of the teacher model, aiming to explore new features outperforming the teacher. More specifically, we focus on where the teacher performs poorly and encourage the student model to explore complementary features different from the teacher model. To improve the distinguishability of the student for different classes, the student learns the self-attention-based feature variation (AIFV) between classes. Extensive experiments on medical and public image datasets demonstrate that our approach makes the student model learn better representations and outperforms state-of-art methods by combining two knowledge distillation strategies. © 2023 IEEE.

关键词： Distillation

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：