Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding.However,these approaches have some limitations.For example,a cover image lacks s...Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding.However,these approaches have some limitations.For example,a cover image lacks self-adaptability,information leakage,or weak concealment.To address these issues,this study proposes a universal and adaptable image-hiding method.First,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image domain.Second,to improve perceived human similarity,perceptual loss is incorporated into the training process.The experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality output.Furthermore,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at 0.0001.Moreover,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.展开更多
Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly dist...Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.展开更多
Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to ach...Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.展开更多
U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentat...U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the materials.Three representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction accuracy.It is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure segregation.The reasons for the accuracy improvement were discussed based on the feature maps analysis.展开更多
With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significanc...With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significance and practical application value.Therefore,it is necessary to summarize the current research and provide some reference for researchers in this field.This article conducted a detailed and in-depth analysis and summarized of relevant research and typical methods of visual question answering field.First,relevant background knowledge about VQA(Visual Question Answering)was introduced.Secondly,the issues and challenges of visual question answering were discussed,and at the same time,some promising discussion on the particular methodologies was given.Thirdly,the key sub-problems affecting visual question answering were summarized and analyzed.Then,the current commonly used data sets and evaluation indicators were summarized.Next,in view of the popular algorithms and models in VQA research,comparison of the algorithms and models was summarized and listed.Finally,the future development trend and conclusion of visual question answering were prospected.展开更多
近年来,波段选择在高光谱图像降维处理中得到了广泛地应用,然而常用的数据降维方法并没能将与人类视觉系统相关的信息进行有效利用,如果将人类与生俱来的视觉注意机制能力应用到高光谱图像中目标的视觉显著性特征的增强或识别,对于高光...近年来,波段选择在高光谱图像降维处理中得到了广泛地应用,然而常用的数据降维方法并没能将与人类视觉系统相关的信息进行有效利用,如果将人类与生俱来的视觉注意机制能力应用到高光谱图像中目标的视觉显著性特征的增强或识别,对于高光谱图像的目标检测研究无疑会产生相当的促进作用。研究提出引入视觉注意机制理论应用于波段选择研究,构建面向目标检测应用的视觉注意机制波段选择模型。通过分析计算波段图幅的目标与背景的可识别程度,量化所在波段对地物目标与背景的判别能力,提出了基于目标视觉可识别度的波段选择方法;利用LC显著性算法进行空间域的视觉显著性目标分析,计算背景与目标的显著性差异绝对值,提出基于LC显著目标结构分布的波段选择方法。将这两种方法结合提出的改进子空间划分方法,建立面向目标检测的视觉注意机制波段选择模型,并经高光谱遥感AVIRIS San Diego公开数据集进行目标检测实验验证,结果表明所提出的基于视觉注意机制的波段选择模型对于目标检测应用具有较好的检测效果,实现了数据降维和高效的计算处理。展开更多
为了提高语音分离的效果,除了利用混合的语音信号,还可以借助视觉信号作为辅助信息。这种融合了视觉与音频信号的多模态建模方式,已被证实可以有效地提高语音分离的性能,为语音分离任务提供了新的可能性。为了更好地捕捉视觉与音频特征...为了提高语音分离的效果,除了利用混合的语音信号,还可以借助视觉信号作为辅助信息。这种融合了视觉与音频信号的多模态建模方式,已被证实可以有效地提高语音分离的性能,为语音分离任务提供了新的可能性。为了更好地捕捉视觉与音频特征中的长期依赖关系,并强化网络对输入上下文信息的理解,本文提出了一种基于一维扩张卷积与Transformer的时域视听融合语音分离模型。将基于频域的传统视听融合语音分离方法应用到时域中,避免了时频变换带来的信息损失和相位重构问题。所提网络架构包含四个模块:一个视觉特征提取网络,用于从视频帧中提取唇部嵌入特征;一个音频编码器,用于将混合语音转换为特征表示;一个多模态分离网络,主要由音频子网络、视频子网络,以及Transformer网络组成,用于利用视觉和音频特征进行语音分离;以及一个音频解码器,用于将分离后的特征还原为干净的语音。本文使用LRS2数据集生成的包含两个说话者混合语音的数据集。实验结果表明,所提出的网络在尺度不变信噪比改进(Scale-Invariant Signal-to-Noise Ratio Improvement,SISNRi)与信号失真比改进(Signal-to-Distortion Ratio Improvement,SDRi)这两种指标上分别达到14.0 dB与14.3 dB,较纯音频分离模型和普适的视听融合分离模型有明显的性能提升。展开更多
基金supported by the National Key R&D Program of China(Grant Number 2021YFB2700900)the National Natural Science Foundation of China(Grant Numbers 62172232,62172233)the Jiangsu Basic Research Program Natural Science Foundation(Grant Number BK20200039).
