检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zha, Yaohua Wang, Jinpeng Dai, Tao Chen, Bin Wang, Zhi Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University China College of Computer Science and Software Engineering Shenzhen University China Harbin Institute of Technology Shenzhen China Research Center of Artificial Intelligence Peng Cheng Laboratory China

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at https://***/zyh16143998882/ICCV23-IDPT. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sentence Constituent-Aware Aspect-Category Sentiment Analysis with Graph Attention Networks 1

引用

9th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2020

作者： Li, Yuncong Yin, Cunxiang Zhong, Sheng-hua Baidu Inc. Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9783030604509

ISBN: (纸本)9783030604493

Aspect category sentiment analysis (ACSA) aims to predict the sentiment polarities of the aspect categories discussed in sentences. Since a sentence usually discusses one or more aspect categories and expresses different sentiments toward them, various attention-based methods have been developed to allocate the appropriate sentiment words for the given aspect category and obtain promising results. However, most of these methods directly use the given aspect category to find the aspect category-related sentiment words, which may cause mismatching between the sentiment words and the aspect categories when an unrelated sentiment word is semantically meaningful for the given aspect category. To mitigate this problem, we propose a Sentence Constituent-Aware Network (SCAN) for aspect-category sentiment analysis. SCAN contains two graph attention modules and an interactive loss function. The graph attention modules generate representations of the nodes in sentence constituency parse trees for the aspect category detection (ACD) task and the ACSA task, respectively. ACD aims to detect aspect categories discussed in sentences and is a auxiliary task. For a given aspect category, the interactive loss function helps the ACD task to find the nodes which can predict the aspect category but cant predict other aspect categories. The sentiment words in the nodes then are used to predict the sentiment polarity of the aspect category by the ACSA task. The experimental results on five public datasets demonstrate the effectiveness of SCAN (Data and code can be found at https://***/l294265421/SCAN). © 2020, Springer Nature Switzerland AG.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Simple Dashboard for OpenStack Horizon 2021

A Simple Dashboard for OpenStack Horizon

引用

2021 4th International Conference on Computing and Big Data

作者： Hongbin Wang Shaoxu Li Dan Deng Leixiao Li Jing Gao Jie Li College of Data Science and Application Inner Mongolia University of Technology China and Inner Mongolia Autonomous Region Software Service Engineering Technology Research Center based on Big Data China College of Computer and Information Engineering Inner Mongolia Agricultural University China

ISBN: (纸本)9781450387194

OpenStack is an open source cloud computing management project, which allows flexible resources applying. The traditional OpenStack dashboard is inflexible, thus a simple dashboard is designed. The simple dashboard integrates keystone, horizon, grace, nova, neutron, swift and other components, communicates with the traditional OpenStack dashboard and runs in the form of docker container. We implemented simple dashboard on a small cloud platform. Compared with the traditional dashboard, the interface of simple dashboard is simpler, more flexible and easy to use.

关键词： Cloud computing Horizon OpenStack Simple dashboard

来源：评论

学校读者我要写书评

暂无评论

Diversifying Agent’s Behaviors in Interactive Decision Models

arXiv

引用

arXiv 2022年

作者： Pan, Yinghui Zhang, Hanyi Zeng, Yifeng Ma, Biyang Tang, Jing Ming, Zhong Department of Computer and Information Sciences Northumbria University NewcastleNE7 7UX United Kingdom College of Computer Science and Software Engineering Shenzhen University Shenzhen510810 China

Modelling other agents’ behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in an uncertain environment. However, modelling insufficiency occurs when the agents are competitive and the subject agent can not get full knowledge about other agents. Even when the agents are collaborative, they may not share their true behaviors due to their privacy concerns. In this article, we investigate into diversifying behaviors of other agents in the subject agent’s decision model prior to their interactions. Starting with prior knowledge about other agents’ behaviors, we use a linear reduction technique to extract representative behavioral features from the known behaviors. We subsequently generate their new behaviors by expanding the features and propose two diversity measurements to select top-K behaviors. We demonstrate the performance of the new techniques in two well-studied problem domains. This research will contribute to intelligent systems dealing with unknown unknowns in an open artificial intelligence world. Copyright © 2022, The Authors. All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Symbolic Verification of Fuzzy Logic Models

Symbolic Verification of Fuzzy Logic Models

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Siang Zhao Zhongyang Li Zhenbang Chen Ji Wang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China

Fuzzy logic is widely applied in various applications. However, verifying the correctness of fuzzy logic models can be difficult. This extended abstract presents our ongoing work on verifying fuzzy logic models. We treat a fuzzy logic model as a program and propose a verification method based on symbolic execution for fuzzy logic models. We have developed and implemented the environment models for the common functions and the inference rules in fuzzy logic models. Our preliminary evaluation shows the potential of our verification method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Spot Instance Reliability and Security Using Cloud-Native Data and Tools

arXiv

引用

arXiv 2025年

作者： Saqib, Muhammad Malhotra, Shubham Mehta, Dipkumar Jangid, Jagdish Yashu, Fnu Dixit, Sachin Texas Tech University Dept. of Computer Science United States Rochester Institute of Technology Dept. of Software Engineering United States C.K.Pithawalla College of Eng. and Tech India Infinera Corp United States Stony Brook University Dept. of Computer Science United States Stripe Inc United States

