检索结果-内蒙古大学图书馆

IEEE Annual International Symposium Virtual Reality

作者： Yiwei Bao Jiaxi Wang Zhimin Wang Feng Lu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

Recent research based on hand-eye coordination has shown that gaze could improve object selection and translation experience under certain scenarios in AR. However, several limitations still exist. Specifically, we investigate whether gaze could help object selection with heavy 3D occlusions and help 3D object translation in the depth dimension. In addition, we also investigate the possibility of reducing the gaze calibration burden before use. Therefore, we develop new methods with proper gaze guidance for 3D interaction in AR, and also an implicit online calibration method. We conduct two user studies to evaluate different interaction methods and the results show that our methods not only improve the effectiveness of occluded objects selection but also alleviate the arm fatigue problem significantly in the depth translation task. We also evaluate the proposed implicit online calibration method and find its accuracy comparable to standard 9 points explicit calibration, which makes a step towards practical use in the real world.

关键词： Three-dimensional displays Design methodology Estimation User interfaces Fatigue Calibration Task analysis

来源：评论

学校读者我要写书评

暂无评论

High-Order Differential Regularizing Implicit Surface Representation of Point Cloud

High-Order Differential Regularizing Implicit Surface Repres...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuhang Cheng Ziyang Fan Hongyu Wu Xiaogang Wang College of Computer and Information Science Southwest University Chongqing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Reconstructing surfaces from diverse raw data in computer graphics poses an enduring challenge. While recent methods deploy neural networks for direct implicit surface reconstruction, they struggle with degraded raw data quality, especially in edge regions. To address this, we advocate for employing high-order total generalized variation (TGV) as a regularization term for implicit surface representation. Acknowledging the non-trivial nature of extending typical image processing methods to implicit surfaces, we present an end-to-end trainable network framework for TGV in implicit surface reconstruction. This approach preserves sharp features, enhances smooth region recovery, and minimizes artificial artifacts. Simultaneously, we address the challenge of increased computational complexity associated with current algorithms by predicting it directly through an implicit neural function. Experimental results demonstrate the efficacy of our technical approach, providing a promising solution for robust implicit surface reconstruction.

关键词： Point cloud compression Surface reconstruction Image edge detection Data integrity Neural networks computer graphics Prediction algorithms Computational complexity Image reconstruction Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees

arXiv

引用

arXiv 2023年

作者： Marzari, Luca Corsi, Davide Marchesini, Enrico Farinelli, Alessandro Cicalese, Ferdinando Department of Computer Science University of Verona Italy Laboratory for Information & Decision Systems Massachusetts Institute of Technology United States

Identifying safe areas is a key point to guarantee trust for systems that are based on Deep Neural Networks (DNNs). To this end, we introduce the AllDNN-Verification problem: given a safety property and a DNN, enumerate the set of all the regions of the property input domain which are safe, i.e., where the property does hold. Due to the #P-hardness of the problem, we propose an efficient approximation method called ϵ-ProVe. Our approach exploits a controllable underestimation of the output reachable sets obtained via statistical prediction of tolerance limits, and can provide a tight —with provable probabilistic guarantees— lower estimate of the safe areas. Our empirical evaluation on different standard benchmarks shows the scalability and effectiveness of our method, offering valuable insights for this new type of verification of DNNs. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Parallelism or Fairness? How to Be Friendly for SSDs in Cloud Environments

Parallelism or Fairness? How to Be Friendly for SSDs in Clou...

引用

IEEE International Conference on Cluster Computing

作者： Yang Zhou Fang Wang Zhan Shi Dan Feng Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology Ministry of Education of China Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350358711

ISBN: (纸本)9798350358728

Modern SSDs achieve low latency and high throughput by utilizing multiple levels of SSD parallelism. Fairness is also a critical design consideration in cloud environments and has inspired great interest in recent years to study it. However, we find that excessive striving for SSD parallelism can inadvertently harm the SSD fairness due to the striped data layout. We observe from our experimental analysis that some common access patterns in cloud loads (e.g., high-intensity I/O) are not addressed by SSD parallelism, which can affect both SSD parallelism and fairness. In this paper, we analyze two address mapping policies with orthogonal characteristics from SSD parallelism and fairness perspectives. Based on extensive experiments and observations, we schedule a hybrid address mapping policy to achieve fairness of SSDs in cloud environments by distinguishing different I/O access modes and cold/hot data, while ensuring SSD performance. Experimental results on the latest block-level I/O traces show that our approach significantly improves performance and fairness by up to 77.3% and 62.8%, respectively, over the previous schemes with negligible cost. Meanwhile, it can also reduce the write amplification by 23.5% to 33.5%.

