检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yulin Wu Ruimin Hu Xiaochen Wang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

In reality, audible and visible sound sources are closely aligned, and they can help humans locate sources exactly. To exploit the complementarity between audio and visual data in multi-speaker direction of arrival (DoA) estimation, we propose a novel network consisting of 3D convolution neural networks (3D-CNNs) and 2D-CNNs mixture networks with residual dense blocks. It has two main advantages: 1) both input audio and visual features are low-level signal representation: the real and imaginary parts of STFT coefficients for the audio feature and pixel coordinates for the visual feature, which can allow the network to learn to extract the most informative high-level features. 2) 3D-CNNs with the residual dense block are used for audio and visual feature mapping along the time and frequency axis. The following 2D-CNNs are to ensemble the high-level features along the DoA axis. Experimental results demonstrate promising SSL performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Person Re-identification with Stochastic Training Strategy

arXiv

引用

arXiv 2021年

作者： Liu, Tianyang Lin, Yutian Du, Bo The National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Unsupervised person re-identification (re-ID) has attracted increasing research interests because of its scalability and possibility for real-world applications. state-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning. This approach suffers two problems. First, the centroid generated by unsupervised learning may not be a perfect prototype. Forcing images to get closer to the centroid emphasizes the result of clustering, which could accumulate clustering errors during iterations. Second, previous instance memory based methods utilize features updated at different training iterations to represent one centroid, these features are inconsistent due to the change of encoder. To this end, we propose an unsupervised re-ID approach with a stochastic learning strategy. Specifically, we adopt a stochastic updated memory, where a random instance from a cluster is used to update the cluster-level memory for contrastive learning. In this way, the relationship between randomly selected pair of images are learned to avoid the training bias caused by unreliable pseudo labels. By picking a sole last seen sample to directly update each cluster center, the stochastic memory is also always up-to-date for classifying to keep the consistency. Besides, to relieve the issue of camera variance, a unified distance matrix is proposed during clustering, where the distance bias from different camera domains is reduced and the variances of identities are emphasized. Our proposed method outperforms the state-of-the-arts in all the common unsupervised and UDA re-ID tasks. The code will be available at https://***/lithium770/Unsupervised-Person-re-ID-with-Stochastic-Training-Strategy. Copyright © 2021, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A face super-resolution approach using shape semantic mode regularization

A face super-resolution approach using shape semantic mode r...

引用

IEEE International Conference on Image Processing

作者： Chengdong Lan Ruimin Hu Zhen Han Zhongyuan Wang National Engineering Research Center on Multimedia Software State Key Laboratory of Software Engineering Wuhan University Wuhan China National Engineering Research Center on Multimedia Software School of Computer Wuhan University Wuhan China National Engineering Research Center on Multimedia Software Wuhan University Wuhan China

In actual imaging environment, a variety of factors have an impact on the quality of images, which leads to pixel distortion and aliasing. The traditional face super-resolution algorithm only uses the difference of image pixel values as similarity criterion, which degrades similarity and identification of reconstructed facial images. Image semantic information with human understanding, especially structural information, is robust to the degraded pixel values. In this paper, we propose a face super-resolution approach using shape semantic model. This method describes the facial shape as a series of fiducial points on facial image. And shape semantic information of input image is obtained manually. Then a shape semantic regularization is added to the original objective function. The steepest descent method is used to obtain the unified coefficient. Experimental results demonstrate that the proposed method outperforms the traditional schemes significantly both in subjective and objective quality.

关键词： Shape Face Image resolution Semantics Surveillance Image reconstruction Pixel

来源：评论

学校读者我要写书评

暂无评论

SLSNet: Weakly-Supervised Skin Lesion Segmentation network with Self-attentions 20th

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network w...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Pei, Songwen Huang, Junjie School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai200062 China

ISBN: (纸本)9789819970247

computer-aided skin lesion segmentation with high precision is crucial to diagnose skin cancers in the early stage. However, the lack of pixel-level labels makes the skin lesion segmentation tasks challenging. To tackle this problem, a new weakly-supervised skin lesion segmentation network with self-attentions named SLSNet is proposed. SLSNet contains two modules and uses image-level labels as supervision information. One module named Intra-image Self-attention Seed Expansion (ISE) digs intra-image self-attentions with an expansion loss and a confidence loss to expand seed areas. The other module named Inter-image Affinity-based Noise Suppression (IAS) suppresses the noise pixels in attention maps via inter-image correlations. Extensive experiments conducted on ISIC-2017 dataset show that SLSNet achieves relatively high performance while reducing human labeling efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

Completion time-a ware flow scheduling in heterogenous networks 1

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： He, Shiming Xie, Kun Zhang, Dafang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Hunan Province Engineering Research Center of Electric Transportation and Smart Distributed Network Changsha University of Science and Technology Changsha410114 China College of Computer Science and Electronics Engineering Hunan University Changsha410082 China Department of Electrical and Computer Engineering State University of New York at Stony Brook NY United States

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

In China, the expressway isn’t free. When a vehicle exits, the exit toll station needs to calculate the toll according to the vehicle trajectory obtained by sending a trajectory query task to the trajectory center remotely. For the accurate of toll and keep the exit smoothly, transmitting the trajectory result reliably and in time is a key issue. There are three heterogenous networks in expressway, Fibernet, Telecommunications network and 3G. We concurrently exploit three heterogenous networks by allocating the trajectory result into three sub-flows where each sub-flow is transmitted in one kind of networks. But existing multipath transfer solution(FMTCP) doesn’t consider the difference of completed time among all sub-flows and can’t make sure the completed time in time. Therefore, we formulate the sub-flows schedule as a integer programming problem, which is proved to be NP-hard problem, and propose a Completion time-aware Flow Scheduling scheme (CaFS) which calculates the size of sub-flows. For the reliably, it exploits generation-based network coding. For the transmission in time, CaFS allocates the size of sub-flow into suitable generation and scheduling the generations. The simulation results demonstrate that, comparing with the FMTCP, CaFS improves 31. 9% in completion time and 30% in task finished rate. © Springer International Publishing Switzerland 2015.

