检索结果-内蒙古大学图书馆

4th International Conference on artificial intelligence in Information and Communication, ICAIIC 2022

作者： Kim, Jaeyoon O'Reilly, Una-May Seok, Junhee Korea University Department of Electrical and Computer Engineering Seoul Korea Republic of Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory Cambridge United States

ISBN: (纸本)9781665458184

There are many attempts to analyze the relationship between functional magnetic resonance imaging (fMRI) data and text stimuli representation in cognitive neuroscience research. Because programming codes are exemplary text stimuli, appropriate code representation for neuroscience research has been actively studied. In this paper, we focus on representing python code for fMRI research through natural language processing (NLP) techniques. We collect 7, 893 python codes of 23 question types from a code competition website and build three different models based on sequence-to-sequence, bag-of-words, and bigram representation. The model is evaluated to classify the types of questions. Finally, the model is applied to classify 108 python codes which were used for a cognitive neuroscience study of fMRI. We are looking forward to analyzing fMRI data with the proposed code representation for understanding how the human brain is active. © 2022 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

3D Face Modeling via Weakly-Supervised Disentanglement Network Joint Identity-Consistency Prior

3D Face Modeling via Weakly-Supervised Disentanglement Netwo...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Guohao Li Hongyu Yang Di Huang Yunhong Wang School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Generative 3D face models featuring disentangled controlling factors hold immense potential for diverse applications in computer vision and computer graphics. However, previous 3D face modeling methods face a challenge as they demand specific labels to effectively disentangle these factors. This becomes particularly problematic when integrating multiple 3D face datasets to improve the generalization of the model. Addressing this issue, this paper introduces a Weakly-Supervised Disentanglement Framework, denoted as WSDF, to facilitate the training of controllable 3D face models without an overly stringent labeling requirement. Adhering to the paradigm of Variational Autoencoders (VAEs), the proposed model achieves disentanglement of identity and expression controlling factors through a two-branch encoder equipped with dedicated identity-consistency prior. It then faithfully re-entangles these factors via a tensor-based combination mechanism. Notably, the introduction of the Neutral Bank allows precise acquisition of subject-specific information using only identity labels, thereby averting degeneration due to insufficient supervision. Additionally, the framework incorporates a label-free second-order loss function for the expression factor to regulate deformation space and eliminate extraneous information, resulting in enhanced disentanglement. Extensive experiments have been conducted to substantiate the superior performance of WSDF. Our code is available at https://***/liguoha096/WSDF.

关键词： Training Solid modeling Three-dimensional displays Deformation Face recognition Computational modeling Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Kang Shen, Zhishu Lei, Zhen Liu, Xianhui Zhang, Tiehua Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan China Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan China Tongji University College of Electronics and Information Engineering Shanghai China Tongji University School of Computer Science and Technology Shanghai China

Traffic signal control systems (TSCSs) are integral to intelligent traffic management, fostering efficient vehicle flow. Traditional approaches often simplify road networks into standard graphs, which results in a failure to consider the dynamic nature of traffic data at neighboring intersections, thereby neglecting higher-order interconnections necessary for real-time control. To address this, we propose a novel TSCS framework to realize intelligent traffic control. This framework collaborates with multiple neighboring edge computing servers to collect traffic information across the road network. To elevate the efficiency of traffic signal control, we have crafted a multi-agent soft actor-critic (MA-SAC) reinforcement learning algorithm. Within this algorithm, individual agents are deployed at each intersection with a mandate to optimize traffic flow across the road network collectively. Furthermore, we introduce hypergraph learning into the critic network of MA-SAC to enable the spatio-temporal interactions from multiple intersections in the road network. This method fuses hypergraph and spatio-temporal graph structures to encode traffic data and capture the complex spatio-temporal correlations between multiple intersections. Our empirical evaluation, tested on varied datasets, demonstrates the superiority of our framework in minimizing average vehicle travel times and sustaining high-throughput performance. This work facilitates the development of more intelligent urban traffic management solutions. We release the code to support the reproducibility of this work at https://***/Edun-Eyes/TSC. © 2002-2012 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior

arXiv

引用

arXiv 2024年

作者： Li, Guohao Yang, Hongyu Huang, Di Wang, Yunhong School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

ZHED is NP-complete 34

ZHED is NP-complete

引用

34th Canadian Conference on Computational Geometry, CCCG 2022

作者： Saha, Sagnik Demaine, Erik D. MIT United States MIT Computer Science and Artificial Intelligence Laboratory 32 Vassar St CambridgeMA02139 United States

We prove that the 2017 puzzle game ZHED is NPcomplete, even with just tiles numbered 1. Such a puzzle is defined by a set of unit-square tiles in a square grid, and a target square of the grid. A move consists of selecting a previously unselected tile and then filling the next unfilled square in a chosen direction from that tile (similar to Tipover and Cross Purposes). We prove the NP-completeness of deciding whether the target square can be filled, by a reduction from rectilinear planar monotone 3SAT. © 2022 Yeganeh Bahoo and Konstantinos Georgiou.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Timed Calculus with Mobility for Wireless Networks 23

A Timed Calculus with Mobility for Wireless Networks

引用

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Xie, Wanling Zhu, Huibiao Wu, Xi School of Computer Science and Artificial Intelligence Aliyun School of Big Data School of Software ChangZhou University ChangZhou China Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China School of Computer Science The University of Sydney Australia