关键词： Schedules Layout Interference Parallel processing Predictive models Throughput Data models Resource management Decision trees Low latency communication

来源：评论

学校读者我要写书评

暂无评论

Transforming vision transformer: towards efficient multi-task asynchronous learning 24

Transforming vision transformer: towards efficient multi-tas...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Hanwen Zhong Jiaxin Chen Yutong Zhang Di Huang Yunhong Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang University China and School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798331314385

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Formulation of Optimization Problems with Radiation Field Phases as Design Variables for Pattern Synthesis of Linear Antenna Arrays

引用

China Communications 2022年第12期19卷 86-100页

作者： Fei Zhao Jun He Sanyou Zeng Changhe Li Qinghui Xu Zhigao Zeng School of Mechanical Engineering and Electronic Information China University of GeosciencesWuhan 430074China Science and Technology on Blind Signal Processing Laboratory Southwest Electronics and Telecommunication Technology Research InstituteChengdu 610041China School of Automation China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074China College of Computer Hunan University of TechnologyZhuzhou CityHunan Province412007China

Pattern synthesise of antenna arrays is usually complicated optimization problems,while evolutionary algorithms(EAs)are promising in solving these *** paper does not propose a new EA,but does construct a new form of optimization *** new optimization formulation has two differences from the common *** is the objective function is the field error between the desired and the designed,not the usual amplitude error between the desired and the *** difference is beneficial to decrease complexity in some *** second difference is that the design variables are changed as phases of desired radiation field within shaped-region,instead of excitation *** difference leads to the reduction of the number of design variables.A series of synthesis experiments including equally and unequally spaced linear arrays with different pattern shape requirements are applied,and the effectiveness and advantages of the proposed new optimization problems are *** results show that the proposing a new optimization formulation with less complexity is as significant as proposing a new algorithm.

关键词： pattern synthesis evolutionary algorithms linear antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Diabetes Type Using Random Forest Algorithm and SVM for Improving Accuracy 1

引用

International Conference on Advances in Communication technology and computer Engineering, ICACTCE 2023

作者： Hai, Tao Zhou, Jincheng Olatunji, Timothy A. Ajoboh, Oluwakemi A. Chen, Lee Iwendi, Celestine Omeoga, Nkechi Sinha, Anurag School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Guiyang550025 China School of Information and Artificial Intelligence Nanchang Institute of Science and Technology Nanchang China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Qiannan Duyun558000 China School of Creative Technologies University of Bolton BoltonBL3 5AB United Kingdom Manchester Metropolitan University Manchester United Kingdom Department of Computer Science and Information Technology IGNOU New Delhi India

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

To improve the accuracy in the detection of diabetes-type diagnosis using Random Forest Algorithm and Support Vector Method. A dataset on diabetes was collected on ***. Support vector method analysis was performed on the data using kernel as linear, poly, and rbf with random state = 42 and test size = 0.2. The Random Forest Algorithm with n_estimators = 100 has the same accuracy as the support vector method with the kernel as rbf. When it comes to type diagnosis for a patient having diabetes, the Random Forest Algorithm and Support Vector Method with kernel rbf can be used, unlike another kernel of the Support Vector Method. The dataset was also visualized using power. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

Prompting Large Language Models with Answer Heuristics for K...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Reward Distribution Mechanism Based on Temporal Attention in Episodic Multi-Agent Reinforcement Learning 6

Research on Reward Distribution Mechanism Based on Temporal ...

引用

6th Asian Conference on Artificial Intelligence technology, ACAIT 2022

作者： Fang, Baofu Cao, Mingkuan Wang, Zaijun Wang, Hao Hefei University of Technology Intelligent Interconnected Systems Laboratory of Anhui Province School of Computer Science and Information Engineering Hefei China Civil Aviation Flight University of China Key Laboratory of Flight Techniques and Flight Safety Guanghan China

ISBN: (纸本)9781665453110

In episodic multi-agent reinforcement learning, we study how to distribute episodic rewards at the end of an episode by trajectory time steps to obtain high-quality and interpretable learning reward signals to guide agent training. This paper proposes a reward distribution method based on temporal attention. This method is used to characterize the influence of actions on state transitions along the trajectory, and the effect of each influence on the global reward at each time step. This method is combined with a deep deterministic strategy, and a multi-agent algorithm based on the temporal attention reward distribution mechanism is proposed to speed up the convergence speed of the agent. The effectiveness of the algorithm is verified in a multi-agent pursuit environment. Compared with other reward distribution methods, the method in this paper converges faster and obtains higher rewards. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Code Generation Based on Quality-Aware Reordering

Code Generation Based on Quality-Aware Reordering

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Yuan Song Luo Yu College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Translation efforts from natural language to code generation have achieved great success with large pre-trained language models. However, selecting the correct code output for the problem posed by the generated set of candidate codes is still challenging. In this paper, we address this problem by proposing an outcome-based quality-aware reordering method for code selection. This method scores each code by whether the set of candidate codes passes the test cases or not as a reference to select the top k best code outputs. In addition, this method depends on the quality and number of test cases. However, it is impractical to manually create a large number of test cases for each problem, so this paper adopts an automated approach that utilizes the current model to generate test cases for each problem. The experimental results show that the approach proposed in this paper obtains a significant improvement in the pass@k benchmark for each model, and the correctness and quality of test cases generated automatically using the model are discussed experimentally. Summarizing the experimental results and discussions, the result-based quality-aware reordering method proposed in this paper achieves a significant improvement in solving the problem of selecting the correct output from natural language to code generation, effectively improves the accuracy of evaluation by automating the generation of test cases, and provides an effective solution to improving the correctness of code generation.

关键词： Codes Accuracy Computational modeling Estimation Signal processing Benchmark testing

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：