关键词： network coding

来源：评论

学校读者我要写书评

暂无评论

UDT:U-shaped deformable transformer for subarachnoid haemorrhage image segmentation

引用

CAAI Transactions on Intelligence Technology 2024年第3期9卷 756-768页

作者： Wei Xie Lianghao Jin Shiqi Hua Hao Sun Bo Sun Zhigang Tu Jun Liu Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal UniversityWuhanChina School of Computer Science Central China Normal UniversityWuhanChina National Language Resources Monitoring and Research Center for Network Media Central China Normal UniversityWuhanChina The First Affiliated Hospital of Dalian Medical University DalianChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Information Systems Technology and Design Pillar Singapore University of Technology and DesignSingaporeSingapore

Subarachnoid haemorrhage(SAH),mostly caused by the rupture of intracranial aneu-rysm,is a common disease with a high fatality *** lesions are generally diffusely distributed,showing a variety of scales with irregular *** complex characteristics of lesions make SAH segmentation a challenging *** cope with these difficulties,a u-shaped deformable transformer(UDT)is proposed for SAH ***,first,a multi-scale deformable attention(MSDA)module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions,where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale ***,the cross deformable attention-based skip connection(CDASC)module is designed to model the irregular edge char-acteristic of SAH lesions,where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder ***,the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed *** experiments are conducted on the self-built SAH-CT dataset and two public medical datasets(GlaS and MoNuSeg).Experimental results show that the presented UDT achieves the state-of-the-art performance.

关键词： image segmentation medical image processing

来源：评论

学校读者我要写书评

暂无评论

A theoretical analysis of backdoor poisoning attacks in convolutional neural networks 24

A theoretical analysis of backdoor poisoning attacks in conv...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Boqi Li Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysis

arXiv

引用

arXiv 2024年

作者： Zhong, Qihuang Li, Haiyun Zhuang, Luyao Liu, Juhua Du, Bo School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Aspect-based Sentiment Analysis (ABSA) is an important sentiment analysis task, which aims to determine the sentiment polarity towards an aspect in a sentence. Due to the expensive and limited labeled data, data generation (DG) has become the standard for improving the performance of ABSA. However, current DG methods usually have some shortcomings: 1) poor fluency and coherence, 2) lack of diversity of generated data, and 3) reliance on some existing labeled data, hindering its applications in real-world scenarios. With the advancement of large language models (LLMs), LLM-based DG has the potential to solve the above issues. Unfortunately, directly prompting LLMs struggles to generate the desired pseudo-label ABSA data, as LLMs are prone to hallucinations, leading to undesired data generation. To this end, we propose a systematic Iterative Data Generation framework, namely IDG, to boost the performance of ABSA. The core of IDG is to make full use of the powerful abilities (i.e., instruction-following, in-context learning and self-reflection) of LLMs to iteratively generate more fluent and diverse pseudo-label data, starting from an unsupervised sentence corpus. Specifically, IDG designs a novel iterative data generation mechanism and a self-reflection data filtering module to tackle the challenges of unexpected data generation caused by hallucinations. Extensive experiments on four widely-used ABSA benchmarks show that IDG brings consistent and significant performance gains among five baseline ABSA models. More encouragingly, the synthetic data generated by IDG can achieve comparable or even better performance against the manually annotated data. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Generalized Zero-Shot Learning Based on Variational Information Bottleneck

Audio-Visual Generalized Zero-Shot Learning Based on Variati...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yapeng Li Yong Luo Bo Du School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Audio-visual generalized zero-shot learning (GZSL) aims to train a model on seen classes for classifying data samples from both seen classes and unseen classes. Due to the absence of unseen training samples, the model tends to misclassify unseen class samples into seen classes. To mitigate this problem, in this paper, we propose a method based on variational information bottleneck for audio-visual GZSL. Specifically, we model the joint representations as a product-of-experts over marginal representations to integrate the information of audio and visual. Besides, we introduce variational information bottleneck to the learning of audio-visual joint representations and marginal representations of audio, visual, and text label modalities. This helps our model reduce the negative impact of information that cannot be generalized to unseen classes. Experimental results conducted on the UCF-GZSL, VGGSound-GZSL, and ActivityNet-GZSL benchmarks demonstrate the effectiveness and superiority of the proposed model for audio-visual GZSL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequential Kernel Goodness-of-fit testing 24

Sequential Kernel Goodness-of-fit testing

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zhengyu Zhou Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Goodness-of-fit testing, a classical statistical tool, has been extensively explored in the batch setting, where the sample size is predetermined. However, practitioners often prefer methods that adapt to the complexity of a problem rather than fixing the sample size beforehand. Classical batch tests are generally unsuitable for streaming data, as valid inference after data peeking requires multiple testing corrections, resulting in reduced statistical power. To address this issue, we delve into the design of consistent sequential goodness-of-fit tests. Following the principle of testing by betting, we reframe this task as selecting a sequence of payoff functions that maximize the wealth of a fictitious bettor, betting against the null in a repeated game. We conduct experiments to demonstrate the adaptability of our sequential test across varying difficulty levels of problems while maintaining control over type-I errors.

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：