检索结果-内蒙古大学图书馆

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Meta Episodic learning with Dynamic Task Sampling for CLIP-based Point Cloud Classification

arXiv

引用

arXiv 2024年

作者： Ghose, Shuvozit Wang, Yang Department of Computer Science University of Manitoba Winnipeg Canada Department of Computer Science and Software Engineering Concordia University Montreal Canada

Point cloud classification refers to the process of assigning semantic labels or categories to individual points within a point cloud data structure. Recent works have explored the extension of pre-trained CLIP to 3D recognition. In this direction, CLIP-based point cloud models like PointCLIP, CLIP2Point have become state-of-the-art methods in the few-shot setup. Although these methods show promising performance for some classes like airplanes, desks, guitars, etc, the performance for some classes like the cup, flower pot, sink, nightstand, etc is still far from satisfactory. This is due to the fact that the adapter of CLIP-based models is trained using randomly sampled N-way K-shot data in the standard supervised learning setup. In this paper, we propose a novel meta-episodic learning framework for CLIP-based point cloud classification, addressing the challenges of limited training examples and sampling unknown classes. Additionally, we introduce dynamic task sampling within the episode based on performance memory. This sampling strategy effectively addresses the challenge of sampling unknown classes, ensuring that the model learns from a diverse range of classes and promotes the exploration of underrepresented categories. By dynamically updating the performance memory, we adaptively prioritize the sampling of classes based on their performance, enhancing the model’s ability to handle challenging and real-world scenarios. Experiments show an average performance gain of 3-6% on ModelNet40 and ScanobjectNN datasets in a few-shot setup. © 2024, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

EvoChain: A Framework for Tracking and Visualizing Smart Contract Evolution

EvoChain: A Framework for Tracking and Visualizing Smart Con...

引用

International Mining software Repositories, MSR

作者： Ilham Qasse Mohammad Hamdaqa Björn Þór Jónsson Department of Computer Science Reykjavik University Reykjavik Iceland Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada

ISBN: (数字)9798331501839

ISBN: (纸本)9798331501846

Tracking the evolution of smart contracts is challenging due to their immutable nature and complex upgrade mechanisms. We introduce EvoChain, a comprehensive framework and dataset designed to track and visualize smart contract evolution. Building upon data from our previous empirical study, EvoChain models contract relationships using a Neo4j graph database and provides an interactive web interface for exploration. The framework consists of a data layer, an API layer, and a user interface layer. EvoChain allows stakeholders to analyze contract histories, upgrade paths, and associated vulnerabilities by leveraging these components. Our dataset encompasses approximately 1.3 million upgradeable proxies and nearly 15,000 historical versions, enhancing transparency and trust in blockchain ecosystems by providing an accessible platform for understanding smart contract evolution.

关键词： software maintenance Databases Smart contracts Ecosystems Data visualization Data models Blockchains Stakeholders Security Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A Review of Semantic-Based Reasoning Framework for Context-Aware Mobile-Crowdsourcing 13

A Review of Semantic-Based Reasoning Framework for Context-A...

引用

13th International Conference on Information Technology in Asia, CITA 2023

作者： Abdulsalam, Nana Hauwa Muhammad, Sufri Mohamed, Raihani Universiti Putra Malaysia Department of Software Engineering and Information System Selangor Serdang43400 Malaysia Universiti Putra Malaysia Department of Computer Science Selangor Serdang43400 Malaysia

ISBN: (纸本)9798350326208

Technology has increased the interest and demand for pervasive systems which require contextual information to function at optimal capacity. There have been numbers of research in context-aware systems that has limited focused on the semantic-based approach in the crowdsourcing domain. Thus, it promotes challenges in the context and service acquisition and representation for reasoning control mechanism. This paper aims to review semantic-based reasoning framework with a focus on the mobile crowdsourcing domain. Different domains acquire different contextual information, either extrinsic or intrinsic. The review of the frameworks has help to formulate a process framework that applied semantic approach that has the important component for context-aware reasoning process. The framework can be used in the context-aware mobile crowdsourcing domain or can be generalized to other domain to aid reasoning control. Its advantage over other crowdsourcing frameworks which is focuses not only on context and service acquisition but also the representation on the acquired information. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis and Propagation of Feature Revisions in Preprocessor-based software Product Lines

Analysis and Propagation of Feature Revisions in Preprocesso...

引用

2024 software engineering, SE 2024

作者： Michelon, Gabriela K. Assunção, Wesley K.G. Grünbacher, Paul Egyed, Alexander Institute of Software Systems Engineering and LIT Lab Johannes Kepler University Linz Linz4040 Austria Department of Computer Science North Carolina State University RaleighNC27695 United States Institute of Software Systems Engineering Johannes Kepler University Linz Linz4040 Austria

This is a summary of a paper [Mi23] published in the IEEE International Conference on software Analysis, Evolution and Reengineering (SANER) 2023. It describes a tool-supported approach for analyzing and propagating f... 详细信息

ISBN: (纸本)9783885797371

关键词： computer software reusability

来源：评论

学校读者我要写书评

暂无评论

The Need for Greed in Artificial Decisionmakers

The Need for Greed in Artificial Decisionmakers

引用

International Symposium on Technology and Society (ISTAS)

作者： Nathaniel Kremer-Herman Ankur Gupta Department of Computer Science Seattle University Seattle USA Department of Computer Science and Software Engineering Butler University Indianapolis USA

ISBN: (数字)9798331540708

ISBN: (纸本)9798331540715

We usually teach our children not to be greedy. Many of the ethical principles ingrained in cultures worldwide emphasize the importance of one’s place in a larger community. However, there is need for some greed to prevent needless self-sacrifice. We explore this balancing act between caring for the broader community and caring for one’s own needs and desires through the lens of artificial decisionmaking agents. Using our modern reimplementation of the societal simulation Sugarscape, we explore the outcomes of societies where the agents employ varying amounts of greed. We show that entirely selfless and entirely selfish societies are doomed to collapse in most instances. We also show that societies that are 10% to 80% greedy have high wellbeing across a variety of commonsense metrics. These results highlight the exciting promise of developing computationally-derived guidelines for ethical behavior for individual agents which correspond to significant societal impacts.

