检索结果-内蒙古大学图书馆

Improved Lossless Data Hiding for JPEG Images Based on Histogram Modification

Computers, Materials & Continua 2018年第6期55卷 495-507页

作者： Yang Du Zhaoxia Yin Xinpeng Zhang Key Laboratory of Intelligent Computing&Signal Processing Ministry of EducationAnhui UniversityHefei230601P.R.China Department of Computer Science Purdue UniversityWest lafayette47906USA School of Communication and Information Engineering Shanghai UniversityShanghai 200072P.R.China

This paper proposes a lossless and high payload data hiding scheme for JPEG images by histogram *** most in JPEG bitstream consists of a sequence of VLCs(variable length codes)and the appended *** VLC has a corresponding RLV(run/length value)to record the AC/DC *** achieve lossless data hiding with high payload,we shift the histogram of VLCs and modify the DHT segment to embed *** we sort the histogram of VLCs in descending order,the filesize expansion is *** paper’s key contribution includes:Lossless data hiding,less filesize expansion in identical pay-load and higher embedding efficiency.

关键词： Lossless data hiding histogram VLC JPEG.

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptive Fusion Network for High Performance RGBT Tracking

Deep Adaptive Fusion Network for High Performance RGBT Track...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Yuan Gao Chenglong Li Yabin Zhu Jin Tang Tao He Futian Wang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei China Anhui COWAROBOT CO. Ltd Wuhu China

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Due to the complementarity of RGB and thermal data, RGBT tracking has received more and more attention in recent years because it can effectively solve the degradation of tracking performance in dark environments and bad weather conditions. How to effectively fuse the information from RGB and thermal modality is the key to give full play to their complementarities for effective RGBT tracking. In this paper, we propose a high performance RGBT tracking framework based on a novel deep adaptive fusion network, named DAFNet. Our DAFNet consists of a recursive fusion chain that could adaptively integrate all layer features in an end-to-end manner. Due to simple yet effective operations in DAFNet, our tracker is able to reach the near-real-time speed. Comparing with the state-of-the-art trackers on two public datasets, our DAFNet tracker achieves the outstanding performance and yields a new state-of-the-art in RGBT tracking.

关键词： Feature extraction Target tracking Robustness Fuses Convolution Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Wide-band EM Scattering from Multiple Dielectric targets above a Dielectric Rough Sea Surface Based on Maehly Approximation 7

Wide-band EM Scattering from Multiple Dielectric targets abo...

引用

2017 7th IEEE International Symposium on Microwave, Antenna, Propagation, and EMC Technologies

作者： Ran Bao An Qi Wang Zhi Xiang Huang Key Laboratory of intelligent Computing & Signal Processing Anhui University

ISBN: (纸本)9781509059300;9781509059294

In this paper an efficient method is proposed to simulate the wide-band electromagnetic(EM)scattering from multiple dielectric targets above a dielectric PM rough sea surface,which is based on Chebyshev series and Maehly *** with the traditional frequency domain algorithms,such as method of moments(MoM),the proposed algorithm is efficiently in reducing the computational *** results show that the Maehly approximation and the repeatedly simulations obtained by the MoM have achieved an excellent agreement both in horizontal and vertical polarization.

关键词： Maehly approximation method of moments PM rough sea surface

来源：评论

学校读者我要写书评

暂无评论

Pose-adaptive hierarchical attention network for facial expression recognition

arXiv

引用

arXiv 2019年

作者： Liu, Yuanyuan Peng, Jiyao Zeng, Jiabei Shan, Shiguang School of Geography and Information Engineering China University of Geosciences Wuhan430074 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Center for Excellence in Brain Science and Intelligence Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Multi-view facial expression recognition (FER) is a challenging task because the appearance of an expression varies in poses. To alleviate the influences of poses, recent methods either perform pose normalization or learn separate FER classifiers for each pose. However, these methods usually have two stages and rely on good performance of pose estimators. Different from existing methods, we propose a pose-adaptive hierarchical attention network (PhaNet) that can jointly recognize the facial expressions and poses in unconstrained environment. Specifically, PhaNet discovers the most relevant regions to the facial expression by an attention mechanism in hierarchical scales, and the most informative scales are then selected to learn the poseinvariant and expression-discriminative representations. PhaNet is end-to-end trainable by minimizing the hierarchical attention losses, the FER loss and pose loss with dynamically learned loss weights. We validate the effectiveness of the proposed PhaNet on three multi-view datasets (BU-3DFE, Multi-pie, and KDEF) and two in-the-wild FER datasets (AffectNet and SFEW). Extensive experiments demonstrate that our framework outperforms the state-of-the-arts under both within-dataset and cross-dataset settings, achieving the average accuracies of 84.92%, 93.53%, 88.5%, 54.82% and 31.25% respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Fast Simulations of Electromagnetic Scattering from 1-D Rough Surface through Adaptively Modified Characteristic Basis Function Method 7

Fast Simulations of Electromagnetic Scattering from 1-D Roug...

