检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Guo-Hao Wei, Yi-Lin Zheng, Dian Wu, Xiao-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In this work, we propose a novel discriminative framework for dexterous grasp generation, named Dexterous Grasp TRansformer (DGTR), capable of predicting a diverse set of feasible grasp poses by processing the object point cloud with only one forward pass. We formulate dexterous grasp generation as a set prediction task and design a transformer-based grasping model for it. However, we identify that this set prediction paradigm encounters several optimization challenges in the field of dexterous grasping and results in restricted performance. To address these issues, we propose progressive strategies for both the training and testing phases. First, the dynamic-static matching training (DSMT) strategy is presented to enhance the optimization stability during the training phase. Second, we introduce the adversarial-balanced test-time adaptation (AB-TTA) with a pair of adversarial losses to improve grasping quality during the testing phase. Experimental results on the DexGraspNet dataset demonstrate the capability of DGTR to predict dexterous grasp poses with both high quality and diversity. Notably, while keeping high quality, the diversity of grasp poses predicted by DGTR significantly outperforms previous works in multiple metrics without any data pre-processing. Codes are available at https://***/iSEE-laboratory/DGTR. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Distributed estimation on semi-supervised generalized linear model

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 3735-3775页

作者： Jiyuan Tu Weidong Liu Xiaojun Mao School of Mathematics Shanghai University of Finance and Economics Shanghai China School of Mathematical Sciences MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China

Semi-supervised learning is devoted to using unlabeled data to improve the performance of machine learning algorithms. In this paper, we study the semi-supervised generalized linear model (GLM) in the distributed setup. In the cases of single or multiple machines containing unlabeled data, we propose two distributed semi-supervised algorithms based on the distributed approximate Newton method. When the labeled local sample size is small, our algorithms still give a consistent estimation, while fully supervised methods fail to converge. Moreover, we theoretically prove that the convergence rate is greatly improved when sufficient unlabeled data exists. Therefore, the proposed method requires much fewer rounds of communications to achieve the optimal rate than its fully-supervised counterpart. In the case of the linear model, we prove the rate lower bound after one round of communication, which shows that rate improvement is essential. Finally, several simulation analyses and real data studies are provided to demonstrate the effectiveness of our method.

关键词： distributed learning semi-supervised learning generalized linear model

来源：评论

学校读者我要写书评

暂无评论

EmoDamp: A Model for Speaker Emotion Inference in Dialogues with Bidirectional Emotion Damping Mechanism 6

EmoDamp: A Model for Speaker Emotion Inference in Dialogues ...

引用

6th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2023

作者： Jiang, Yueqi Sun, Xiao Wang, Jiamin AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei China

ISBN: (纸本)9798400709203

Emotion analysis in conversation has been a popular research topic in the natural language processing field. While much of the existing research has focused on emotion recognition in conversation, the emotion inference task in conversation is more challenging due to its specific prerequisites. In this paper, we propose EmoDamp, a novel model for the conversational emotion inference task. By referring to psychological theories, a bidirectional emotion damping network(BED Net) is designed to model the emotion generation mechanism. Furthermore, external commonsense knowledge is also used to supplement the prediction results to make them more consistent with authentic logic. Finally, a conditional random field (CRF) is used to capture the potential constraints of the emotion transfer process in conversation and simulate emotion contagion. Experimental results on two benchmark datasets demonstrate that EmoDamp outperforms the baseline model, achieving improved results on each emotion category and showcasing its effectiveness. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Nonseparating Independent Sets and Maximum Genus of Graphs

引用

Acta Mathematicae Applicatae Sinica 2022年第3期38卷 719-728页

作者： Chao YANG Han REN Er-ling WEI Center of Intelligent Computing and Applied Statistics School of MathematicsPhysics and StatisticsShanghai University of Engineering ScienceShanghai 201620China School of Mathematical Sciences East China Normal UniversityShanghai 200241China Shanghai Key Laboratory of PMMP Shanghai 200241China School of Mathematics Renmin University of ChinaBeijing 100872China

A subset I of vertices of an undirected connected graph G is a nonseparating independent set(NSIS)if no two vertices of I are adjacent and G􀀀I is *** Z(G)denote the cardinality of a maximum NSIS of G.A nonseparating independent set containing Z(G)vertices is called the maximum nonseparating independent *** this paper,we firstly give an upper bound for Z(G)of regular graphs and determine Z(G)for some types of circular ***,we show a relationship between Z(G)and the maximum genus M(G)of a general ***,an important formula is provided to compute Z(G),i.e.,Z(G)=Σx∈I dI(x)+2(M(G-I)-γM(G))+(ξ(G-I)-ξ(G));where I is the maximum nonseparating independent set and ξ(G)is the Betti deficiency(Xuong,1979)of G.