关键词： Measurement Ethics Computational modeling Lenses Guidelines

来源：评论

学校读者我要写书评

暂无评论

Depth3DSketch: Freehand Sketching Out of Arm’s Reach in Virtual Reality

Depth3DSketch: Freehand Sketching Out of Arm’s Reach in Vir...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Bashar, Mohammad Raihanul Amini, Mohammadreza Stuerzlinger, Wolfgang Sarac, Mine Pfeuffer, Ken Machuca, Mayra Donaji Barrera Batmaz, Anil Ufuk Department of Computer Science & Software Engineering Concordia University MontrealQC Canada Simon Fraser University VancouverBC Canada Kadir Has University Istanbul Turkey Department of Computer Science Aarhus University Aarhus Denmark Faculty of Computer Science Dalhousie University HalifaxNS Canada

ISBN: (纸本)9798400713958

Due to the increasing availability and popularity of virtual reality (VR) systems, 3D sketching applications have also boomed. Most of these applications focus on peripersonal sketching, e.g., within arm’s reach. Yet, sketching in larger scenes requires users to walk around the virtual environment while sketching or to change the sketch scale repeatedly. This paper presents Depth3DSketch, a 3D sketching technique that allows users to sketch objects up to 2.5 m away with a freehand sketching technique. Users can select the sketching depth with three interaction methods: using the joystick on a single controller, the intersection from two controllers, or the intersection from the controller ray and the user’s gaze. We compared these interaction methods in a user study. Results show that users preferred the joystick to select visual depth, but there was no difference in user accuracy or sketching time between the three methods. © 2025 Copyright held by the owner/author(s).

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

EvoChain: A Framework for Tracking and Visualizing Smart Contract Evolution

arXiv

引用

arXiv 2025年

作者： Qasse, Ilham Hamdaqa, Mohammad Jónsson, Björn Þór Department of Computer Science Reykjavik University Reykjavik Iceland Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proposed intelligence systems based on digital Forensics: Review paper

引用

Materials Today: Proceedings 2023年 80卷 2647-2651页

作者： Ismael Sahib, Hussein Qahatan AlSudani, Mustafa Hasan Ali, Mohammed Qassim Abbas, Haydar Moorthy, Kohbalan Mundher Adnan, Myasar Faculty of Computer Science and Information Technology UniversitiTun Hussein Onn Malaysia Computer Techniques Engineering Department Faculty of Information Technology Imam Ja'afar Al-sadiq University Najaf Iraq Faculty of Computer Systems & Software Engineering Universiti Malaysia Pahang Kuantan Malaysia Islamic University Najaf Iraq Faculty of Engineering School of Computing Universiti Teknologi Malaysia 81310 Johor Bahru Malaysia

The field of information security, in general, has seen shifts a traditional approach to an intelligence system. Moreover, an increasing of researchers to focus on propose intelligence systems and framework based on the forensic case studies because of the limitations of traditional methods such as analysis intensive data manually, intelligence visualization to make the evidence more understandable and intelligence system for store data. However, most of these intelligence systems are still facing different limitations. Furthermore, the primary goal of this work analysis popular intelligence system that was used based on forensic. Moreover, propose new algorithms and hybrid model which it's achieved good results in dif-ferent other fields to develop the forensic systems in the future. © 2021

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Augmentation using the U-NET Architecture

Brain Tumor Augmentation using the U-NET Architecture

引用

2022 International Conference on Frontiers of Information Technology, FIT 2022

作者： Jabbar, Mohsin Siddiqui, Maria Hussain, Farhan Daud, Sultan Nust College of E&me Department of Computer and Software Engineering Islamabad Pakistan Namal University Department of Computer Science Mianwali Pakistan

ISBN: (纸本)9798350345933

Studies have found out that tumors in brain are one of the fiercest diseases which can ultimately lead to death. Gliomas are the most commonly found primary tumors that are very hard to predict and can be found anywhere in the brain. It is prime objective to differentiate the different tumor tissues such as enhancing tissues, edema, from healthy ones. To do this task, two types of segmentation techniques come into existent i.e. manual and automatic. The automation methods of brain tumor segmentation have gained ground over manual segmentation algorithms and further its estimation is very closer to clinical results. In this paper we propose a comprehensive U-NET architecture with modification in their layers for 2D slices segmentation as a major contribution to BRATS 2015 challenge. Then we enlisted different dataset that are available publicly i.e. BRATS and DICOM. Further, we present a robust frame- work inspired from U-NET model with addition and modification of layers and image pre-processing methodology such as contrast enhancement for visible input and output details. In this way our approach achieves highest dice score 0.92 on the publicly available BRATS 2015 dataset and with better time constraint i.e. training time decreases to 80-90 minute instead of previously 2 to 3 days. © 2022 IEEE.

关键词： Tumors

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：