检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FineFormer: Fine-Grained Adaptive Object Transformer for Image Captioning

FineFormer: Fine-Grained Adaptive Object Transformer for Ima...

引用

IEEE International Conference on data Mining (ICDM)

作者： Bo Wang Zhao Zhang Jicong Fan Mingbo Zhao Choujun Zhan Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Information Science and Technology Donghua University Shanghai China School of Electrical and Computer Engineering Nanfang College Guangzhou Guangzhou China School of Information Engineering Zhengzhou University Zhengzhou China

Image captioning is still a challenging task aiming at describing the contents of image by words. Current image caption methods usually assume the object relation to be important if the semantic and spatial geometric relationships between objects are close and large, but the relations meeting this assumption are not necessarily important to describe the contents of image in a fine-grained way. That is, the importance of fine-grained object relations is not properly taken into account. Besides, current Transformer based image caption models also fail to consider the importance of fine-grained objects, since they generate all the words of a sentence at one time, which cannot Figure out which objects are more important and vice versa. In this paper, we propose a novel Fine-grained Adaptive Object Transformer (FineFormer) network, which can jointly discover the importance of fine-grained objects and object relations for image captioning. Specifically, a new concept of adaptive soft-foreground attention is proposed to highlight the fine-grained objects dominating the descriptive contents. To characterize and calculate the important relations between fine-grained objects, we also propose an adaptive object relation attention to refine the object relation from the generation process of relation. As such, FineFormer can describe the contents of image more accurately, by reducing the interference of unimportant objects in the background. Extensive experiments on the highly-competitive MS-COCO dataset demonstrated the superiority of our FineFormer.

关键词： Adaptation models Adaptive systems Current transformers Semantics Interference data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Quality Assessment of Electrocardiogram Signals Using Contrastive Learning

Quality Assessment of Electrocardiogram Signals Using Contra...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Meiping Zhong Zuoyong Li ChuanSheng Wang Jiayan Huang WanQi Zhao Haoyi Fan College of Computer and Big Data Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona Spain New Engineering Industry College Putian University Putian China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Quality assessment of electrocardiogram (ECG) signals holds significant importance in reducing the high-frequency false alarms in automated arrhythmia diagnosis. Existing quality assessment methods primarily rely on empirical threshold setting or the calculation of relevant statistical values to formulate decision rules. However, the thresholds set in this manner are typically based on experience and knowledge, resulting in decision rules that lack flexibility and struggle to adapt to changes in the dataset. To address this issue, many researchers have turned to deep learning algorithms for ECG signal quality assessment. Nevertheless, most existing deep learning methods usually require large-scale and labeled ECG data for training, whose acquiring is typically challenging. Therefore, this paper proposes an efficient method for ECG signal quality assessment. First, we use a contrast learning framework to construct sample pairs through multilevel data augmentation. Second, a densely connected convolutional network (DenseNet) is used to improve the model's ability of extracting local features in ECG signals, and a Squeeze-and-Excitation attention module is introduced to make the model pay more attention to critical features. Finally, the feature representation is learned by minimizing the contextual contrast loss to bring similar samples closer and push dissimilar samples farther away. In this way, we can utilize the contrastive learning framework to extract temporal representations from unlabeled data and transfer them to downstream ECG signal quality assessment tasks. Extensive experiments on the Physionet/CinC Challenge 2011 dataset demonstrate that our approach outperforms most existing quality assessment methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chronic Disease Detection Via Non-negative Latent Feature Analysis

Chronic Disease Detection Via Non-negative Latent Feature An...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Leming Zhou Qing Li Mingsheng Shang College of Computer Science and Technology Chongqing University of Posts and Telecommunications Academy of Sciences Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

ISBN: (纸本)9781665440493

Chronic diseases such as coronary heart disease (CHD) are of significant harm to human health. However, chronic disease detection commonly relies on many examinations to implement reliable diagnosis, resulting in a fatal delay in therapy. On the other hand, obtained examination data are often incomplete with numerous missing data, which further increases the difficulty in detection. To address this issue, this paper develops an inherently non-negative latent feature analysis-incorporating into a chronic disease detection (INC) model. The main idea are as follows: 1) adopting an inherently non-negative latent feature analysis model with a non-linear function to extract the non-negative latent features from incomplete examination data for accurate prediction of the unknown missing ones; 2) detecting the chronic disease based on the high-dimensional and different types of inspection features via classifiers. Experiments on actual CHD datasets demonstrate that the proposed INC model outperforms state-of-the-art models in detection accuracy, which well fits the desire of preliminary screening on coronary heart disease (CHD).

