The generic Meanshift is susceptible to interference of background pixels with the target pixels in the kernel of the reference model, which compromises the tracking performance. In this paper, we enhance the target c...The generic Meanshift is susceptible to interference of background pixels with the target pixels in the kernel of the reference model, which compromises the tracking performance. In this paper, we enhance the target color feature by attenuating the background color within the kernel through enlarging the pixel weightings which map to the pixels on the target. This way, the background pixel interference is largely suppressed in the color histogram in the course of constructing the target reference model. In addition, the proposed method also reduces the number of Meanshift iterations, which speeds up the algorithmic convergence. The two tests validate the proposed approach with improved tracking robustness on real-world video sequences.展开更多
Inspired by human behaviors, a robot object tracking model is proposed on the basis of visual attention mechanism, which is fit for the theory of topological perception. The model integrates the image-driven, bottom-u...Inspired by human behaviors, a robot object tracking model is proposed on the basis of visual attention mechanism, which is fit for the theory of topological perception. The model integrates the image-driven, bottom-up attention and the object-driven, top-down attention, whereas the previous attention model has mostly focused on either the bottom-up or top-down attention. By the bottom-up component, the whole scene is segmented into the ground region and the salient regions. Guided by top-down strategy which is achieved by a topological graph, the object regions are separated from the salient regions. The salient regions except the object regions are the barrier regions. In order to estimate the model, a mobile robot platform is developed, on which some experiments are implemented. The experimental results indicate that processing an image with a resolution of 752 × 480 pixels takes less than 200 ms and the object regions are unabridged. The analysis obtained by comparing the proposed model with the existing model demonstrates that the proposed model has some advantages in robot object tracking in terms of speed and efficiency.展开更多
Creutzfeldt-Jakob disease (CJD) is a rare but fatal neurodegenerative prion disease. Classic CJD comprises a clinical triad of rapidly progressive dementia, myoclonus, and EEG abnormality. At initial presentation, thi...Creutzfeldt-Jakob disease (CJD) is a rare but fatal neurodegenerative prion disease. Classic CJD comprises a clinical triad of rapidly progressive dementia, myoclonus, and EEG abnormality. At initial presentation, this classic triad is present only in a minority of cases. Visual impairment is one of the predominant manifestations in the course of CJD, especially in Heidenhain variant phenotype. We reported a case presenting with progressive blurred vision, along with other neurological symptoms, who diagnosed as sporadic CJD with cortical blindness in China.展开更多
Compared with the traditional crypto- graphy, visual cryptography （VC） decrypts secret images referring to the characteristics of human vision, rather than the cryptography knowledge or complex computations. Further...Compared with the traditional crypto- graphy, visual cryptography （VC） decrypts secret images referring to the characteristics of human vision, rather than the cryptography knowledge or complex computations. Furthermore, seeing to the freeness of the secret key, the whole process of encryption as well as deeryption for the visual cryptography meets a fast dealing course. As to the security concern, it is able to guarantee that no one can have access to any clues about the content of a secret image from individual cover images. Thus, owing to the studies on this area, the target of light-weighted cryptography is reached. Now the visual cryptography has been developed from the meaningless shadows to the meaningful ones. Seeing to the highly developed technique, some advanced VC techniques are introduced in this survey, respectively.展开更多
