检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng Zheng Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China China Three Gorges University Yichang China

Many vision-related processing tasks, including edge detection and image segmentation, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One classical approach to recover an everywhere-in-focus image is to use Laplacian pyramid image fusion. First, several source images with different focuses of the same scene are taken and decomposed into the low/high-frequency components image sequences. Within these decompositions, the high-frequency components image sequences with the largest magnitude are selected at each pixel location. Finally, the fused image can be recovered from the decomposed components image sequences. In the support vector machine (SVM), the pixels with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. In this paper, we use Laplacian pyramid for the multi resolution decomposition, and then replace the traditional salient features by support values of the mapped least squares (LS)-SVM for fusing image. Experimental results illustrate that the proposed method outperforms the traditional approach.

关键词： Focusing image sequences Support vector machines Layout Laplace equations image edge detection image segmentation Optical sensors Lenses image fusion

来源：评论

学校读者我要写书评

暂无评论

A SUPPORT VALUE TRANSFORM-BASED MULTI FOCUS image FUSION METHOD

A SUPPORT VALUE TRANSFORM-BASED MULTI FOCUS IMAGE FUSION MET...

引用

2006 8th International Conference on Signal processing

作者： Sheng ZHENG Jian Liu Guangxi Zhu Jinwen Tian College of Electrical Engineering & Information Technology China Three Gorges University Electronic & Information Engineering Department Huazhong University of Science and Technology(HUST) State Edu Commission Key Lab for Image Processing & Intelligent Control HUST Chinese Key lab of optic & electronics HUST State Edu Commission Key Lab for Image Processing & Intelligent Control

＜正＞The image fusion is an important approach to produce a single complete image which preserves all relevant information from different *** this paper,we proposed a support value transform-based multi focus image fusion method,where the fused saliency features are represented by support values. Based on the mapped least squares support vector machine,the support value transform is developed as a multi-scale analysis *** fusing results on the multi focus images demonstrate that the proposed image fusion method is effective and efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation

引用

Science China(Information Sciences) 2024年第8期67卷 130-146页

作者： Yingjian LIU Jiang LI Xiaoping WANG Zhigang ZENG School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education Institute of Artificial Intelligence Huazhong University of Science and Technology

Emotion recognition in conversation(ERC) has attracted growing attention in recent years as a result of the advancement and implementation of human-computer interface technologies. In this paper,we propose an emotional inertia and contagion-driven dependency modeling approach(EmotionIC) for ERC tasks. Our EmotionIC consists of three main components, i.e., identity masked multi-head attention(IMMHA), dialogue-based gated recurrent unit(DiaGRU), and skip-chain conditional random field(SkipCRF).Compared to previous ERC models, EmotionIC can model a conversation more thoroughly at both the feature-extraction and classification levels. The proposed model attempts to integrate the advantages of attention-and recurrence-based methods at the feature-extraction level. Specifically, IMMHA is applied to capture identity-based global contextual dependencies, while Dia GRU is utilized to extract speaker-and temporal-aware local contextual information. At the classification level, SkipCRF can explicitly mine complex emotional flows from higher-order neighboring utterances in the conversation. Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark *** ablation studies confirm that our modules can effectively model emotional inertia and contagion.

关键词： emotion recognition in conversation emotional inertia and contagion multi-head attention gated recurrent unit conditional random field

来源：评论

学校读者我要写书评

暂无评论

control-oriented fault detection of solid oxide fuel cell system unknown input on fuel supply

Control-oriented fault detection of solid oxide fuel cell sy...

