检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shang, Zirui Zhu, Yubo Li, Hongxi Yang, Shuo Wu, Xinxiao Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Video summarization aims to eliminate visual redundancy while retaining key parts of video to construct concise and comprehensive synopses. Most existing methods use discriminative models to predict the importance scores of video frames. However, these methods are susceptible to annotation inconsistency caused by the inherent subjectivity of different annotators when annotating the same video. In this paper, we introduce a generative framework for video summarization that learns how to generate summaries from a probability distribution perspective, effectively reducing the interference of subjective annotation noise. Specifically, we propose a novel diffusion summarization method based on the Denoising Diffusion Probabilistic Model (DDPM), which learns the probability distribution of training data through noise prediction, and generates summaries by iterative denoising. Our method is more resistant to subjective annotation noise, and is less prone to overfitting the training data than discriminative methods, with strong generalization ability. Moreover, to facilitate training DDPM with limited data, we employ an unsupervised video summarization model to implement the earlier denoising process. Extensive experiments on various datasets (TVSum, SumMe, and FPVSum) demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning

arXiv

引用

arXiv 2024年

作者： Yang, Shuo Shang, Zirui Wang, Yongqi Deng, Derong Chen, Hongwei Cheng, Qiyuan Wu, Xinxiao Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China

This paper proposes a novel framework for multi-label image recognition without any training data, called data-free framework, which uses knowledge of pre-trained Large Language Model (LLM) to learn prompts to adapt pre-trained Vision-Language Model (VLM) like CLIP to multi-label classification. Through asking LLM by well-designed questions, we acquire comprehensive knowledge about characteristics and contexts of objects, which provides valuable text descriptions for learning prompts. Then we propose a hierarchical prompt learning method by taking the multi-label dependency into consideration, wherein a subset of category-specific prompt tokens are shared when the corresponding objects exhibit similar attributes or are more likely to co-occur. Benefiting from the remarkable alignment between visual and linguistic semantics of CLIP, the hierarchical prompts learned from text descriptions are applied to perform classification of images during inference. Our framework presents a new way to explore the synergies between multiple pre-trained models for novel category recognition. Extensive experiments on three public datasets (MS-COCO, VOC2007, and NUS-WIDE) demonstrate that our method achieves better results than the state-of-the-art methods, especially outperforming the zero-shot multi-label recognition methods by 4.7% in mAP on MS-COCO. Copyright © 2024, 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

Residual Hyperbolic Graph Convolution Networks

arXiv

引用

arXiv 2024年

作者： Xue, Yangkai Dai, Jindou Lu, Zhipeng Wu, Yuwei Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Hyperbolic graph convolutional networks (HGCNs) have demonstrated representational capabilities of modeling hierarchical-structured graphs. However, as in general GCNs, over-smoothing may occur as the number of model layers increases, limiting the representation capabilities of most current HGCN models. In this paper, we propose residual hyperbolic graph convolutional networks (R-HGCNs) to address the over-smoothing problem. We introduce a hyperbolic residual connection function to overcome the over-smoothing problem, and also theoretically prove the effectiveness of the hyperbolic residual function. Moreover, we use product manifolds and HyperDrop to facilitate the R-HGCNs. The distinctive features of the R-HGCNs are as follows: (1) The hyperbolic residual connection preserves the initial node information in each layer and adds a hyperbolic identity mapping to prevent node features from being indistinguishable. (2) Product manifolds in R-HGCNs have been set up with different origin points in different components to facilitate the extraction of feature information from a wider range of perspectives, which enhances the representing capability of R-HGCNs. (3) HyperDrop adds multiplicative Gaussian noise into hyperbolic representations, such that perturbations can be added to alleviate the over-fitting problem without deconstructing the hyperbolic geometry. Experiment results demonstrate the effectiveness of R-HGCNs under various graph convolution layers and different structures of product manifolds. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Normative Prior Network for Anomaly Segmentation in Retinal OCT Images 2nd

Normative Prior Network for Anomaly Segmentation in Retinal ...

引用

2nd International Conference on Image, Vision and intelligent Systems, ICIVIS 2022

作者： Zhou, Xueying Dong, Jiwen Li, Xiaohui Han, Tianhao Hou, Qingtao Gao, Xizhan School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China Ji Nan Chao Feng Intelligent Technology Co. LTD. Jinan China

ISBN: (纸本)9789819909223

Anomaly segmentation refers to leveraging only normal images for model training to detect pixel-level anomalies in abnormal images in test phase, which gets rid of the reliance on expensive manual labels and is able to detect rare anomalies that are hard to collect in training dataset. However, previous works performing anomaly segmentation in retinal OCT images heavily relied on complex post-processing methods and cannot detect anomalies in an end-to-end manner. To overcome that, in this paper, a novel anomaly segmentation method is proposed to segment retinopathy based on normative prior network. Specifically, a segmentation network and a variational autoencoder is constructed to extract retinal regions and learn normative prior of normal retinal structure, respectively. In inference phase, the anomalous region can be directly segmented by low structural similarity between abnormal retinal structure and the normal one reconstructed by variational autoencoder. Extensive experiments are conducted to evaluate the performance of the proposed method and the experimental results show that it achieves the state-of-the-art (SOTA) performance for anomaly segmentation in retinal OCT images. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Residual Transformer for Hyperspectral Image Classification Using Limited Training Samples 5

Asymmetric Residual Transformer for Hyperspectral Image Clas...