关键词： nonseparating independent sets maximum genus graph embedding decycling set

来源：评论

学校读者我要写书评

暂无评论

Hubble parameter estimation via dark sirens with the LISA-Taiji network

引用

National Science Review 2022年第2期9卷 52-62页

作者： Renjie Wang Wen-Hong Ruan Qing Yang Zong-Kuan Guo Rong-Gen Cai Bin Hu Department of Astronomy Beijing Normal University CAS Key Laboratory of Theoretical Physics Institute of Theoretical Physics Chinese Academy of Sciences School of Physical Sciences University of Chinese Academy of Sciences College of Engineering Physics Shenzhen Technology University School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences

The Hubble parameter is one of the central parameters in modern cosmology,and describes the present expansion rate of the *** values of the parameter inferred from late-time observations are systematically higher than those inferred from early-time measurements by about 10%.To reach a robust conclusion,independent probes with accuracy at percent levels are *** waves from compact binary coalescence events can be formulated into the standard siren approach to provide an independent Hubble parameter *** future space-borne gravitational wave observatory network,such as the LISA-Taiji network,will be able to measure the gravitational wave signals in the millihertz bands with unprecedented *** including several statistical and instrumental noises,we show that,within a five-year operation time,the LISA-Taiji network is able to constrain the Hubble parameter within 1% accuracy,and possibly beats the scatters down to 0.5% or even better.

关键词： gravitational waves Hubble parameter super massive black hole

来源：评论

学校读者我要写书评

暂无评论

Multiple Images Steganography of JPEG Images Based on Optimal Payload Distribution

引用

Computer Modeling in engineering & Sciences 2020年第10期125卷 417-436页

作者： Yang Pei Xiangyang Luo Yi Zhang Liyan Zhu Zhong Yuan Network Security Research Institute Zhengzhou UniversityZhengzhou450000China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450000China

Multiple images steganography refers to hiding secret messages in multiple natural images to minimize the leakage of secret messages during ***,the main multiple images steganography algorithms mainly distribute the payloads as sparsely as possible inmultiple cover images to improve the detection error rate of stego *** order to enable the payloads to be accurately and efficiently distributed in each cover image,this paper proposes a multiple images steganography for JPEG images based on optimal payload ***,the algorithm uses the principle of dynamic programming to redistribute the payloads of the cover images to reduce the time required in the process of payloads ***,by reducing the difference between the features of the cover images and the stego images to increase the detection error rate of the stego ***,this paper uses a data decomposition mechanism based on Vandermonde *** if part of the data is lost during the transmission of the secret messages,as long as the data loss rate is less than the data redundancy rate,the original secret messages can be *** results show that the method proposed in this paper improves the efficiency of payloads distribution compared with existing multiple images *** the same time,the algorithm can achieve the optimal payload distribution of multiple images steganography to improve the anti-statistical detection performance of stego images.

关键词： Multiple images steganography payloads distribution dynamic programming messages recovery

来源：评论

学校读者我要写书评

暂无评论

A study of grid failure mode drivers and methods for accelerated life testing of a 30cm diameter ion thruster

引用

Plasma Science and Technology 2023年第11期25卷 122-132页

作者：孙明明龙建飞陈娟娟杨威郭伟龙陈新伟 Science and Technology on Vacuum Technology and Physics Laboratory Lanzhou Institute of PhysicsLanzhou 730000People’s Republic of China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024People’s Republic of China Gravitational Wave Universe Taiji Laboratory Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024People’s Republic of China Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province University of Chinese Academy of SciencesHangzhou 310024People’s Republic of China School of Electrical Engineering Chongqing University of Science and TechnologyChongqing 404100People’s Republic of China

In view of the high cost caused by the 1:1 lifetime verification test of ion thrusters,the lifetime acceleration test should be *** work uses the PIC-MCC(Particle-in-Cell MonteCarlo Collision)method to analyze the five failure factors that lead to the failure of the accelerator grid of a 30 cm diameter ion thruster under the working mode of 5 k ***,the acceleration stress levels corresponding to different failure factors are *** results show that background pressure has the highest stress level on the grid's *** accelerator grid aperture's mass sputtering rate under the rated vacuum degree(1×10^(-4)Pa)of 5 k W work mode is 8.78 times that of the baseline vacuum degree(1×10^(-6)Pa),and the mass sputtering rate under worse vacuum degree(5×10^(-3)Pa)is 5.08 times that of 1×10^(-4)*** the influence of the other four failure factors,namely,the voltage of the accelerator grid,upstream plasma density,the screen grid voltage and mass utilization efficiency,the mass sputtering rates of the accelerator grid hole are 2.32,2.67,1.98 and 2.51 times those of the accelerator grid hole under baseline condition,*** ion sputtering results of two 30 cm diameter ion thrusters(both installed with new grids assembly)after working for 1000 h show that the mass sputtering rate of the accelerator grid hole under vacuum conditions of 5×10^(-3)Pa is 4.54 times that under the condition of 1×10^(-4)Pa,and the comparison error between simulation results and test results of acceleration stress is about 10%.In the subsequent ion thruster lifetime verification,the working vacuum degree can be adjusted according to the acceleration stress level of background pressure,so as to shorten the test time and reduce the test cost.

关键词： ion thruster failure factors acceleration stress level

来源：评论

学校读者我要写书评

暂无评论

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

arXiv

引用

arXiv 2025年

作者： Gu, Shengbo Qiu, Yu-Kun Tang, Yu-Ming Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model. © 2025, CC BY.

关键词： Federated learning

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：