引用

作者： Wu, Xiao-long Xu, Yuan-wu Xue, Tao Shuai, Junchao Jiang, Jianhua Deng, Zhonghua Fu, Xiaowei Li, Xi School of Automation Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science & Technology Wuhan China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Wuhan Industrial Economic Development Research Center Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China

As the solid oxide fuel cell (SOFC) system work environment is a high-temperature environment for a long time, it is difficult to obtain the SOFC stack internal state change directly. When the fault occurs, it is difficult to determine where the fault occurs. Moreover, the existing literature ignores the impact of faults, which creates many problems for SOFC system control. Therefore, a state observer-based fault detection method, which is used to detect the input flow sensor fault and the fuel input fault, is proposed. Their advantage is that they do not need data processing. To realize the fault detection, the observer is used to track the changes of SOFC stack chamber temperature. To obtain the observer estimation parameter, an approach from the actual stack structure parameters is employed to approximate the observer parameters. The results show the proposed fault detect method can judge fuel input fault type quickly and shield the disturbances signals from the sensor effectively. The proposed method also can be used to other operating points or air input fault. © 2018 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Learning Second-Order Attentive Context for Efficient Correspondence Pruning

arXiv

引用

arXiv 2023年

作者： Ye, Xinyi Zhao, Weiyue Lu, Hao Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Correspondence pruning aims to search consistent correspondences (inliers) from a set of putative correspondences. It is challenging because of the disorganized spatial distribution of numerous outliers, especially when putative correspondences are largely dominated by outliers. It is more challenging to ensure effectiveness while maintaining efficiency. In this paper, we propose an effective and efficient method for correspondence pruning. Inspired by the success of attentive context in correspondence problems, we first extend the attentive context to the first-order attentive context and then introduce the idea of attention in attention (ANA) to model second-order attentive context for correspondence pruning. Compared with first-order attention that focuses on feature-consistent context, second-order attention dedicates to attention weights itself and provides an additional source to encode consistent context from the attention map. For efficiency, we derive two approximate formulations for the naive implementation of second-order attention to optimize the cubic complexity to linear complexity, such that second-order attention can be used with negligible computational overheads. We further implement our formulations in a second-order context layer and then incorporate the layer in an ANA block. Extensive experiments demonstrate that our method is effective and efficient in pruning outliers, especially in high-outlier-ratio cases. Compared with the state-of-the-art correspondence pruning approach LMCNet, our method runs 14 times faster while maintaining a competitive accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Echo state Networks Based Method for Harmonic Extraction in Shunt Active Power Filters

Echo State Networks Based Method for Harmonic Extraction in ...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Jinbang Xu Jun Yang Feng Liu Zhixiong Zhang Anwen Shen Department of Control Science & Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science & Technology Wuhan China

With the wide use of power conversion devices, harmonic currents are being injected into the power grid. Shunt Active Power Filters (SAPF) is a power electronic device to compensate the harmonic currents caused by nonlinear loads. As the foundation of the harmonics recognition and compensation, harmonic extraction techniques are becoming more and more important. This paper proposes a new harmonic extraction method based on the Echo state Networks (ESN). ESN is a new type of Recurrent Neural Networks (RNN), which has much faster training speed than other types of RNN. To evaluate the dynamic system modeling capability of the ESN, the ESN with different dynamic reservoir size are discussed. The performance of the ESN based harmonic extraction method is compared with traditional methods and method based on multilayer perceptron networks (MLP). The ESN algorithm is trained and tested in MATLAB.

关键词： Harmonic analysis Power harmonic filters Training Training data Reservoirs Neurons

来源：评论

学校读者我要写书评

暂无评论

Topic Embedded Representation Enhanced Variational Wasserstein Autoencoder for Text Modeling 5

Topic Embedded Representation Enhanced Variational Wasserste...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Xiang, Zheng Liu, Xiaoming Yang, Guan Liu, Yang Zhongyuan University of Technology School of Computer Science Zhengzhou China Henan Key Laboratory on Public Opinion Intelligent Analysis Zhengzhou China Key Laboratory of text processing and image understanding Zhengzhou China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Shandong University Key Lab of Cryptologic Technology and Information Security Ministry of Education Xi'an China

