检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Ding Jiang Mang Ye National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

arXiv

引用

arXiv 2023年

作者： Jiang, Ding Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Dear-DIA^(XMBD): Deep Autoencoder Enables Deconvolution of Data-Independent Acquisition Proteomics

引用

research 2024年第1期6卷 707-720页

作者： Qingzu He Chuan-Qi Zhong Xiang Li Huan Guo Yiming Li Mingxuan Gao Rongshan Yu Xianming Liu Fangfei Zhang Donghui Guo Fangfu Ye Tiannan Guo Jianwei Shuai Jiahuai Han Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China Oujiang Laboratory(Zhejiang Lab for Regenerative Medicine Vision and Brain Health)and Wenzhou InstituteUniversity of Chinese Academy of SciencesWenzhouZhejiang 325001China School of Life Sciences Xiamen UniversityXiamen 361102China State Key Laboratory of Cellular Stress Biology Innovation Center for Cell Signaling NetworkXiamen 361102China Department of Computer Science Xiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine School of MedicineXiamen UniversityXiamen 361102China Bruker(Beijing)Scientific Technology Co.Ltd. BeijingChina Westlake Laboratory of Life Sciences and Biomedicine Key Laboratory of Structural Biology of Zhejiang ProvinceSchool of Life SciencesWestlake University18 Shilongshan RoadHangzhou 310024China Institute of Basic Medical Sciences Westlake Institute for Advanced Study18 Shilongshan RoadHangzhou 310024China Westlake Omics Ltd. Yunmeng Road 1HangzhouChina Department of Electronic Engineering Xiamen UniversityXiamen 361005China

Data-independent acquisition(DIA)technology for protein identification from mass spectrometry and related algorithms is developing *** spectrum-centric analysis of DIA data without the use of spectra library from data-dependent acquisition data represents a promising *** this paper,we proposed an untargeted analysis method,Dear-DIA^(XMBD),for direct analysis of DIA ***-DIA^(XMBD) first integrates the deep variational autoencoder and triplet loss to learn the representations of the extracted fragment ion chromatograms,then uses the k-means clustering algorithm to aggregate fragments with similar representations into the same classes,and finally establishes the inverted index tables to determine the precursors of fragment clusters between precursors and peptides and between fragments and *** show that Dear-DIA^(XMBD) performs superiorly with the highly complicated DIA data of different species obtained by different instrument platforms.

关键词： Deep Auto Independent

来源：评论

学校读者我要写书评

暂无评论

Look from Coarse to Fine: A Hierarchical Lane Detection network

Look from Coarse to Fine: A Hierarchical Lane Detection Netw...

引用

Artificial Intelligence Innovation (ICAII), International Conference on

作者： Xichen Yu Yanduo Zhang Tao Lu Xun Li Jun Chang Hubei Provincial Key Laboratory of Intelligent Robot School of Computer Science and Engineering & School of Artificial Intelligence Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and School of Computer Science Wuhan University Wuhan China

Lane detection involves identifying a high-level semantic identifier with a slender structure, which requires both high-level feature detection for existence and low-level features for shape and position determination. The objective of this study is to introduce a framework called hierarchical lane detection (HLDNet), which from coarse to fine established stronger relationships between the global and local lanes to achieve stable and accurate lane detection. Specifically, we reframe the existing lane identification method by expressing lanes as a combination of lane instances (for existence detection) and lane point sets (for shape detection). Our proposed Lane IoU loss improves the model performance by regressing the lane instance as a whole. To enhance stability, we capture the complete lane with high-level features using multiple receptive fields. Additionally, our model adaptively fuses high- and low-level features, propagates key features between channels, and further enhances lane local feature representation. Our experimental results show significant improvements in the stability and accuracy of lane detection across multiple benchmark datasets and can run in realtime at a speed of 91 FPS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Noisy Segment Learning for Fatigue Detection

SSRN

引用

SSRN 2024年

作者： Wang, Mei Hu, Ruimin Liao, Liang Wang, Xiaochen Chen, Xiaohe Hu, Jinzhang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China The Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China The School of Computer Science and Engineering Nanyang Technological University Singapore The Wuhan Research Institute of Posts and Telecommunications Wuhan430072 China

In fatigue detection, fine-grained labels (seconds-based) commonly inherit coarse-grained labels (minutes-based or more). However, due to the dynamic and time-varying nature of fatigue states, ``Noisy Segments'' often arise in Fine-Grained Fatigue Detection (FD-FGNS). To address this, we propose an Adaptive Fine-Grained Noisy segment learning (AFGN) method, which differs from traditional manual relabeling approaches. AFGN consists of an unsupervised Trustworthy sample Extraction (uTE) method and a Dynamic Noise-tolerant Selective-supervised Contrastive Learning (DNSCL) module. uTE extracts trustworthy samples for positive guidance learning, while DNSCL effectively enhances the model’s tolerance to noise, ensuring robust latent representation learning. Furthermore, we introduce two re-annotated datasets with fine-grained labels, reDROZY and reRLDD. Empirical evidence demonstrates the superiority of AFGN over benchmark methods in mitigating noise in fatigue detection. This study, diving into the unexplored area of fine-grained fatigue detection with noisy labels, opens up new research and application prospects in this field. © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Token Contrast for Weakly-Supervised Semantic Segmentation

Token Contrast for Weakly-Supervised Semantic Segmentation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Lixiang Ru Heliang Zheng Yibing Zhan Bo Du Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China JD Explore Academy China

