基于混合运动激励和时序增强的篮球运动员动作识别算法

为了解决在背景相似的篮球视频中提取特征级运动信息不充分和捕获长时序依赖关系困难等问题,从局部和全局的角度出发,提出一种混合运动激励和时序增强网络(mixed motion excitation and temporal enhancement network,MTE-Net),该网络由在时间建模上互补的混合运动激励(mixed motion excitation,MME)模块和时序增强(temporal enhancement,TE)模块构成。混合运动激励模块通过计算短距离视频帧之间混合的特征级差分来充分表征局部运动信息,并显性地对运动敏感通道进行激励。时序增强模块对长距离视频帧使用自注意力机制来构建时序关联函数并捕获时序之间的全局依赖关系,增强视频中的重要帧序列。在不额外引入光流和过多参数的情况下,在SpaceJam篮球动作数据集上的实验结果表明,与其他主流的动作识别算法相比,所提模型对篮球运动员动作识别的准确率更高。     

治安监控视频中暴力行为的识别与检测

为了充分提取治安监控视频中的时空特征和时序特征,并对暴力行为进行准确的识别与检测,提出一种基于三维卷积神经网络(3DCNN)和卷积长短期记忆网络(Conv LSTM)的暴力行为识别算法。首先,采用一种通用视频描述符—3DCNN结构,提取视频的短时特征,这些特征封装了视频中与目标和场景相关的背景信息,然后,构建Conv LSTM网络对3DCNN提取的短时特征在时间轴上进行建模,进而充分提取视频的高层时序特征。最后,利用Sigmoid函数分类行为动作。为了验证该算法的高效性,对所提出的方法在暴力行为数据集Hockey上进行验证,达到了98.96%的识别精度。测试结果表明,该融合模型在检测效果上优于目前人工提取特征的方法和深度学习的方法。     

基于稀疏Transformer的长短时序关联动作识别算法

针对主流的视频动作识别算法对时序信息的挖掘不充分,而Transformer能够更好地处理长序列和全局依赖性问题,本文将3DCNN和Transformer结合起来,提出了基于稀疏Transformer的长短时序关联动作识别算法,从而实现对视频的全局时序信息进行建模。该算法提取预训练视频模型各个片段特征,嵌入视频特征聚类模块降低输入特征的潜在噪声,并利用基于稀疏自注意力的Transformer长短时序关联模块,引入稀疏掩码矩阵,对相似度矩阵进行掩码操作,抑制较小的注意力权重,选择性地保留重要的长短时序信息,提高模型对全局上下文信息的注意力集中程度。本文在UCF101和HMDB51数据集上进行了大量的实验,验证了本文算法的有效性,在参数量和计算复杂度较小的情况下准确率高于同类权威算法。     

基于融合注意力机制与CNN-LSTM的人体行为识别算法

为解决单一的卷积神经网络（CNN）缺乏利用时序信息与单一循环神经网络（RNN）对局部信息把握不全问题,提出了融合注意力机制与时空网络的深度学习模型（CLA-net）的人体行为识别方法。首先,通过CNN的强学习能力提取局部特征;其次,利用长短时记忆网络（LSTM）提取时序信息;再次,运用注意力机制获取并优化最重要的特征;最后使用softmax分类器对识别结果进行分类。仿真实验结果表明,CLA-net模型在UCI HAR和DaLiAc数据集上的准确率分别达到95.35%、99.43%,F1值分别达到95.35%、99.43%,均优于对比实验模型,有效提高了识别精度。     

基于C3D和视觉元素的视频描述

随着深度学习技术的发展,利用卷积神经网络(CNN)提取视频帧特征,再用循环神经网络(RNN)生成句子的方法被广泛用于视频描述任务中.然而,这种直接转换方式忽略了很多视频内在信息,如视频序列的时序信息、运动信息及丰富的视觉元素信息等.为此,文中提出了一种基于自适应帧循环填充法的多模态视频描述(AFCF-MVC)模型;采用自适应特征提取法提取含有丰富时空信息和运动信息的视频C3D特征,使得C3D特征包含了整个视频序列所有帧的信息,并将其作为神经网络的输入;针对不同视频的标注句子长度不同问题,提出了自适应帧循环填充法,即根据标注句子的长度自适应地控制输入特征的个数,在保证句子输入完整的前提下为神经网络提供尽可能多的特征输入,并起到重复学习的作用;为了充分利用视频丰富的视觉元素信息,通过视觉检测器检测出视频帧的视觉元素信息,编码后作为额外的补充信息融合进AFCF-MVC模型中.在M-VAD和MPII-MD数据集上的实验结果显示,该模型既能准确地描述视频中的内容,也能在语法结构上模拟出人类语言的丰富性.     