引用

5th International Conference on Video, Signal and Image Processing, VSIP 2023

作者： Sun, Yaxiu Wang, Minhui Xiang, Jianhong Hao, Lihong Sun, Rui Wu, Yaruo College Of Information And Communication Engineering Harbin Engineering University Harbin150001 China National Key Laboratory Of Communication Anti-Jamming Technology College Of Information And Communication Engineering Harbin Engineering University Harbin150001 China Agile And Intelligent Computing Key Laboratory Chengdu610000 China

ISBN: (纸本)9798400709272

In recent years, the combination of convolutional neural network (CNN) and transformer has become a trend. CNN is good at capturing local information, while transformer is good at capturing global features of images. Hyperspectral images (HSI) have rich spatial feature information, and hundreds of continuous spectral bands contain a lot of deep sequence semantic information. Therefore, combining CNN and transformer can fully learn data feature information, which CNN can extract local spatial information, and transformer can extract band sequence information. In this paper, a new model ARFormer is proposed, which combines asymmetric residual connection (AR) block and improved vision transformer. First, the AR block contains the three-dimensional (3D) asymmetrical convolution and residual connection, which could extract abundant features information with fewer convolutional layers and parameters of model. Then the improved vision transformer introduces Re-attention, which could increase the diversity of the attention graph at different levels. Experiments in this paper are carried out on three famous hyperspectral datasets, including Indian Pines (IP), Trento (TR), and Pavia University (UP) datasets. The experimental results of HSI classification show that ARFormer achieves better classification accuracy than several existing models. Especially when the training samples are limited. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Quantification of valve stiction in control loops using adaptive differential evolution algorithm

Quantification of valve stiction in control loops using adap...

引用

2024 China Automation Congress, CAC 2024

作者： Yang, Dong Lang, Xun Wu, Jiande Yu, Wanke Liu, Songhua Xie, Lei Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Automation China University of Geosciences Wuhan China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350368604

Accurately and promptly quantifying stiction is crucial for valve maintenance in industrial settings and ensuring the stability of control loop performance. However, current Hammerstein-based stiction quantification methods overlook valve dynamics, potentially leading to inaccurate quantification. Therefore, this paper proposes a novel stiction quantification method based on an adaptive differential evolution algorithm. In addition to considering the impact of valve dynamics on stiction, the proposed method demonstrates a certain level of robustness against the interference of unknown noise. Finally, the effectiveness of the proposed method is demonstrated through a series of simulations and industrial case studies. © 2024 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

引用

2024 China Automation Congress, CAC 2024

作者： Lang, Yumin Wu, Jiande Lang, Xun Yu, Wanke Yang, Chuanyan Su, Hongye Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Automation China University of Geosciences Wuhan China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350368604

Oscillation is a significant indication of the deterioration of control system performance and needs to be carefully monitored to ensure safe and stable process operations. However, industrial processes are often prone to noisy artifacts and nonstationary trends, resulting in low signal-to-noise ratios. In order to tackle this problem, this study introduces a novel framework for enhanced trend removal and noise reduction, which is featured by the following steps:(i) The circulant singular spectrum analysis (CiSSA) is used to decompose oscillation data into several reconstructed components (RCs). (ii) The estimated power spectral density (PSD) ofthese RCs is then smoothed using the Savitzky-Golay filter (SGF) to eliminate noise and identify the RCs corresponding to oscillatory components. (iii) These identified RCs are subsequently reconstructed to produce purified oscillatory data. The effectiveness of the suggested approach is validated using simulations and real-world industrial case studies. The findings indicate that the method notably enhances the quality of oscillatory data. © 2024 IEEE.