红外小目标的检测一直是红外追踪系统的关键技术,针对现有红外小目标检测方法在复杂背景下易造成虚警、检测速度慢的不足,从人类视觉系统的角度出发,参考了多尺度局部能量因子检测方法(multiscale local contrast measure using a local...红外小目标的检测一直是红外追踪系统的关键技术,针对现有红外小目标检测方法在复杂背景下易造成虚警、检测速度慢的不足,从人类视觉系统的角度出发,参考了多尺度局部能量因子检测方法(multiscale local contrast measure using a local energy factor,MLCM-LEF),提出了一种基于双层局部能量因子的红外小目标检测方法.从局部能量差异与局部亮度差异两个角度进行目标检测,使用双层局部能量因子从能量角度描述小目标与背景的相异程度,同时采取加权亮度差因子从亮度角度对图像进行目标检测,通过二维高斯融合上述二者的处理结果,最终利用图像均值和标准差进行自适应阈值分割,提取红外小目标.经过公开数据集实验测试,该方法在抑制背景噪声、减低虚警概率的表现上比主流的检测方法有所提升,与MLCM-LEF算法相比,基于双层局部能量因子的方法将单帧检测时间降低至三分之一.展开更多
目的对国内外有关孕期体重管理干预内容的研究现状、热点及趋势进行可视化分析,为国内开展相关研究和临床实践提供参考。方法通过计算机检索2018年1月1日至2022年12月31日发表于万方数据知识服务平台、中国知网、Web of Science及PubMe...目的对国内外有关孕期体重管理干预内容的研究现状、热点及趋势进行可视化分析,为国内开展相关研究和临床实践提供参考。方法通过计算机检索2018年1月1日至2022年12月31日发表于万方数据知识服务平台、中国知网、Web of Science及PubMed数据库中与孕期体重管理有关的文献,通过文献计量分析软件CiteSpace 5.0对文献关键词进行可视化分析。结果共检索到中文文献815篇,英文文献554篇。关键词分析结果显示,国内外孕期体重管理研究对象重点聚焦于肥胖及妊娠期糖尿病孕妇人群,干预内容以孕期饮食营养和体力活动为核心,以线下专科门诊或移动医疗技术为平台,结合体重、孕前体质指数、血糖、血脂、运动量等指标进行评估监测,开展妊娠妇女孕期体重管理的相关研究。结论孕期体重管理已成为近年来国内外学者的研究热点。未来有必要进一步重视妊娠妇女的孕期体重管理工作,开展高质量的临床研究,制定国内孕期体重管理的本土化指南,推进助产机构孕期体重管理的规范开展。展开更多
为更好地利用单词词性包含的语义信息和伴随单词出现时的非自然语言上下文信息,提出动态调整语义的词性加权多模态情感分析(part of speech weighted multi-modal sentiment analysis model with dynamic semantics adjustment,PW-DS)模...为更好地利用单词词性包含的语义信息和伴随单词出现时的非自然语言上下文信息,提出动态调整语义的词性加权多模态情感分析(part of speech weighted multi-modal sentiment analysis model with dynamic semantics adjustment,PW-DS)模型.该模型以自然语言为主体,分别使用基于Transformer的双向编码器表示(bidirectional encoder representation from Transformers,BERT)模型、广义自回归预训练(generalized autoregressive pretraining for language understanding,XLNet)模型和一种鲁棒优化的BERT预训练(robustly optimized BERT pretraining approach,RoBERTa)模型为文本模态做词嵌入编码;创建动态调整语义模块将自然语言和非自然语言信息有效结合;设计词性加权模块,提取单词词性并赋权以优化情感判别.与张量融合网络和低秩多模态融合等当前先进模型的对比实验结果表明,PW-DS模型在公共数据集CMU-MOSI和CMU-MOSEI上的平均绝对误差分别达到了0.607和0.510,二分类准确率分别为89.02%和86.93%,优于对比模型.通过消融实验分析了不同模块对模型效果的影响,验证了模型的有效性.展开更多
基金Supported by the Program for Technology Innovation Team of Ningbo Government (No. 2011B81002)the Ningbo University Science Research Foundation (No.xkl11075)
文摘The generic Meanshift is susceptible to interference of background pixels with the target pixels in the kernel of the reference model, which compromises the tracking performance. In this paper, we enhance the target color feature by attenuating the background color within the kernel through enlarging the pixel weightings which map to the pixels on the target. This way, the background pixel interference is largely suppressed in the color histogram in the course of constructing the target reference model. In addition, the proposed method also reduces the number of Meanshift iterations, which speeds up the algorithmic convergence. The two tests validate the proposed approach with improved tracking robustness on real-world video sequences.
基金supported by National Basic Research Program of China (973 Program) (No. 2006CB300407)National Natural Science Foundation of China (No. 50775017)
文摘Inspired by human behaviors, a robot object tracking model is proposed on the basis of visual attention mechanism, which is fit for the theory of topological perception. The model integrates the image-driven, bottom-up attention and the object-driven, top-down attention, whereas the previous attention model has mostly focused on either the bottom-up or top-down attention. By the bottom-up component, the whole scene is segmented into the ground region and the salient regions. Guided by top-down strategy which is achieved by a topological graph, the object regions are separated from the salient regions. The salient regions except the object regions are the barrier regions. In order to estimate the model, a mobile robot platform is developed, on which some experiments are implemented. The experimental results indicate that processing an image with a resolution of 752 × 480 pixels takes less than 200 ms and the object regions are unabridged. The analysis obtained by comparing the proposed model with the existing model demonstrates that the proposed model has some advantages in robot object tracking in terms of speed and efficiency.