ISBN: (纸本)9798400700705

Unreliability of communication links is a very common problem in wireless networks, and node mobility as one of significant features may importantly affect the reliability of communication links. In this paper, we present a Timed Calculus with Mobility for Wireless Networks called MTCWN to capture mobility in wireless networks. In our calculus, we introduce a random direction mobility model to depict node movement. With time passing, the mobility function and its timeout will be changed by this mobility model. Our calculus also describe local broadcast communication in wireless networks. Moreover, we study the operational semantics of the MTCWN calculus and illustrate the applications of the semantics rules by examples. © 2023 ACM.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Generating Editable Head Avatars with 3D Gaussian GANs

arXiv

引用

arXiv 2024年

作者： Li, Guohao Yang, Hongyu Men, Yifang Huang, Di Li, Weixin Yang, Ruijie Wang, Yunhong School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

Generating animatable and editable 3D head avatars is essential for various applications in computer vision and graphics. Traditional 3D-aware generative adversarial networks (GANs), often using implicit fields like Neural Radiance Fields (NeRF), achieve photorealistic and view-consistent 3D head synthesis. However, these methods face limitations in deformation flexibility and editability, hindering the creation of lifelike and easily modifiable 3D heads. We propose a novel approach that enhances the editability and animation control of 3D head avatars by incorporating 3D Gaussian Splatting (3DGS) as an explicit 3D representation. This method enables easier illumination control and improved editability. Central to our approach is the Editable Gaussian Head (EG-Head) model, which combines a 3D Morphable Model (3DMM) with texture maps, allowing precise expression control and flexible texture editing for accurate animation while preserving identity. To capture complex non-facial geometries like hair, we use an auxiliary set of 3DGS and tri-plane features. Extensive experiments demonstrate that our approach delivers high-quality 3D-aware synthesis with state-of-the-art controllability. Our code and models are available at https://***/liguohao96/EGG3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Field Grape Berry Counting Algorithm Based on Spatial Attention Mechanism

Field Grape Berry Counting Algorithm Based on Spatial Attent...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Tang, Yuling Li, Yanan Sun, Ming Qi, Yang Wuhan Institute of Technology School of Computer Science and Engineering School of Artificial Intelligence Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9781665465335

Automated grape yield estimation is one of the important aspects of intelligent vineyard management. In order to meet requirements of fast estimation and large-scale grape yield estimation in complex field environments, this paper proposes a Spatial Attention Grape Berry Counting Network (SAGBCNet). Firstly, the Spatial Feature Network (SFNet) is used to extract more spatial information of grape berries in image. Then attention mechanism is used to adaptively fit the long-distance context features of location and channel, so as to effectively distinguish the grape berry from background. Finally, through Feature Fusion Network, feature maps of different scales are fused to generate the predicted density map, and counting results of grape berries in the field are obtained. The experiment on the field grape counting dataset showed that SAGBCNet obtained a lower counting error for grape berries. The mean absolute error (MAE) and mean squared error (MSE) were 35.39 and 47.39 respectively. © 2022 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Data Markets: Trading Data using a Multi-Agent System

Machine Learning Data Markets: Trading Data using a Multi-Ag...

引用

2022 IEEE/WIC/ACM International Joint Conference on Web intelligence and Intelligent Agent Technology (WI-IAT)

作者： Hajar Baghcheband Carlos Soares Luis Paulo Reis FEUP - Faculty of Engineering LIACC-Artificial Intelligence & Computer Science Laboratory (member of LASI LA) University of Porto Porto Portugal FEUP - Faculty of Engineering LIACC-Artificial Intelligence & Computer Science Laboratory (member of LASI LA) University of Porto Fraunhofer AICOS Portugal Porto Portugal

The amount of data produced by distributed devices, such as smart devices and the IoT, is increasing continuously. The cost of transmitting data and also distributed computing power raise interest in distributed data mining (DDM). However, in a pure DDM scenario, data availability may not be enough to generate reliable models in a distributed environment. So, the ability to exchange data efficiently and effectively will become a crucial component of *** this paper, we propose the concept of the Machine Learning Data Market (MLDM), a framework for the exchange of data among autonomous agents. We consider a set of learning agents in a cooperative distributed ML, where agents negotiate data to improve the models they use locally. In the proposed data market, the system’s predictive accuracy is investigated, as well as the economic value of *** question addressed in this paper is: How data exchange among the agents will improve the accuracy of the learning model. Agent budget is defined as a limitation of negotiation. We defined a multi-agent system with negotiation and assessed it against the multi-agent system baseline and the single-agent system. The proposed framework is analyzed based on the different sizes of batch data collected over time to find out how this changes the effect of the negotiation on the accuracy of the model. The results indicate that even simple negotiation among agents increases their learning accuracy.

关键词： Upper bound Biological system modeling Distributed databases Machine learning Predictive models Data models Reliability

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Stable Reduced-Order Visuomotor Policies for Nonlinear Systems via Sums-of-Squares Optimization

Synthesizing Stable Reduced-Order Visuomotor Policies for No...

引用

IEEE Conference on Decision and Control

作者： Glen Chou Russ Tedrake Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA

We present a method for synthesizing dynamic, reduced-order output-feedback polynomial control policies for control-affine nonlinear systems which guarantees runtime stability to a goal state, when using visual observations and a learned perception module in the feedback control loop. We leverage Lyapunov analysis to formulate the problem of synthesizing such policies. This problem is nonconvex in the policy parameters and the Lyapunov function that is used to prove the stability of the policy. To solve this problem approximately, we propose two approaches: the first solves a sequence of sum-of-squares optimization problems to iteratively improve a policy which is provably-stable by construction, while the second directly performs gradient-based optimization on the parameters of the polynomial policy, and its closed-loop stability is verified a posteriori. We extend our approach to provide stability guarantees in the presence of observation noise, which realistically arises due to errors in the learned perception module. We evaluate our approach on several underactuated nonlinear systems, including pendula and quadrotors, showing that our guarantees translate to empirical stability when controlling these systems from images, while baseline approaches can fail to reliably stabilize the system.

关键词：

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：