基于语言模型及循环卷积神经网络的事件检测

目前,事件检测的难点在于一词多义和多事件句的检测.为了解决这些问题,提出了一个新的基于语言模型的带注意力机制的循环卷积神经网络模型(recurrent and convolutional neural network with attention based on language models,LM-ARCNN).该模型利用语言模型计算输入句子的词向量,将句子的词向量输入长短期记忆网络获取句子级别的特征,并使用注意力机制捕获句子级别特征中与触发词相关性高的特征,最后将这两部分的特征输入到包含多个最大值池化层的卷积神经网络,提取更多上下文有效组块.在ACE2005英文语料库上进行实验,结果表明,该模型的F1值为74.4%,比现有最优的文本嵌入增强模型(DEEB)高0.4%.     

基于SAT-GCN的花样滑冰选手动作检测算法研究

针对花样滑冰运动人体运动轨迹复杂、动作类型多样、普通人肉眼难以区分且常规的行为识别方法识别准确率低的问题，提出了一种基于时空图卷积网络与多通道注意力机制融合方法 (SAT-GCN)的花样滑冰动作识别算法。该算法首先将视频提取成连续的单独帧，使用OpenPose算法提取人体骨骼关键点数据，降低背景噪声干扰；然后使用时空图卷积算法对骨骼关键点数据进行动作分类。算法对时空图卷积算法进行改进，加入了多通道时空注意力机制融合模块，使得模型更加关注重要的关键点、时间帧片段、特征；使用时序卷积网络(TCN)提取人体骨架关键点在时间序列上的特征；使用SoftMax对提取后的特征进行动作分类。在花样滑冰数据集FSD-10和公开的人类行为数据集Kinetics-Skeleton上进行训练和测试，与改进前的时空图卷积网络(ST-GCN)进行对比，本文所提算法的预测准确率在2个数据集上均有所提升，验证了多通道注意力机制融合方法在花样滑冰选手动作检测任务中的有效性。     

融合多尺度注意力和双向LSTM的行人重识别

将深度学习应用于行人重识别领域,嵌入多尺度注意力融合模块至神经网络中进行多尺度特征提取和表示,可有效提升注意力机制对深度学习网络的识别性能。提出了一种基于SE block的多尺度通道注意力融合模块,并结合ResNet50卷积神经网络提取特征;然后通过双向LSTM网络进一步提取特征序列上下文信息,在提高模型对图像重要特征的提取能力的同时,降低对图像冗余特征的关注度;最后使用级联难采样三元组损失函数和交叉熵损失函数共同训练网络模型,使样本能够在高维特征空间中实现聚类,进一步提升模型识别准确性。所提出算法在Market1501数据集和CUHK03数据集分别进行实验,并在同等条件下和其他注意力模块算法进行比较。为进一步验证各模块作用,对算法进行消融实验,以验证各模块的有效性,实验结果表明,所提出方法可有效应用于行人重识别     

结合注意力机制的Bi-LSTM维吾尔语事件时序关系识别

针对维吾尔语事件时序关系识别问题,提出了一种结合注意力机制的双向长短时记忆模型.基于维吾尔语语言及事件时序关系的特点,抽取13项基于事件间内部结构信息的特征.将词向量作为双向长短时记忆模型的输入,挖掘给定事件句隐含的上下文语义信息.结合事件触发词建立注意力机制,获取该事件句的事件语义特征.将事件内部结构特征和语义特征相融合,作为softmax层的输入,进而完成事件时序关系的识别.实验结果表明,该方法在获取事件句隐含语义信息的同时也能获取对应的事件语义特征.融合事件内部结构特征后,识别准确率为89.42%,召回率为86.70%,衡量模型整体性能的F值为88.03%,从而证明了该方法在维吾尔语事件时序关系识别任务上的有效性.     

多时间尺度双流CNN与置信融合的视频动作识别

考虑视频采样的变化和目标主体运动速度的不同,针对目前深度网络学习的视频序列特征单一、多种动作分类器分类置信程度不同的问题,提出了一种多时间尺度双流CNN与置信融合的视频动作识别方法.对视频序列采用两流神经网络在多个时间尺度上学习,提取不同时间跨度的视频帧之间的上下文信息特征,并采用LSTM进行多种特征的动作类别预测.然...     