文摘Creutzfeldt-Jakob disease (CJD) is a rare but fatal neurodegenerative prion disease. Classic CJD comprises a clinical triad of rapidly progressive dementia, myoclonus, and EEG abnormality. At initial presentation, this classic triad is present only in a minority of cases. Visual impairment is one of the predominant manifestations in the course of CJD, especially in Heidenhain variant phenotype. We reported a case presenting with progressive blurred vision, along with other neurological symptoms, who diagnosed as sporadic CJD with cortical blindness in China.
基金supported by National Science Council under Grant No. NSC98-2218-E-035-001-MY3
文摘Compared with the traditional crypto- graphy, visual cryptography （VC） decrypts secret images referring to the characteristics of human vision, rather than the cryptography knowledge or complex computations. Furthermore, seeing to the freeness of the secret key, the whole process of encryption as well as deeryption for the visual cryptography meets a fast dealing course. As to the security concern, it is able to guarantee that no one can have access to any clues about the content of a secret image from individual cover images. Thus, owing to the studies on this area, the target of light-weighted cryptography is reached. Now the visual cryptography has been developed from the meaningless shadows to the meaningful ones. Seeing to the highly developed technique, some advanced VC techniques are introduced in this survey, respectively.
文摘红外小目标的检测一直是红外追踪系统的关键技术,针对现有红外小目标检测方法在复杂背景下易造成虚警、检测速度慢的不足,从人类视觉系统的角度出发,参考了多尺度局部能量因子检测方法(multiscale local contrast measure using a local energy factor,MLCM-LEF),提出了一种基于双层局部能量因子的红外小目标检测方法.从局部能量差异与局部亮度差异两个角度进行目标检测,使用双层局部能量因子从能量角度描述小目标与背景的相异程度,同时采取加权亮度差因子从亮度角度对图像进行目标检测,通过二维高斯融合上述二者的处理结果,最终利用图像均值和标准差进行自适应阈值分割,提取红外小目标.经过公开数据集实验测试,该方法在抑制背景噪声、减低虚警概率的表现上比主流的检测方法有所提升,与MLCM-LEF算法相比,基于双层局部能量因子的方法将单帧检测时间降低至三分之一.
文摘目的对国内外有关孕期体重管理干预内容的研究现状、热点及趋势进行可视化分析,为国内开展相关研究和临床实践提供参考。方法通过计算机检索2018年1月1日至2022年12月31日发表于万方数据知识服务平台、中国知网、Web of Science及PubMed数据库中与孕期体重管理有关的文献,通过文献计量分析软件CiteSpace 5.0对文献关键词进行可视化分析。结果共检索到中文文献815篇,英文文献554篇。关键词分析结果显示,国内外孕期体重管理研究对象重点聚焦于肥胖及妊娠期糖尿病孕妇人群,干预内容以孕期饮食营养和体力活动为核心,以线下专科门诊或移动医疗技术为平台,结合体重、孕前体质指数、血糖、血脂、运动量等指标进行评估监测,开展妊娠妇女孕期体重管理的相关研究。结论孕期体重管理已成为近年来国内外学者的研究热点。未来有必要进一步重视妊娠妇女的孕期体重管理工作,开展高质量的临床研究,制定国内孕期体重管理的本土化指南,推进助产机构孕期体重管理的规范开展。
文摘为更好地利用单词词性包含的语义信息和伴随单词出现时的非自然语言上下文信息,提出动态调整语义的词性加权多模态情感分析(part of speech weighted multi-modal sentiment analysis model with dynamic semantics adjustment,PW-DS)模型.该模型以自然语言为主体,分别使用基于Transformer的双向编码器表示(bidirectional encoder representation from Transformers,BERT)模型、广义自回归预训练(generalized autoregressive pretraining for language understanding,XLNet)模型和一种鲁棒优化的BERT预训练(robustly optimized BERT pretraining approach,RoBERTa)模型为文本模态做词嵌入编码;创建动态调整语义模块将自然语言和非自然语言信息有效结合;设计词性加权模块,提取单词词性并赋权以优化情感判别.与张量融合网络和低秩多模态融合等当前先进模型的对比实验结果表明,PW-DS模型在公共数据集CMU-MOSI和CMU-MOSEI上的平均绝对误差分别达到了0.607和0.510,二分类准确率分别为89.02%和86.93%,优于对比模型.通过消融实验分析了不同模块对模型效果的影响,验证了模型的有效性.