关键词： Power spectral density

来源：评论

学校读者我要写书评

暂无评论

An evolutionary multiobjective method based on dominance and decomposition for feature selection in classification

引用

Science China(information Sciences) 2024年第2期67卷 5-19页

作者： Jing LIANG Yuyang ZHANG Ke CHEN Boyang QU Kunjie YU Caitong YUE Ponnuthurai Nagaratnam SUGANTHAN School of Electrical and Information Engineering Zhengzhou University State Key Laboratory of Intelligent Agricultural Power Equipment School of Electrical Engineering and Automation Henan Institute of Technology School of Electronics and Information Zhongyuan University of Technology KINDI Center for Computing Research College of EngineeringQatar University

Feature selection in classification can be considered a multiobjective problem with the objectives of increasing classification accuracy and decreasing the size of the selected feature subset. Dominance-based and decomposition-based multiobjective evolutionary algorithms(MOEAs) have been extensively used to address the feature selection problem due to their strong global search capability. However, most of them face the problem of not effectively balancing convergence and diversity during the evolutionary process. In addressing the aforementioned issue, this study proposes a unified evolutionary framework that combines two search forms of dominance and decomposition. The advantages of the two search methods assist one another in escaping the local optimum and inclining toward a balance of convergence and diversity. Specifically, an improved environmental selection strategy based on the distributions of individuals in the objective space is presented to avoid duplicate feature subsets. Furthermore, a novel knowledge transfer mechanism that considers evolutionary characteristics is developed, allowing for the effective implementation of positive knowledge transfer between dominance-based and decomposition-based feature selection methods. The experimental results demonstrate that the proposed algorithm can evolve feature subsets with good convergence and diversity in a shorter time compared with 9 state-of-the-art feature selection methods on 20 classification problems.

关键词： evolutionary algorithms feature selection multiobjective optimization knowledge transfer classification

来源：评论

学校读者我要写书评

暂无评论

GAN-based Symmetric Embedding Costs Adjustment for Enhancing Image Steganographic Security 24

GAN-based Symmetric Embedding Costs Adjustment for Enhancing...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ye, Miaoxin Zhou, Saixing Luo, Weiqi Tan, Shunquan Huang, Jiwu Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-Sen University Guangzhou China Shenzhen Key Laboratory of Media Security College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen MSU-BIT University Shenzhen China

ISBN: (纸本)9798400706868

Designing embedding costs is pivotal in modern image steganography. Many studies have shown adjusting symmetric embedding costs to asymmetric ones can enhance steganographic security. However, most existing methods heavily depend on manually defined parameters or rules, limiting security performance improvements. To overcome this limitation, we introduce an advanced GAN-based framework that transitions symmetric costs to asymmetric ones without the need for the manual intervention seen in existing approaches, such as the detailed specification of cost modulation directions and magnitudes. In our framework, we firstly achieve symmetric costs for a cover image, which is randomly split into two sub-images, with part of the secret information embedded into one. Subsequently, we design a GAN model to adjust the embedding costs of the second sub-image to asymmetric, facilitating the secure embedding of the remaining secret information. To support our phased embedding approach, our GAN's discriminator incorporates two steganalyers with different tasks: distinguishing the generator's final output, i.e., the stego image, from both the input cover image and the partially embedded stego image, providing diverse guidance to the generator. In addition, we introduce a simple yet effective update strategy to ensure a stable training process. Comprehensive experiments demonstrate that our method significantly enhances security over existing symmetric steganography techniques, achieving state-of-the-art levels compared to other methods focused on embedding costs adjustments. Additionally, detailed ablation studies validate our approach's effectiveness. © 2024 ACM.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Learning Interaction Detection 24

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Lear...

引用

33rd ACM Web Conference, WWW 2024

作者： Ma, Haiping Yang, Yong Qin, Chuan Yu, Xiaoshan Yang, Shangshang Zhang, Xingyi Zhu, Hengshu Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin PBC School of Finance Tsinghua University Beijing China School of Artificial Intelligence Anhui University Anhui Hefei China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin Beijing China

ISBN: (纸本)9798400701719

Knowledge tracing (KT) is a crucial task in online learning, aimed at tracing and predicting each student's knowledge states throughout their learning process. Over the past decade, it has garnered widespread attention due to it provides the potential for more tailored and adaptive online learning experiences. Although most current KT methodologies emphasize optimizing network structures to enhance predictive accuracy for future student performance, they often neglect anomalous interactions in students' learning processes, which may arise from low data quality (i.e., inferior question quality) and abnormal student behaviors (i.e., guessing and mistakes). To this end, in this paper, we propose a novel framework, termed HD-KT, designed to enhance the robustness of existing KT methodologies with Hybrid learning interactions Denoising approach. Specifically, we introduce two detectors for anomalous learning interactions, namely knowledge state-guided anomaly detector and student profile-guided anomaly detector. In the first detection module, we design a sequential autoencoder to identify anomalous learning interactions by detecting atypical student knowledge states. In the second module, we incorporate an attention mechanism by modeling a student's long-term profile to capture irregular interactions. Extensive experiments on four real-world benchmark datasets have decisively shown our HD-KT markedly boosts the robustness of numerous prevailing KT models, consequently increasing the accuracy of future student performance predictions. Additionally, our case studies highlight the versatility of HD-KT in addressing diverse downstream tasks, such as exercise quality analysis and learning behavior-based student clustering. © 2024 ACM.

关键词： Students

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：