检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Yunbo Tao Daizong Liu Pan Zhou Yulai Xie Wei Du Wei Hu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wangxuan Institute of Computer Technology Peking University

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the white-box setting to iteratively update the coordinate perturbations based on gradients, or utilize the output model logits to estimate noisy gradients in the black-box setting. However, these attack methods are hard to be deployed in real-world scenarios since realistic 3D applications will not share any model details to users. Therefore, we explore a more challenging yet practical 3D attack setting, i.e., attacking point clouds with black-box hard labels, in which the attacker can only have access to the prediction label of the input. To tackle this setting, we propose a novel 3D attack method, termed 3D Hard-label attacker (3DHacker), based on the developed decision boundary algorithm to generate adversarial samples solely with the knowledge of class labels. Specifically, to construct the class-aware model decision boundary, 3DHacker first randomly fuses two point clouds of different classes in the spectral domain to craft their intermediate sample with high imperceptibility, then projects it onto the decision boundary via binary search. To restrict the final perturbation size, 3DHacker further introduces an iterative optimization strategy to move the intermediate sample along the decision boundary for generating adversarial point clouds with smallest trivial perturbations. Extensive evaluations show that, even in the challenging hard-label setting, 3DHacker still competitively outperforms existing 3D attacks regarding the attack performance as well as adversary quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on Retentive Network

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on ...

引用

Computer Information science and Application Technology (CISAT), International Conference on

作者： Ruilin Su Wanshan Zhang Dunhui Yu Hubei University Wuhan China Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model’s memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model’s own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing.

关键词： Training Knowledge engineering Accuracy Spread spectrum communication Knowledge graphs Transformers Sampling methods Cognition Natural language processing Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Joint Scheduling and Beamforming Design in Traffic-Aware RIS Aided MEC Network

Joint Scheduling and Beamforming Design in Traffic-Aware RIS...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Li, Aichen Liu, Yang Wu, Qingqing Shi, Qingjiang Zhao, Jun Dalian University of Technology School of Information and Communication Engineering China University of Macau Department of Electrical and Computer Engineering China Tongji Univ. Shanghai Shenzhen Research Institute of Big Data School of Software Eng. Shenzhen China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9781665459754

This paper considers exploiting reconfigurable intelligent surface (RIS) in a multi-user multi-access mobile computing (MEC) system. To precisely model the traffic behaviors of the tasks, we consider queuing procedures at both mobile users and the cloud server. This consideration leads to concatenation of queues and makes our problem much more difficult than existing literature since analytic expression of the objective is impossible. Our goal is to jointly optimize the task scheduling, RIS configuration and computation resource allocation to improve the MEC network's overall computation rate in the long run while maintaining the stability of the queues. To tackle this highly challenging stochastic problem, we develop a Lyapunov guided deep reinforcement learning (DRL) solution, which borrows the Lyapunov optimization theory to stabilize queues and at the same time can effectively optimize the intractable objective in an online manner. Numerical results will be presented to verify the effectiveness of our solution and the performance boost due to the deployment of RIS. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Visual Analysis Motivated Super-Resolution Model for Image Reconstruction

Visual Analysis Motivated Super-Resolution Model for Image R...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Huifen Wang Junda Xue Mingchuan Yang Yuan Zhang College of Big Data and Artificial Intelligence China Telecom Research Institute Shanghai China College of Big Data and Artificial Intelligence China Telecom Research Institute Beijing China College of Information Science and Electronic Engineering Zhejiang University College of Big Data and Artificial Intelligence China Telecom Research Institute Hangzhou China

ISBN: (纸本)9781665475938

This paper presents a concise end-to-end visual analysis motivated super-resolution model VASR for image reconstruction. Compatible with the existing machine vision feature coding framework, the features extracted from the machine vision task model are super-resolution amplified to reconstruct the original image for human vision. The experimental results show that without additional bit-streams, VASR can well complete the task of image reconstruction based on the extracted machine features, and has achieved good results on COCO, OpenImages, TVD, and DIV2K datasets.

