检索结果-内蒙古大学图书馆

International Conference on machine learning and Applications (ICMLA)

作者： Hakan Cevikalp Electrical and Electronics Engineering Department Machine Learning and Computer Vision Laboratory Eskisehir Osmangazi University Eskisehir Turkey

This paper introduces a binary large margin classifier that approximates each class with an hyper disk constructed from its training samples. For any pair of classes approximated with hyper disks, there is a corresponding linear separating hyper plane that maximizes the margin between them, and this can be found by solving a convex program that finds the closest pair of points on the hyper disks. More precisely, the best separating hyper plane is chosen to be the one that is orthogonal to the line segment connecting the closest points on the hyper disks and at the same time bisects the line. The method is extended to the nonlinear case by using the kernel trick, and the multi-class classification problems are dealt with constructing and combining several binary classifiers as in Support Vector machine (SVM) classifier. The experiments on several databases show that the proposed method compares favorably to other popular large margin classifiers.

关键词： Support vector machines Databases Kernel Training Approximation methods Optimization Accuracy

来源：评论

学校读者我要写书评

暂无评论

EARP: Integration with Entity Attribute and Relation Path for Event Knowledge Graph Representation learning

EARP: Integration with Entity Attribute and Relation Path fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ze Xu Hao Zhou Ting He Huazhen Wang College of Computer Science and Technology Huaqiao University Xiamen China Key Laboratory of Computer Vision and Machine Learning Huaqiao University Fujian Province University Xiamen China

Event knowledge graph (EKG) as a special case of knowledge graph (KG) can realize the goal of event prediction, and has been proved useful in medical diagnosis and intelligent recommendation. To successfully build an EKG, knowledge representation learning is often required to compute the semantic links of entities and relationships in a low-dimensional space and solve the data sparsity issue in knowledge acquisition, fusion and reasoning. This paper proposes a new EKG representation learning model featuring the integration of event entity attributes and relation paths. By utilizing the knowledge of entity attribute, which contains entity type and entity description, and the knowledge about relation paths, the entity initial vector is obtained by multiplying entity semantic vector, entity description representation vector and entity type representation vector, and the representation of relation path is obtained according to the relation between event pairs, a translation-based model framework is used to integrate and train all vectors to obtain the entity learning vector and the relation learning vector. our method can generate more expressive learning representations, and consequently, enhance the inference performance of EKG. Experiments on publicly available real-world EKG datasets show that our method achieves better performance than the state-of-the-art models on two typical tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

End-Edge-Cloud Collaborative Offloading of Splittable Tasks in Internet of Vehicles: A Multi-Agent Reinforcement learning Approach

SSRN

引用

SSRN 2024年

作者： Fan, Weiwei Gao, Zhenguo Zhang, Jiahui Jiang, Yang College of Computer Science and Technology Huaqiao University Fujian Xiamen China Key Laboratory of Computer Vision Machine Learning of Fujian Province University Fujian Xiamen China

The rapid development of intelligent transportation and the exponential growth of data traffic drive the emerging of more computation-intensive latency-critical tasks in vehicles, bring challenges to the task offloading research in the Internet of Vehicles (IoV), which is for providing vehicles with ultralow latency task processing services via offloading tasks to Edge Servers (ESs) and Cloud Servers (CSs). Focusing on offloading splittable tasks, an end-edge-cloud cooperative splittable task offloading framework is presented for IoV where vehicles with idle resources are regarded as temporary ESs for complementing the computing services of ESs and CSs. Then, we propose a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to minimize task completion latency by making comprehensive decisions jointly involving task splition, communication and computation resource allocation. Furthermore, we propose a Group-based Random Updating Strategy (GRUS) for multi-agent deep reinforcement model training to promote training efficiency. To incentivize High-performance Vehicles (HVs) to offer edge computing services via sharing their spare computation resources, we construct a Multi-Leader Multi-Follower Stackelberg (MLMFS) incentive game model where CSs act as leaders and HVs act as followers. We prove the existence of Stackelberg Equilibrium (SE) point, and propose an Optimal Dynamic Response (ODR) algorithm to drive the CSs' resource renting price decisions and the HVs' resource sharing amount decisions to arrive at the SE point via multi-round negotiations. Simulation results demonstrate the superiority of the proposed algorithm over some selected benchmark algorithms. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation 37

A Single 2D Pose with Context is Worth Hundreds for 3D Human...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Zhao, Qitao Zheng, Ce Liu, Mengyuan Chen, Chen Robotics Institute Carnegie Mellon University United States Center for Research in Computer Vision University of Central Florida United States Key Laboratory of Machine Perception Peking University Shenzhen Graduate School China

ISBN: (纸本)9781713899921

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [74], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3d Human Pose Estimation from Video Via Multi-Scale Multi-Level Spatial Temporal Features

SSRN

引用

SSRN 2023年

作者： Fan, Liling Jiang, Kunliang Zhou, Weixue Gao, Zhenguo Luo, Yanmin The College of Computer Science and Technology in Huaqiao University Fujian Xiamen China Key Laboratory of Computer Vision Machine Learning of Fujian Province University Fujian Xiamen China