文摘Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding.However,these approaches have some limitations.For example,a cover image lacks self-adaptability,information leakage,or weak concealment.To address these issues,this study proposes a universal and adaptable image-hiding method.First,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image domain.Second,to improve perceived human similarity,perceptual loss is incorporated into the training process.The experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality output.Furthermore,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at 0.0001.Moreover,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.
基金Supported by Tianjin Municipal Natural Science Foundation of China(Grant No.19JCJQJC61600)Hebei Provincial Natural Science Foundation of China(Grant Nos.F2020202051,F2020202053).
文摘Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.
基金This work was supported by the Sichuan Science and Technology Program(2021YFQ0003).
文摘Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.
基金support from National Natural Science Foundation of China(Nos.52071238 and U20A20279)National Key Research and Development Program of China(2022YFB3706701)the 111 Project(No.D18018)。
文摘U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the materials.Three representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction accuracy.It is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure segregation.The reasons for the accuracy improvement were discussed based on the feature maps analysis.
基金Project(61702063)supported by the National Natural Science Foundation of China。
文摘With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significance and practical application value.Therefore,it is necessary to summarize the current research and provide some reference for researchers in this field.This article conducted a detailed and in-depth analysis and summarized of relevant research and typical methods of visual question answering field.First,relevant background knowledge about VQA(Visual Question Answering)was introduced.Secondly,the issues and challenges of visual question answering were discussed,and at the same time,some promising discussion on the particular methodologies was given.Thirdly,the key sub-problems affecting visual question answering were summarized and analyzed.Then,the current commonly used data sets and evaluation indicators were summarized.Next,in view of the popular algorithms and models in VQA research,comparison of the algorithms and models was summarized and listed.Finally,the future development trend and conclusion of visual question answering were prospected.
文摘近年来,波段选择在高光谱图像降维处理中得到了广泛地应用,然而常用的数据降维方法并没能将与人类视觉系统相关的信息进行有效利用,如果将人类与生俱来的视觉注意机制能力应用到高光谱图像中目标的视觉显著性特征的增强或识别,对于高光谱图像的目标检测研究无疑会产生相当的促进作用。研究提出引入视觉注意机制理论应用于波段选择研究,构建面向目标检测应用的视觉注意机制波段选择模型。通过分析计算波段图幅的目标与背景的可识别程度,量化所在波段对地物目标与背景的判别能力,提出了基于目标视觉可识别度的波段选择方法;利用LC显著性算法进行空间域的视觉显著性目标分析,计算背景与目标的显著性差异绝对值,提出基于LC显著目标结构分布的波段选择方法。将这两种方法结合提出的改进子空间划分方法,建立面向目标检测的视觉注意机制波段选择模型,并经高光谱遥感AVIRIS San Diego公开数据集进行目标检测实验验证,结果表明所提出的基于视觉注意机制的波段选择模型对于目标检测应用具有较好的检测效果,实现了数据降维和高效的计算处理。
文摘为了提高语音分离的效果,除了利用混合的语音信号,还可以借助视觉信号作为辅助信息。这种融合了视觉与音频信号的多模态建模方式,已被证实可以有效地提高语音分离的性能,为语音分离任务提供了新的可能性。为了更好地捕捉视觉与音频特征中的长期依赖关系,并强化网络对输入上下文信息的理解,本文提出了一种基于一维扩张卷积与Transformer的时域视听融合语音分离模型。将基于频域的传统视听融合语音分离方法应用到时域中,避免了时频变换带来的信息损失和相位重构问题。所提网络架构包含四个模块:一个视觉特征提取网络,用于从视频帧中提取唇部嵌入特征;一个音频编码器,用于将混合语音转换为特征表示;一个多模态分离网络,主要由音频子网络、视频子网络,以及Transformer网络组成,用于利用视觉和音频特征进行语音分离;以及一个音频解码器,用于将分离后的特征还原为干净的语音。本文使用LRS2数据集生成的包含两个说话者混合语音的数据集。实验结果表明,所提出的网络在尺度不变信噪比改进(Scale-Invariant Signal-to-Noise Ratio Improvement,SISNRi)与信号失真比改进(Signal-to-Distortion Ratio Improvement,SDRi)这两种指标上分别达到14.0 dB与14.3 dB,较纯音频分离模型和普适的视听融合分离模型有明显的性能提升。