关键词： Learning systems Heart Representation learning Analytical models Predictive models Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

Research on Path Planning of Robot Arm Based on RRT-connect Algorithm

Research on Path Planning of Robot Arm Based on RRT-connect ...

引用

第33届中国控制与决策会议

作者： Chaoli Zhao Xing Ma Chunyang Mu The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia North Minzu University School of Electrical and Information Engineering North Minzu University College of Mechatronic Engineering North Minzu University

To address the shortcomings of the RRT-connect algorithm in terms of low efficiency of path planning in sampling space and high randomness of node sampling,this paper proposes a three-source fast extended random tree algorithm(GT-RRT) combined with gravitational *** algorithm adds a third node as a new extension node between the start point and the target point,so that the algorithm can extend the random tree from the start point,the target point and the third *** the same time,a gravitational field is superimposed on each of the three nodes to guide the generation of nodes,reducing the search range of the null *** GT-RRT and RRT-connect algorithms are compared in 30 simulation experiments,and the results show that the improved algorithm has better path planning efficiency than the original algorithm in complex ***,this paper verifies the effectiveness of the improved algorithm in both the moveit simulation and the real environment by using the robot arm of Baxter robot as an example.

关键词： Path planning RRT-connect Gravitational potential field Robotic arm

来源：评论

学校读者我要写书评

暂无评论

A PDDL based Disaster Storyline Generation Approach

A PDDL based Disaster Storyline Generation Approach

引用

第三十九届中国控制会议

作者： Mingrong Tang Jinxin Ni Qifeng Zhou Automation Department of Xiamen University Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision

The rapid development of computer technology has brought challenges to the management of disaster *** an emergency occurs, a huge amounts of relevant information will be produced. In order to form a clear event development context from the overloaded Internet data and improve the corresponding efficiency of emergency events, in this paper, we propose a method for disaster storyline construction based on intelligent planning. Specifically, we first extract the semantic information from the News text to build a Planning Domain Definition Language（PDDL） domain model, which contains complete domain knowledge. Then we use a planner to plan the event storylines that meets the presets in the domain model. To our knowledge, this is the first attempt to combine natural language processing（NLP） technology with intelligent planning technology for disaster storyline generation. Different from the previous method, our proposed model is more focused both on the event evolve information and the government emergency measures, which can provide more reference value for relevant emergency response.

关键词： Planning Domain Definition Language Disaster Storyline Generation Dependency Parsing

来源：评论

学校读者我要写书评

暂无评论

Ddm-Vslam: Depth Prediction for Dynamic Culling Monocular Vision Slam

SSRN

引用

SSRN 2022年

作者： Bai, Zongwen Liu, Xiangzhen Zhou, Meili Wozniak, Marcin Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan’an University Yan’an716000 China School of Physics and Electronic Information Yan’an University Yan’an716000 China Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44100 Poland

Existing monocular visual SLAM solutions are mostly achieved by adding various sensors to improve the accuracy of monocular cameras, which is not the best performance of monocular cameras and is not friendly to existing hardware devices. This paper proposes a visual SLAM system based on ORB-SLAM3, which aims to maximize monocular resources. On the basis of monocular cameras, depth map prediction network is added to simulate depth cameras. Feature points are extracted using CNN and ORB fusion method, and feature filtering is carried out combining with depth maps. In order to improve the pose prediction accuracy of monocular camera in driving scenes and avoid the interference of dynamic objects to SLAM system, an image instance segmentation network is introduced in this paper. The code is public at https://***/MrLiuXiangzhen/DDM-SLAM . © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Estimating Power Consumption of Containers and Virtual Machines in data Centers

Estimating Power Consumption of Containers and Virtual Machi...