In this paper, a novel framework for 2D-to-3D human pose estimation from video is proposed by exploiting multi-scale multi-level spatial temporal features. To extract and exploit the rich features, the framework consists of three branch networks: a temporal feature core network for extracting temporal coherence among frames, a multi-scale feature branch network for extracting multi-scale features using multiple receptive fields with various sizes, and a multi-level feature branch network for extracting multilevel features from layers at different depths. In the framework, the features are consolidated to capture various spatial and temporal relationships associated with the human body, and are exploited to resolve depth ambiguity and self-occlusions, leading to more accurate estimations. Extensive experiments on Human3.6M and HumanEva-I show that our framework achieves competitive performance on 2D-to-3D human pose estimation in video. Code is available at: https://***/fll123/3Dhumanpose. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-task Collaborative Network for Image-Text Retrieval 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Qin, Xueyang Li, Lishuang Hao, Jing Ge, Meiling Huang, Jiayi Pang, Guangyao School of Computer Science and Technology Dalian University of Technology Dalian116024 China School of Computer Engineering Weifang University Weifang261061 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China

ISBN: (数字)9783031533112

ISBN: (纸本)9783031533105

Image-text retrieval aims to capture semantic relevance between images and texts. Most existing approaches rely solely on the image-text pairs to learn visual-semantic representation through fine-grained alignments while neglecting the potential beneficial impact of unimodal tasks on cross-modal retrieval. To this end, we present a Multi-Task Collaborative Network (MTCN) that leverages the synergy between multiple tasks to enhance the performance of image-text retrieval. Specifically, we introduce three unimodal tasks, including text-text matching, image multi-label classification, and text multi-label classification, and train together with target task image-text retrieval from the perspective of semantic constraints. Additionally, we employ a modality interaction module for image-text retrieval to discover interrelationships between these two modalities. Subsequently, a cascaded graph convolutional network combined with a multi-layer perceptron is used to infer the correlation scores between images and texts. We conduct comprehensive experiments on two benchmark datasets, Flickr30K and MSCOCO, and the quantitative and qualitative experimental results demonstrate the effectiveness of the proposed method. The source code is available at https://***/FlyCuteBird/MTCN. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Mixed Intrusion Detection System utilizing K-means and Extreme Gradient Boosting 2

A Mixed Intrusion Detection System utilizing K-means and Ext...

引用

2022 2nd International Conference on Communication Technology and Information Technology, ICCTIT 2022

作者： Lv, Haifeng Ji, Xiaoyu Ding, Yong Guangxi Key Laboratory of Machine Vision and Intelligent Control WuZhou University Wuzhou China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou China

The intrusion detection system (IDS) plays an important part because it offers an efficient way to prevent and mitigate cyber attacks. Numerous deep learning methods for intrusion anomaly detection have been developed as a result of recent advances in artificial intelligence (AI) in order to strengthen internet security. The balance among the high detection rate (DR), the low false alarm rate (FAR) and disaster of dimensionality is the crucial apprehension while devising an effective IDS. For the binary classification of intrusion detection systems, we present in this study a mixed model called K-means-XGBoost consisting of K-means and (Extreme Gradient Boosting, XGBoost) algorithms. The distributed computation of our method is achieved in Spark platform to rapidly separate normal events and anomaly events. In phrases of accuracy, DR, F1-score, recall, precision, and error indices FAR, the proposed model's performance is measured via the well-known dataset of NSL-KDD. The experimental outcomes indicate that our method is outstandingly better among accuracy, DR, F1-score, training time, and processing speed, compared to other models which are recently created. In particular, the accuracy, F1-score, and DR of the proposed model can achieve as high as 93.28%, 94.39%, and 99.22% in the NSL-KDD dataset, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Integrating local information-based link prediction algorithms with owa operator

Integrating local information-based link prediction algorith...

引用

3rd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2014

作者： Liu, James N.K. He, Yu-Lin Hu, Yan-Xing Wang, Xi-Zhao Shiu, Simon C.K. Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Key Laboratory in Machine Learning and Computational Intelligence of Hebei Province College of Mathematics and Computer Science Hebei University Baoding 071002 China

ISBN: (纸本)9789897580185

The objective of link prediction for social network is to estimate the likelihood that a link exists between two nodes x and y. There are some well-known local information-based link prediction algorithms (LILPAs) which have been proposed to handle this essential and crucial problem in the social network analysis. However, they can not adequately consider the so-called local information: The degrees of x and y, the number of common neighbors of nodes x and y, and the degrees of common neighbors of x and y. In other words, not any LILPA takes into account all the local information simultaneously. This limits the performances of LILPAs to a certain degree and leads to the high variability of LILPAs. Thus, in order to make full use of all the local information and obtain a LILPA with highly-predicted capability, an ordered weighted averaging (OWA) operator based link prediction ensemble algorithm (LPEOWA) is proposed by integrating nine different LILPAs with aggregation weights which are determined with maximum entropy method. The final experimental results on benchmark social network datasets show that LPEOWA can obtain higher prediction accuracies which is measured by the area under the receiver operating characteristic curve (AUC) in comparison with nine individual LILPAs. Copyright © 2014 SCITEPRESS.

关键词： Maximum entropy methods

来源：评论

学校读者我要写书评

暂无评论

Integrating document clustering and topic modeling

Integrating document clustering and topic modeling

引用

29th Conference on Uncertainty in Artificial Intelligence, UAI 2013

作者： Xie, Pengtao Xing, Eric P. State Key Laboratory on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing 100084 China Machine Learning Department Carnegie Mellon University Pittsburgh PA 15213 United States

Document clustering and topic modeling are two closely related tasks which can mutually benefit each other. Topic modeling can project documents into a topic space which facilitates effective document clustering. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clusters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which integrates document clustering and topic modeling into a unified framework and jointly performs the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document collection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global topics shared across clusters. We employ variational inference to approximate the posterior of hidden variables and learn model parameters. Experiments on two datasets demonstrate the effectiveness of our model.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

arXiv

引用

arXiv 2021年

作者： Mirza, Muhammad Jehanzeb Micorek, Jakub Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection. © 2021, CC BY.

关键词： Object recognition

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：