Semantically Meaningful(语义上有意义)研究综述
Semantically Meaningful 语义上有意义 - In this study, we focus on the development of contextual, semantically meaningful representations of the driver state, which can then be used to determine the appropriate timing and conditions for transfer of control between driver and vehicle. [1] To endow such environments with truly autonomous behaviours, algorithms must extract semantically meaningful information from whichever sensor data is available. [2] During the training of the deep model, a domain prediction loss, a domain confusion loss, and a task-specific classification loss are effectively integrated to enable the learned feature to distinguish between different latent source domains, transfer between source and target domains, and become semantically meaningful among different classes. [3] To address this issue, test adaptation techniques can be used to automatically generate semantically meaningful GUI tests from test cases of applications with similar functionalities. [4] The skeleton is then recovered from the flux representation, which captures the position of skeletal pixels relative to semantically meaningful entities (e. [5] Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder, and is able to discover semantically meaningful latent codes without any supervision. [6] Existing computer-aided diagnosis algorithms show poor segmentation performance because of specular reflections, insufficient training data and the inability to focus on semantically meaningful lesion parts. [7] We show that the method introduced generates semantically meaningful high-level events, suitable for process mining; it is evaluated on real-world patient treatment data of a large U. [8] We provide further analysis demonstrating that unsupervised cluster selection results in semantically meaningful results, that finer grained categorization often has higher utility for VPR than high level semantic categorization (e. [9] As we will show, in many domains, DTW-based motifs represent semantically meaningful conserved behavior that would escape our attention using all existing Euclidean distance-based methods. [10] Targets in Experiments 1 and 2 were matrix-style sentences, while targets in Experiment 3 were semantically meaningful sentences. [11] Conventional SLAM systems lack the ability to create semantically meaningful maps for scene understanding of robots. [12] Expert feedback from movement ecologists shows the effectiveness of tailored visual-interactive means and visual analytics paradigms at segmenting multi-scale data, enabling them to perform semantically meaningful analyses. [13] MeanShift is one of the popular clustering algorithms and can be used to partition a digital image into semantically meaningful regions in an unsupervised manner. [14] However, the Earth is not covered equally by semantically meaningful classes. [15] Furthermore, they are efficient in performing interpolations between data-points in semantically meaningful ways. [16] Inspired by recent progress in video representation techniques, we further introduce the similarity of video representations to construct a semantically meaningful reward for this task. [17] In this paper, we present an attentive contextual network (ACN) to learn the spatially transformed image features and dense multi-scale contextual information of an image to generate semantically meaningful captions. [18] To reach a new level in the use of information processing technologies, first of all, a transition to a semantically meaningful representation is necessary for scientific knowledge extracted from information in a digital environment. [19] We developed an original deep learning method to temporally segment the ultrasound video into semantically meaningful segments (the video description). [20] In this paper, we address pornography detection by creating a model