引用

2017 7th IEEE International Symposium on Microwave, Antenna, Propagation, and EMC Technologies

作者： Jing Jing Wang An Qi Wang Zhi Xiang Huang Key Laboratory of intelligent Computing & Signal Processing Anhui University

ISBN: (纸本)9781509059300;9781509059294

In this paper,the Adaptively Modified Characteristic Basis Function Method(AMCBFM) is proposed to fast simulate the electromagnetic scattering from one-dimensional rough ***,the Primary Characteristic Basis Functions(PCBFs) arising from the self-interaction within the self-block are generated,and the coefficients of the basis function and the first current of each block are ***,the Secondary Characteristic Basis Functions(SCBFs) which account for the mutual coupling effects from the other distinct domains are obtained by using the *** higher SCBFs can be also derived through the same ***,a new precision method is applied to control the current error,which is used to determine the order of the higher order *** Comparing numerical simulations through the AMCBFM and the traditional Characteristic Basis Function Method(CBFM),the AMCBFM can guarantee the accuracy and void higher iteration,and the convergence performance is better than the CBFM in the lower order ***,by comparing numerical results of the AMCBFM and the method of moments(MoM),the AMCBFM can effectively reduce the size of the impedance matrix,and significantly reduce computing time.

关键词： Rough surface Electromagnetic scattering Adaptively Modified Characteristic Basis Function Method of moments

来源：评论

学校读者我要写书评

暂无评论

Refining HTN methods via task insertion with preferences (ArXiv version)

arXiv

引用

arXiv 2019年

作者： Xiao, Zhanhao Wan, Hai Zhuo, Hankui Hankz Herzig, Andreas Perrussel, Laurent Chen, Peilin School of Data and Computer Science Sun Yat-sen University Guangzhou China IRIT Toulouse France University of Toulouse Toulouse France Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Big Data Analysis and Processing China

Hierarchical Task Network (HTN) planning is showing its power in real-world planning. Although domain experts have partial hierarchical domain knowledge, it is time-consuming to specify all HTN methods, leaving them incomplete. On the other hand, traditional HTN learning approaches focus only on declarative goals, omitting the hierarchical domain knowledge. In this paper, we propose a novel learning framework to refine HTN methods via task insertion with completely preserving the original methods. As it is difficult to identify incomplete methods without designating declarative goals for compound tasks, we introduce the notion of prioritized preference to capture the incompleteness possibility of methods. Specifically, the framework first computes the preferred completion profile w.r.t. the prioritized preference to refine the incomplete methods. Then it finds the minimal set of refined methods via a method substitution operation. Experimental analysis demonstrates that our approach is effective, especially in solving new HTN planning instances. Copyright © 2019, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Agent Deep Reinforcement Learning Approach

引用

Journal of Physics: Conference Series 2021年第1期1757卷

作者： Dong Yin Zhe Zhao Yinglong Dai Han Long College of Intelligence Science and Technology National University of Defense Technology Changsha 410073 China College of Liberal Arts and Sciences National University of Defense Technology Changsha 410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha 410081 China

Borrowing the power of deep neural networks, deep reinforcement learning achieved big success in games, and it becomes a popular method to solve the sequential decision-making problems. However, the success is still restricted to single agent training environment. Multi-agent reinforcement learning still is a challenge problem. Although some multi-agent deep reinforcement learning methods have been proposed, they can only perform well when the number of agents is very limited. In this paper, by analyzing the dynamic changing observation space and action space of multi-agent environment, we propose a novel multi-agent deep RL method that compress the joint observation space and action space as the time goes on. The proposed method is potential for a large number of agents cooperative or competitive tasks

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Error Performance and Concatenated Coding of Polar Codes in AWGN Channels

引用

IOP Conference Series: Materials Science and Engineering 2020年第7期768卷

作者： Jing Jin Rui Deng Tiansheng Liu Liping Li Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education) Anhui University Hefei China Department of Electronic Engineering and Information Science University of Science and Technology Hefei China

In additive white Gaussian noise (AWGN) channels, construction of polar codes is needed for every operating signal-to-noise ratio (SNR). Recently, the proposal of the design-SNR reduces the computation effort in constructing polar codes. In this paper, we prove that although the BER performance of the design-SNR construction is not affected, the packet-error-rate (PER) performance is degraded compared with the point-by-point construction. Therefore, a concatenation scheme is proposed to improve the degraded PER performance. Results show the validity of the proposed concatenation scheme when employing the design-SNR construction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Corrections to "Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning"

引用

IEEE transactions on neural networks and learning systems 2021年第8期32卷 3784页

作者： Nan Lai Meina Kan Chunrui Han Xingguang Song Shiguang Shan Key Laboratory of Intelligent Information Processing Institute of Computing Technology (ICT) Chinese Academy of Sciences (CAS) Beijing China University of Chinese Academy of Sciences Beijing China Huawei Technologies Company Ltd. Shenzhen China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai China

In the above article [1], the results of "Fully-supervised (Upper bound)" in Tables III and IV were inadvertently set to intermediate records that were used as placeholders. This error has no effect on any of the interpretations and conclusions. Tables I and II of this amendment show the corrected results (highlighted in italics) of the original Tables III and IV.

关键词： Predictive models Feature extraction Deep learning Learning systems Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Control of Fractional-Order Delayed Memristive Chaotic System with Uncertainty and Disturbance

引用

Communications in Theoretical Physics 2017年第12期67卷 741-748页

作者：丁大为刘芳芳陈辉王年梁栋 Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University School of Electronics and Information Engineering Anhui University

In this paper, a simplest fractional-order delayed memristive chaotic system is proposed in order to control the chaos behaviors via sliding mode control strategy. Firstly, we design a sliding mode control strategy for the fractionalorder system with time delay to make the states of the system asymptotically stable. Then, we obtain theoretical analysis results of the control method using Lyapunov stability theorem which guarantees the asymptotic stability of the noncommensurate order and commensurate order system with and without uncertainty and an external disturbance. Finally,numerical simulations are given to verify that the proposed sliding mode control method can eliminate chaos and stabilize the fractional-order delayed memristive system in a finite time.

关键词： fractional-order system memristive system time delay sliding mode control stability theorem

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：