关键词： Training Visualization Analytical models Image coding Visual communication Machine vision Superresolution

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

How graph neural networks learn: lessons from training dynamics 24

How graph neural networks learn: lessons from training dynam...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Chenxiao Yang Qitian Wu David Wipf Ruoyu Sun Junchi Yan School of Artificial Intelligence & Department of Computer Science and Engineering & MoE Lab of AI Shanghai Jiao Tong University Amazon Web Services School of Data Science The Chinese University of Hong Kong Shenzhen and Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Phenotype Captioning Via Zero-Shot Learning with Semantic Correction Based on Llm

SSRN

引用

SSRN 2025年

作者： Xie, Yushan Dong, Xinyu Zhao, Kejun Sirishantha, G.M.A.D. Xiao, Yuanyuan Yu, Peijia Zhai, Changyuan Wang, Qi State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University China Postgraduate Institute of Agriculture University of Peradeniya University of Peradeniya Peradeniya Sri Lanka Intelligent Equipment Research Center Beijing Academy of Agriculture and Forestry Sciences China

Agriculture is the foundation of global food security and quality of life, with staple crops such as rice, wheat, and maize meeting the dietary needs of the majority of the world's population. These crops are vulnerable to diseases that can cause severe yield losses;for instance, wheat rust disease results in annual losses exceeding \$2.9 billion. Accurate caption of the phenotypic characteristics of plant diseases play a crucial supportive role in diagnosis, which is essential to ensure food security. Existing methods in agriculture fail to adequately address the heterogeneity in visual phenotypes and disease descriptions, resulting in insufficient focus on disease characteristics. To mitigate this issue, we propose a zero-shot image captioning framework, namely PDPC. PDPC uses an extensive descriptive corpus, syntactic analysis, and optimization of semantic structures to significantly improve the quality and generalization of disease descriptions. Additionally, we have constructed a dataset comprising 20,943 image captions of plant disease characteristics for over 60 plant species and 300 diseases. Experimental results demonstrate that the PDPC framework outperforms existing models in accurately describing the characteristics of plant disease. The introduction of this innovative framework not only improves the accuracy of disease descriptions but also provides robust support for the intelligent diagnosis and management of plant diseases, paving the way for improved plant health and increased agricultural yields. Please click the following link to learn more about my paper: http://***/ © 2025, 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

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching for Speaker Diarization

Flow-TSVAD: Target-Speaker Voice Activity Detection via Late...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhengyang Chen Bing Han Shuai Wang Yidi Jiang Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker diarization is typically considered as a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore for the first time the use of neural network-based generative methods for speaker diarization. We implement a Flow-Matching (FM) based generative algorithm within the sequenceto-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm, and our proposed Flow-TSVAD method can significantly outperform the traditional Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, only requiring two inference steps to achieve promising results. Moreover, as a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times, so the ensemble system combining the results from various sampling instances can further boost the diarization performance.

关键词： Voice activity detection Frequency modulation Computational modeling Signal processing algorithms Signal processing Inference algorithms Acoustics Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Di-Net: Decomposed Implicit Garment Transfer Network for Digital Clothed 3d Human

SSRN

引用

SSRN 2024年

作者： Zhong, Xiaojing Su, Yukun Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China Tencent Wechat Department China SenseTime Research

3D virtual try-on tasks aim to generate realistic try-on results for full- body garments, allowing them to be observed from arbitrary perspectives. Recent methods often represent the 3D human form with a fixed topol- ogy, limiting garment representation and leading to higher computational demands. Furthermore, the challenge of flexible transfer over various body parts remains. To address these problems, we introduce DI-Net(Decomposed Implicit Garment Transfer Network), where garment transfer is decomposed into 2D image layout transfer and 3D texture layout transfer. We propose a complementary warping module that leverages dense correspondence learn- ing and sparse flow learning to align the body appearance and garments with the target pose for image layout transfer. Subsequently, the transferred garments are lifted to the 3D human mesh by constructing a pixel-aligned implicit function and predicting the texture based on geometric priors. By applying different semantic masks for garment transfer, we efficiently control the texture of the generated mesh. Experimental results show the effective- ness and superiority of our method in the 3D virtual try-on task. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Global, regional, and national burden of HIV-negative tuberculosis, 1990-2021: findings from the Global Burden of Disease Study 2021