capable of locating and labelling sexual organs in images and extend this model to perform image classification to provide the user with one of 19 semantically meaningful descriptors of the content. [21] The proposed implicit semantic data augmentation (ISDA) first obtains semantically meaningful translations using an efficient sampling based method. [22] (ii) The result of a parameter sweep, rather than a single simulation, is the semantically meaningful result. [23] The proposed deep network is capable of analysing and decomposing unstructured complex point clouds into semantically meaningful parts. [24] Lightweight and semantically meaningful environment maps are crucial for many applications in robotics and autonomous driving to facilitate higher-level tasks such as navigation and planning. [25] However, as we envision robots performing complex tasks specified with semantically meaningful objects, it is necessary to capture semantic categories in the measurements, map representation, and exploration objective. [26] Our results indicate that the application of data mining techniques guided by knowledge gained from qualitative observation was instrumental in the discovery of semantically meaningful features from the raw log data. [27] GANs are powerful models for learning complex distributions to synthesize semantically meaningful samples. [28] It also does not incorporate semantically meaningful business roles, which could have a diverse impact upon access decisions in such multi-domain collaborative business environments. [29] Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters. [30] The aim of the work is to identify semantically meaningful structures of musical texts that vividly represent the original compositional style not from the standpoint of their uniqueness, but as a complex multilayered semantic space. [31] By relying on a siamese network with pre-trained language model encoders, we derived semantically meaningful term embeddings and computed similarity scores between them in a ranked manner. [32] We show that TSB is able to learn completely different transcription styles in controlled experiments on artificial data, it improves text recognition accuracy on large-scale real-world data, and it learns semantically meaningful transcription style embeddings. [33] First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. [34] Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. [35] To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background. [36] The JPSA learns a high-level, semantically meaningful, joint spatial–spectral feature representation from hyperspectral (HS) data by: 1) jointly learning latent subspaces and a linear classifier to find an effective projection direction favorable for classification; 2) progressively searching several intermediate states of subspaces to approach an optimal mapping from the original space to a potential more discriminative subspace; and 3) spatially and spectrally aligning a manifold structure in each learned latent subspace in order to preserve the same or similar topological property between the compressed data and the original data. [37] Firstly, our framework identifies grammatically and semantically meaningful phrases which contain product attributes and their corresponding opinions from original product reviews by using grammar rules and the latent Dirichlet allocation (LDA) model. [38] Then, given a new dataset, effective visualizations can be inferred from the knowledge graph with semantically meaningful rules. [39] SANDI combines visual tags, user-provided tags and background knowledge, and uses an Integer Linear Program to compute alignments that are semantically meaningful. [40] Next, it utilizes Mutual-Information-Maximization followed by an adversarial training strategy to cluster these regions into semantically meaningful classes. [41] In