ISBN: (纸本)9781665485081

Variational Autoencoder (VAE) is now popular in modeling and language generation tasks, which need to pay attention to the diversity of generation results. The existing models are insufficient in capturing the built-in relationships between topic representation and sequential words. At the same time, there is a massive contradiction between the commonly used simple Gaussian prior and the actual complex distribution of languages. To address the above problems, we introduce a hybrid Wasserstein Autoencoder (WAE) with Topic Embedded Representation (TER) for modeling. TER is obtained through an embedding-based topic model and can capture the dependencies and semantic similarities between topics and words. In this case, the learned latent variable has rich semantic knowledge with the help of TER and is easier to explain and control. Our experiments show that our method is competitive with other VAEs in modeling. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generating Natural Language adversarial examples through an improved beam search algorithm

arXiv

引用

arXiv 2021年

作者： Zhao, Tengfei Ge, Zhaocheng Hu, Hanping Shi, Dingmeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education

The research of adversarial attacks in the text domain attracts many interests in the last few years, and many methods with a high attack success rate have been proposed. However, these attack methods are inefficient as they require lots of queries for the victim model when crafting text adversarial examples. In this paper, a novel attack model is proposed, its attack success rate surpasses the benchmark attack methods, but more importantly, its attack efficiency is much higher than the benchmark attack methods. The novel method is empirically evaluated by attacking WordCNN, LSTM, BiLSTM, and BERT on four benchmark datasets. For instance, it achieves a 100% attack success rate higher than the state-of-the-art method when attacking BERT and BiLSTM on IMDB, but the number of queries for the victim models only is 1/4 and 1/6.5 of the state-of-the-art method, respectively. Also, further experiments show the novel method has a good transferability on the generated adversarial examples. © 2021, CC BY.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Predictor-Based Active Anti-Disturbance control for Multi-Rate control Systems with Delayed Sampled-Data

Predictor-Based Active Anti-Disturbance Control for Multi-Ra...

引用

第40届中国控制会议

作者： Jiankun Sun Zhigang Zeng the School of Artificial Intelligence and Automation Huazhong University of Science and Technology the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China

In this paper, we consider the problem of sampleddata active anti-disturbance control design for multi-rate control system subject to delayed sampled-data output. The plant considered in this paper is equipped with a slow-rate sensor and a fastrate actuator. In the presence of non-vanishing disturbance, a new output predictor-based observer is first proposed by only using the delayed sampled-data output, so as to effectively estimate system state and disturbance in the inter-sample time interval.A new sampled-data controller that updates at a fast-rate is then designed with the help of active anti-disturbance *** to prediction and active anti-disturbance techniques, the proposed sampled-data control method can effectively reject the influence of non-vanishing disturbance despite slow-rate sampling and delay of sensor. Finally, the effectiveness of the proposed control method is demonstrated via simulation results of a practical example of the visual servoing control for an inertially stabilized platform.

关键词： Sample-data active anti-disturbance control output delay multi-rate control system

来源：评论

学校读者我要写书评

暂无评论

Efficient word-level sequential coding scheme of bit plane coding for EBCOT in JPEG2000

Efficient word-level sequential coding scheme of bit plane c...

引用

9th International Symposium on Consumer Electronics 2005, ISCE 2005

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian Institute of Pattern Recognition and Artificial Intelligence South-Center University for Nationalities Huazhong University of Science and Technology Wuhan China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China HUST

The embedded block coding with optimized truncation (EBCOT) is the state-of-the-art coding technique for image compression, which is the heart of the latest still image compression standard JPEG2000. EBCOT can be partitioned into three steps: bit plane coding (BPC), context adaptive binary arithmetic coding (CABAC) and postcompression rate-distortion (PCRD) optimization. The bit plane coding in JPEG2000 is a fractional bit-plane coding method, in which the transformed coefficients of a code block are coded bit plane by bit plane with 3 passes in each bit-plane, and context-decision (CX-D) pair of the coded symbol is generated for CABAC. In this paper, a new word-level sequential (WLS) coding scheme for BPC is presented, which makes all the passes coding be completed in one scan, with the context formation in all bit-planes being performed in parallel and all the samples being coded in sequential. The status variables used in context formation are produced on-the-fly. This new algorithm can efficiently implement both the regular mode and vertical causal one recommended by JPEG2000. The proposed algorithm reduces efficiently the size of memory and the amount of memory accessing, and increases significantly the speed of coding. It is well suited for both software and hardware implementation.1 © IEEE.

关键词： image coding

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：