引用

IEEE International Conference on Cluster Computing

作者： Xusheng Zhang Ziyu Shen Bin Xia Zheng Liu Yun Li Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications

ISBN: (数字)9781728166773

ISBN: (纸本)9781728166780

Virtualization technologies provide solutions of cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many effective models for estimating power consumption of virtual machines (VM) have been proposed, few power estimation models of containers have been put forth. In this paper, we offer a fast-training piecewise regression model based on decision tree to build a VM power estimation model and estimate the containers' power by treating the container as a group of processes on the VM. In our model, we characterize the nonlinear relationship between power and features and realize the effective estimation of the containers on the VM. We evaluate the proposed model on 13 workloads in PARSEC and compare it with several models. The experimental results prove the effectiveness of our proposed model on most workloads. Moreover, the estimated power of the containers is in line with expectations.

关键词： Power demand Processor scheduling Estimation Containers Virtual machining data models Virtualization

来源：评论

学校读者我要写书评

暂无评论

A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future

arXiv

引用

arXiv 2024年

作者： Sun, Shilin An, Wenbin Tian, Feng Nan, Fang Liu, Qidong Liu, Jun Shah, Nazaraf Chen, Ping School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an710049 China Institute for Future Transport and Cities Coventry University Priory Street CoventryCV1 5FB United Kingdom Department of Engineering University of Massachusetts Boston BostonMA02125 United States

Artificial intelligence (AI) has rapidly developed through advancements in computational power and the growth of massive datasets. However, this progress has also heightened challenges in interpreting the "black-box" nature of AI models. To address these concerns, eXplainable AI (XAI) has emerged with a focus on transparency and interpretability to enhance human understanding and trust in AI decision-making processes. In the context of multimodal data fusion and complex reasoning scenarios, the proposal of Multimodal eXplainable AI (MXAI) integrates multiple modalities for prediction and explanation tasks. Meanwhile, the advent of Large Language Models (LLMs) has led to remarkable breakthroughs in natural language processing, yet their complexity has further exacerbated the issue of MXAI. To gain key insights into the development of MXAI methods and provide crucial guidance for building more transparent, fair, and trustworthy AI systems, we review the MXAI methods from a historical perspective and categorize them across four eras: traditional machine learning, deep learning, discriminative foundation models, and generative LLMs. We also review evaluation metrics and datasets used in MXAI research, concluding with a discussion of future challenges and directions. A project related to this review has been created at https://***/ShilinSun/mxai_review. Copyright © 2024, The Authors. All rights reserved.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

An ontology-supported inquiry learning technique

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第1期6卷 16-28页

作者： Xue, Xingsi Zhang, Jie Yang, Chaofan Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology No.33 Xuefu South Road University Town Minhou Fuzhou Fujian350118 China School of Computer Science and Engineering Yulin Normal University No.299 Education Middle Road Yulin City Guanxi Province537000 China School of Computer Science and Mathematics Intelligent Information Processing Research Center Fujian University of Technology No.33 Xueyuan Road University Town Minhou Fuzhou Fujian350118 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology No.1 Jinji Road Guilin Guangxi541004 China

Although Inquiry-based Learning (IBL) offers compelling opportunities for the engineering education, one of the challenges to the implementation of it is that the learner always lacks of the background knowledge. To provide him with the necessary knowledge when making the inquiry, this paper proposes an Ontology Supported Inquiry Learning technique (OSIL), which works on the basis of two ontologies, i.e. curriculum ontology and the learner’s ontology. The experimental results show that the constructed curriculum ontology and learner ontology is of high-quality, and the answers recommended by OSIL almost perfectly match with the true answers. From the experimental results, we can see that it is a feasible way of using the software engineering and prototype evolution method to construct the curriculum and learner ontology, and the individual inquiry based on two ontologies is able to provide the learners with high-quality personalized services. © 2021, Taiwan Ubiquitous Information. All rights reserved.

关键词： Curricula

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：