Markedness and its Interpretation in Language Use

Language markedness is a common phenomenon in languages, and is reflected from hearing, vision and sense, i.e. the variation in the three aspects such as phonology, morphology and semantics. This paper focuses on the interpretation of markedness in language use following the three perspectives, i.e. pragmatic interpretation, psychological interpretation and cognitive interpretation, with an aim to define the function of markedness.     

Features of Women's language

Language is a means of verbal communication. People use language to communicate with each other. In the society, no two speakers are exactly alike in the way of speaking. Some differences are due to age, gender, statue and personality. Above all, gender is one of the obvious reasons. The writer of this paper tries to describe the features of women＇s language from these perspectives： pronunciation, intonation, diction, subjects, grammar and discourse. From the discussion of the features of women＇s language, more attention should be paid to language use in social context. What＇s more, the linguistic phenomena in a speaking community can be understood more thoroughly.     

低渗透非均质砂岩油藏启动压力梯度研究

理论推导与室内实验相结合,建立了低渗透非均质砂岩油藏启动压力梯度确定方法。首先借助油藏流场与电场相似的原理,推导了非均质砂岩油藏启动压力梯度计算公式。其次基于稳定流实验方法,建立了非均质砂岩油藏启动压力梯度测试方法。结果表明:低渗透非均质砂岩油藏的启动压力梯度确定遵循两个等效原则。平面非均质油藏的启动压力梯度等于各级渗透率段的启动压力梯度关于长度的加权平均;纵向非均质油藏的启动压力梯度等于各渗透率层的启动压力梯度关于渗透率与渗流面积乘积的加权平均。研究成果可用于有效指导低渗透非均质砂岩油藏的合理井距确定,促进该类油藏的高效开发。     

On Tragic Consciousness In The Works By Ernest Hemingway

As an American modern novelist who were famous in the literary world, Hemingway was not a person who always followed the trend but a sharp observer. At the same time, he was a tragedy maestro, he paid great attention on existence, fate and end-result. The dramatis personae's tragedy of his works was an extreme limit by all means tragedy on the meaning of fearless challenge that failed. The beauty of tragedy was not produced on the destruction of life, but now this kind of value was in the impact activity. They performed for the reader about the tragedy on challenging for the limit and the death.     

Achieving Unusual States of Matter Under High Pressure

正The periodicity of the elements and the non-reactivity of the inner-shell electrons are two related principles of chemistry,rooted in the atomic shell structure.Within compounds,Group I elements,for example,invariably assume the+1 oxidation state,and their chemical properties differ completely from those of the p-block elements.These general rules govern our understanding of chemical structures and reactions.Using first principles calcula-     

Exchange-Correlation and Electronic Excitation Energies from Pairing Matrix Fluctuations

We have developed an adiabatic connection to formulate the ground-state exchange-correlation energy in terms of pairing matrix linear fluctuations.This formulation of the exchange-correlation energy opens a new channel for density functional approximations based on the many-body perturbation theory.We illustrate the potential of such approaches with an approximation based on the particle-particle Random Phase Approximation(pp-RPA).This re-     

Density Functional Theory for the Response of Periodic Systems to Electric Fields Based on the Vector Potential Approach

正The electronic and nuclear(structural/vibrational)response of 1D-3D nanoscale systems to electric fields gives rise to a host of optical,mechanical,spectral,etc.properties that are of high theoretical and applied interest.Due to the computational difficulty of treating such large systems it is convenient to model them as infinite and periodic(at least,in first approximation).The fundamental theoretical/computational problem in doing so is that     

On the Thermodynamic Limit for Responses to Static Electromagnetic Fields

For molecular systems,the quantum-mechanical treatment of their responses to static electromagnetic fields usually employs a scalar-potential treatment of the electric field and a vector-potential treatment of the magnetic field.Although the potential for each field separately is associated with the choice of an(unphysical)origin,the precise choice of the origin for the electrostatic field has little consequences for the results.This is different for the     

An affordable accurate evaluation of the binding conformations predicted by molecular docking studies in bio-system

Franck-Condon factors bridge the gap between theoretical modeling and experimental observations for molecular electronic spectroscopy and electron transfer.Under the displaced harmonic oscillator approximation,multidimensional Franck-Condon factors are decomposed into a product of many one-dimensional(1D)Franck-Condon(FC)factors,and each 1D-FC factor is associated with one Huang-Rhys factor that determines the leading contribution of     

Call for Papers

<正>"The Journal of Shanghai Normal University:Mathematics"is published by Shanghai Normal University as regular issues of The Journal of Shanghai Normal University each year from 2014 in English.The editors-in-chief of the issues are professors Yuhao Cong and Maoan Han.The Journal of Shanghai Normal University was started in 1958 with