This paper presents "Cloudlab," a comprehensive, cloud-native laboratory designed to support network security research and training. Built on Google Cloud and adhering to GitOps methodologies, Cloudlab facilitates the creation, testing, and deployment of secure, containerized workloads using Kubernetes and serverless architectures. The lab integrates tools like Palo Alto Networks firewalls, Bridgecrew for "Security as Code," and automated GitHub workflows to establish a robust Continuous Integration/Continuous Machine Learning pipeline. By providing an adaptive and scalable environment, Cloudlab supports advanced security concepts such as role-based access control, Policy as Code, and container security. This initiative enables data scientists and engineers to explore cutting-edge practices in a dynamic cloud-native ecosystem, fostering innovation and improving operational resilience in modern IT infrastructures. Copyright © 2025, 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

Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding

arXiv

引用

arXiv 2023年

作者： Zhang, Taolin He, Sunan Dai, Tao Chen, Bin Wang, Zhi Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University China College of Computer Science and Software Engineering Shenzhen University China Harbin Institute of Technology Shenzhen China Research Center of Artificial Intelligence Peng Cheng Laboratory China

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vision-language pre-training framework 3DVLP (3D vision-language pre-training with object contrastive learning), which transfers flexibly on 3D vision-language downstream tasks. 3DVLP takes visual grounding as the proxy task and introduces Object-level IoU-guided Detection (OID) loss to obtain high-quality proposals in the scene. Moreover, we design Object-level Cross-Contrastive alignment (OCC) task and Object-level Self-Contrastive learning (OSC) task to align the objects with descriptions and distinguish different objects in the scene, respectively. Extensive experiments verify the excellent performance of 3DVLP on three 3D vision-language tasks, reflecting its superiority in semantic 3D scene understanding. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Decentralized Optimization of Coupled Power-Transportation Network considering Environment-aware User Behavior

Decentralized Optimization of Coupled Power-Transportation N...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Zhiao Cao Yinghua Han Qiang Zhao Jinkuan Wang Shuyi Zhao School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China College of Information Science and Engineering Northeastern University Shenyang China Faculty of business and law Taylor's University Subang Jaya Malaysia

The increasing popularity of electric vehicles (EVs) has led to a growing need for electrified transportation, which has further deepened the interconnectedness of power and transportation networks. To account for EV drivers' preferences in route selection, this paper proposes an environment-aware dispatch model that coordinates the integrated power and transportation network to achieve greater economic benefits and increased utilization of renewable energy. The model employs discrete choice models with an environmental factor to represent user behavior. The constructed user behavior models serve as the basis for the integrated optimal traffic-power flow (IOTPF) model, which aims to optimize the flow of both power and traffic while minimizing the total cost of EV travel and maximizing the use of renewable energy sources. The paper employs a decentralized optimization algorithm to solve the equilibrium flows of the IOTPF model. Numerical results illustrate how the environment-aware user behavior impacts travel costs and the use of renewable energy, demonstrating the effectiveness of the IOTPF model in coordinating the optimal strategy of the integrated power-transportation network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Texture and Orientation-based Feature Extraction for Robust Facial Expression Recognition

Texture and Orientation-based Feature Extraction for Robust ...

引用

International Conference on software engineering Research, Management and Applications (SERA)

作者： Sajid Ali Khan Mohammed Bin Abdulrahman Alawairdhi Mousa AL-Akhras Department of Software Engineering Foundation University Islamabad Islamabad Pakistan College of Computing and Informatics Saudi Electronic University Saudi Arabia Computer Information Systems Department King Abdullah II School for Information Technology The University of Jordan Amman

Facial expressions are the most effective way to characterize people’s motives, emotions, and feelings. Several new methods are proposed each year; however, the accuracy of facial expression recognition still needs to be improved especially in uncontrolled conditions. In this paper, we propose a hybrid facial expression model that considers both texture and orientation features to classify expressions. Two types of descriptors namely Local binary pattern and Weber local descriptor are used to preserve the local intensity information and orientation of edges. In the next step, computing the Histograms of oriented gradients (HOG) features from the Local binary pattern and Weber local descriptor images to capture micro-expressions. Then, the AdaBoost feature selection algorithm is utilized to choose the best features from the combined HOG features. The results of the experiments demonstrate that the method proposed in this study performs better than existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Better Queries for Aspect-Category Sentiment Classification 19

Better Queries for Aspect-Category Sentiment Classification

引用

19th China National Conference on Computational Linguistics, CCL 2020

作者： Li, Yuncong Yin, Cunxiang Zhong, Sheng-hua Zhong, Huiqiang Luo, Jinchang Xu, Siqi Wu, Xiaohui Baidu Inc. Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9783030630300

Aspect-category sentiment classification (ACSC) aims to identify the sentiment polarities towards the aspect categories mentioned in a sentence. Because a sentence often mentions more than one aspect category and expresses different sentiment polarities to them, finding aspect category-related information from the sentence is the key challenge to accurately recognize the sentiment polarity. Most previous models take both sentence and aspect category as input and query aspect category-related information based on the aspect category. However, these models represent the aspect category as a context-independent vector called aspect embedding, which may not be effective enough as a query. In this paper, we propose two contextualized aspect category representations, Contextualized Aspect Vector (CAV) and Contextualized Aspect Matrix (CAM). Specifically, we use the coarse aspect category-related information found by the aspect category detection task to generate CAV or CAM. Then the CAV or CAM as queries are used to search for fine-grained aspect category-related information like aspect embedding by aspect-category sentiment classification models. In experiments, we integrate the proposed CAV and CAM into several representative aspect embedding-based aspect-category sentiment classification models. Experimental results on the SemEval-2014 Restaurant Review dataset and the Multi-Aspect Multi-Sentiment dataset demonstrate the effectiveness of CAV and CAM. © 2020, Springer Nature Switzerland AG.

关键词： Embeddings

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：