Weakly-Supervised Semantic Segmentation (WSSS) using image-level labels typically utilizes Class Activation Map (CAM) to generate the pseudo labels. Limited by the local structure perception of CNN, CAM usually cannot identify the integral object regions. Though the recent Vision Transformer (ViT) can remedy this flaw, we observe it also brings the over-smoothing issue, i.e., the final patch tokens incline to be uniform. In this work, we propose Token Contrast (ToCo) to address this issue and further explore the virtue of ViT for WSSS. Firstly, motivated by the observation that intermediate layers in ViT can still retain semantic diversity, we designed a Patch Token Contrast module (PTC). PTC supervises the final patch tokens with the pseudo token relations derived from intermediate layers, allowing them to align the semantic regions and thus yield more accurate CAM. Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics. CTC facilitates the representation consistency between uncertain local regions and global objects by contrasting their class tokens. Experiments on the PASCAL VOC and MS COCO datasets show the proposed ToCo can remarkably surpass other single-stage competitors and achieve comparable performance with state-of-the-art multi-stage methods. Code is available at https://***/rulixiang/ToCo.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image-Text Coupling network For Hyperspectral Image Classification

Hyperspectral Image-Text Coupling Network For Hyperspectral ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jiaqi Yang Bo Du State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan P. R. China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan P. R. China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Deep learning-based approaches have blossomed in the field of hyperspectral image (HSI) classification. However, most of the existing methods focus only on visual information and ignore textual clues. Textual properties can describe the shape, color, and size of ground objects with a wealth of information and are a great complement to visual features. Therefore, the HSI-Text (HSI-T) coupling network is proposed in this study. Specifically, a geocoder is first designed to encode the geospatial information of the image. Moreover, a textual transformer is introduced to extract the attributes of the language. On the basis of the above structures, an HSI-T coupling network is built to explicitly model visual-textual dependencies. Experimental results on benchmark HSI datasets can verify that the proposed approach can gain better classification accuracy and more fine-grained land cover maps.

关键词： Couplings Visualization Shape Image color analysis Land surface Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

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

作者： Yujun Zhang Yanqu Chen Jiakai Wang Jin Hu Renshuai Tao Xianglong Liu State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression.

关键词： Accuracy Target recognition Perturbation methods Noise Robustness Acoustics Speech processing Digital audio players Automatic speech recognition Resilience

来源：评论

学校读者我要写书评

暂无评论

Imperceptible and Reliable Adversarial Attack 1

引用

4th International Conference on Frontiers in Cyber Security, FCS 2021

作者： Zhang, Jiawei Wang, Jinwei Luo, Xiangyang Ma, Bin Xiong, Naixue School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhenzhou450001 China Shandong Provincial Key Laboratory of Computer Networks and Qilu University of Technology Jinan250353 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States

ISBN: (数字)9789811905230

ISBN: (纸本)9789811905223

Deep neural networks are vulnerable to adversarial examples, which can fool classifiers by adding small perturbations. Various adversarial attack methods have been proposed in the past several years, and most of them add the perturbation in a "sparse" or "global" way. Since the number of pixels perturbed by the "sparse" method and the perturbation intensity of each pixel added by the "global" method are both small, the adversarial property can be destroyed easily. Finally, it makes the adversarial attack and the adversarial training based on these samples unreliable. To address this issue, we present an "pixel-wise" method which is somewhere in between the "sparse" or "global" way. First, the perception of human eyes to the error of different image regions is different. Second, image processing methods have different effects on the different areas of the image. Based on these two considerations, we propose an imperceptible and reliable adversarial attack method, which projects the perturbation to the different areas differently. Extensive experiments demonstrate our method can preserve the attack ability while maintaining good view quality. More importantly, the proposed projection can be combined with existing attack methods to generate a stronger generation algorithm which improves the robustness of adversarial examples. Based on the proposed method, the reliability of adversarial attacks can be greatly improved. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Contributing Dimension Structure of Deep Feature for Coreset Selection

arXiv

引用

arXiv 2024年

作者： Wan, Zhijing Wang, Zhixiang Wang, Yuran Wang, Zheng Zhu, Hongyuan Satoh, Shinichi National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering China The University of Tokyo Japan National Institute of Informatics Japan A*STAR Singapore

Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a sample's representation in enhancing performance and the role of sample diversity in averting overfitting. Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm. They have capably tackled representation via distribution matching guided by the similarities of features, gradients, or other information between data. However, the results of effectively diverse sample selection are mired in sub-optimality. This is because the similarity metrics usually simply aggregate dimension similarities without acknowledging disparities among the dimensions that significantly contribute to the final similarity. As a result, they fall short of adequately capturing diversity. To address this, we propose a feature-based diversity constraint, compelling the chosen subset to exhibit maximum diversity. Our key lies in the introduction of a novel Contributing Dimension Structure (CDS) metric. Different from similarity metrics that measure the overall similarity of high-dimensional features, our CDS metric considers not only the reduction of redundancy in feature dimensions, but also the difference between dimensions that contribute significantly to the final similarity. We reveal that existing methods tend to favor samples with similar CDS, leading to a reduced variety of CDS types within the coreset and subsequently hindering model performance. In response, we enhance the performance of five classical selection methods by integrating the CDS constraint. Our experiments on three datasets demonstrate the general effectiveness of the proposed method in boosting existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep 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：