引用

Infectious Diseases of Poverty 2024年第4期13卷 101-102页

作者： Shun-Xian Zhang Feng-Yu Miao Jian Yang Wen-Ting Zhou Shan Lv Fan-Na Wei Yu Wang Xiao-Jie Hu Ping Yin Pei-Yong Zheng Ming Yang Mei-TiWang Xin-Yu Feng Lei Duan Guo-Bing Yang Ji-Chun Wang Zhen-Hui Lu Longhua Hospital Shanghai University of Traditional Chinese Medicine Shanghai 200032 China National Institute of Parasitic Diseases at Chinese Center for Disease Control and Prevention (Chinese Center for Tropical Diseases Research) NHC Key Laboratory of Parasite and Vector Biology WHO Collaborating Centre for Tropical Diseases National Center for International Research On Tropical Diseases National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Shanghai 200025 China School of Global Health Chinese Center for Tropical Diseases Research-Shanghai Jiao Tong University School of Medicine Shanghai 200025 China Beijing Municipal Health Big Data and Policy Research Center Beijing Institute of Hospital Management Beijing 101100 China Department of Science and Technology Chinese Center for Disease Control and Prevention National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Beijing 102206 China National Health Commission (NHC) Key Laboratory of Biosafety National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Beijing 102206 China Shanghai Mental Health Center Shanghai Jiao Tong University School of Medicine Shanghai 200032 China Gansu Provincial Center for Disease Control and Prevention Lanzhou 730000 China

Background Tuberculosis(TB)is a major infectious disease with significant public health *** widespread transmission,prolonged treatment duration,notable side effects,and high mortality rate pose severe *** study examines the epidemiological characteristics of TB globally and across major regions,providing a scientific basis for enhancing TB prevention and control measures *** The ecological study used data from the Global Burden of Disease(GBD)Study *** assessed new incidence cases,deaths,disability-adjusted life years(DALYs),and trends in age-standardized incidence rates(ASIRs),mortality rates(ASMRs),and DALY rates for drug-susceptible tuberculosis(DS-TB),multidrug-resistant tuberculosis(MDR-TB),and extensively drug-resistant tuberculosis(XDR-TB)from 1990 to 2021.A Bayesian age-period-cohort model was applied to project ASIR and *** In 2021,the global ASIR for all HIV-negative TB was 103.00 per 100,000 population 95%uncertainty interval(UI):92.21,114.91 per 100,000 populationl,declining by 0.40%(95%UI:-0.43,-0.38%)compared to *** global ASMR was 13.96 per 100,000 population(95%UI:12.61,15.72 per 100,000 population),with a decline of 0.44%(95%UI:-0.61,-0.23%)since *** global age-standardized DALY rate for HIV-negative TB was 580.26 per 100,000 population(95%UI:522.37,649.82 per 100,000 population),showing a decrease of 0.65%(95%UI:-0.69,-0.57 per 100,000 population)from *** global ASIR of MDR-TB has not decreased since 2015,instead,it has shown a slow upward trend in recent *** ASIR of XDR-TB has exhibited significant increase in the past 30 *** projections indicate MDR-TB and XDR-TB are expected to see signifcant increases in both ASIR and ASMR from 2022 to 2035,highlighting the growing challenge of drug-resistant *** This study found that the ASIR of MDR-TB and XDR-TB has shown an upward trend in recent *** reduce the TB burden,it is essential to enhance health infrastru

关键词： Tuberculosis Epidemiology Global burden of disease Sociodemographic Index

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：