addition, besides recovering the incomplete tracks, the point trajectories are directly grouped into different object instances, and a number of semantically meaningful temporal primitive actions are automatically discovered. [42] Therefore, it is essential to design an elaborate network for accurate skin lesion classification, which can focus on semantically meaningful lesion parts. [43] In addition, local weights generated by non-negative matrix factorization are applied to the factorized latent space so that the decomposed part space is semantically meaningful. [44] We propose a novel training algorithm for the AE that facilitates learning more semantically meaningful features to address this problem. [45] We found that a simplification network trained with a simple loss, such as pixel loss or discriminator loss, may fail to retain the semantically meaningful details when simplifying a very sketchy and complicated drawing. [46] Its topological features include critical points and separatrices, which segment the domain into regions of coherent flow behavior, provide a sparse and semantically meaningful representation of the underlying data. [47] The measure is conceptually simple, training free, and provides a semantically meaningful quantification of visual attention over time. [48] We suggest that the avoidance of looking towards live others extends to the near space around them, at least in the absence of semantically meaningful gaze targets. [49] We demonstrate how to train an image translation network that can perform real‐time semantically meaningful style transfer to a set of target images with similar content as the source image. [50]在这项研究中，我们专注于开发驾驶员状态的上下文、语义上有意义的表示，然后可用于确定驾驶员和车辆之间控制转移的适当时机和条件。 [1] 为了赋予这样的环境真正的自主行为，算法必须从任何可用的传感器数据中提取语义上有意义的信息。 [2] 在深度模型的训练过程中，域预测损失、域混淆损失和特定任务分类损失被有效整合，使学习到的特征能够区分不同的潜在源域，在源域和目标域之间迁移，并成为在不同类之间具有语义意义。 [3] 为了解决这个问题，可以使用测试适应技术从具有相似功能的应用程序的测试用例中自动生成语义上有意义的 GUI 测试。 [4] 然后从通量表示中恢复骨架，该表示捕获骨架像素相对于语义上有意义的实体的位置（例如。 [5] 与变分自动编码器等其他变体相比，我们的框架表现出更好的解缠结，并且能够在没有任何监督的情况下发现语义上有意义的潜在代码。 [6] 由于镜面反射、训练数据不足以及无法专注于具有语义意义的病变部位，现有的计算机辅助诊断算法表现出较差的分割性能。 [7] 我们展示了所介绍的方法生成了语义上有意义的高级事件，适用于流程挖掘；它是根据大型 U 的真实世界患者治疗数据进行评估的。 [8] 我们提供了进一步的分析，证明无监督的聚类选择会产生语义上有意义的结果，更细粒度的分类对于 VPR 的效用通常高于高级语义分类（例如。 [9] 正如我们将展示的，在许多领域中，基于 DTW 的基序代表了语义上有意义的保守行为，使用所有现有的基于欧几里德距离的方法可以逃避我们的注意。 [10] 实验 1 和 2 中的目标是矩阵式句子，而实验 3 中的目标是语义有意义的句子。 [11] 传统的 SLAM 系统缺乏为机器人场景理解创建语义上有意义的地图的能力。 [12] 运动生态学家的专家反馈显示了量身定制的视觉交互手段和视觉分析范式在分割多尺度数据方面的有效性，使他们能够执行语义上有意义的分析。 [13] MeanShift 是一种流行的聚类算法，可用于以无监督的方式将数字图像划分为具有语义意义的区域。 [14] 然而，地球并没有被具有语义意义的类平等地覆盖。 [15] 此外，它们在以语义上有意义的方式执行数据点之间的插值方面非常有效。 [16] 受视频表示技术最新进展的启发，我们进一步介绍了视频表示的相似性，以为此任务构建具有语义意义的奖励。 [17] 在本文中，我们提出了一个注意力集中的上下文网络（ACN）来学习图像的空间变换图像特征和密集的多尺度上下文信息，以生成具有语义意义的字幕。 [18] 为了在信息处理技术的使用方面达到一个新的水平，首先，对于从数字环境中的信息中提取的科学知识，必须过渡到语义上有意义的表示。 [19] 我们开发了一种原始的深度学习方法，将超声视频时间分割成语义上有意义的片段（视频描述）。 [20] 在本文中，我们通过创建一个能够在图像中定位和标记性器官的模型来解决色情检测问题，并将该模型扩展为执行图像分类，从而为用户提供 19 个具有语义意义的内容描述符之一。 [21] 所提出的隐式语义数据增强（ISDA）首先使用有效的基于采样的方法获得语义上有意义的翻译。 [22] (ii) 参数扫描的结果，而不是单个模拟，是语义上有意义的结果。 [23] 所提出的深度网络能够分析和分解非结构化的复杂点云为语义上有意义的部分。 [24] 轻量级和语义上有意义的环境地图对于机器人和自动驾驶中的许多应用至关重要，以促进导航和规划等更高级别的任务。 [25] 然而，当我们设想机器人执行由具有语义意义的对象指定的复杂任务时，有必要在测量、地图表示和探索目标中捕获语义类别。 [26] 我们的结果表明，以定性观察获得的知识为指导的数据挖掘技术的应用有助于从原始日志数据中发现具有语义意义的特征。 [27] GAN 是学习复杂分布以合成具有语义意义的样本的强大模型。 [28] 它也没有包含语义上有意义的业务角色，这可能对这种多域协作业务环境中的访问决策产生不同的影响。 [29] 实验表明，我们的可解释过滤器在语义上比传统过滤器更有意义。 [30] 这项工作的目的是识别音乐文本的语义上有意义的结构，这些结构生动地代表了原始的作曲风格，而不是从其独特性的角度，而是作为一个复杂的多层语义空间。 [31] 通过依赖具有预训练语言模型编码器的连体网络，我们推导出语义上有意义的术语嵌入，并以排序方式计算它们之间的相似度分数。 [32] 我们表明，TSB 能够在人工数据的受控实验中学习完全不同的转录风格，它提高了大规模真实世界数据的文本识别准确性，并且它学习了语义上有意义的转录风格嵌入。 [33] 首先，我们基于迁移学习任务学习图像的语义上有意义的表示，在此期间，深度神经网络在独立但相似的数据上进行训练。 [34] 使用自然语言查询的视频检索需要在文本和视听输入之间学习语义上有意义的联合嵌入。 [35] 为了克服这个问题，我们开发了一种用于语义上有意义的局部人脸属性转移的新框架，该框架可以灵活地将人脸器官的局部属性从参考图像转移到输入图像中的语义等效器官，同时保留背景。 [36] JPSA 通过以下方式从高光谱 (HS) 数据中学习高级的、语义上有意义的联合空间-光谱特征表示：1) 联合学习潜在子空间和线性分类器，以找到有利于分类的有效投影方向； 2) 逐步搜索子空间的几个中间状态，以接近从原始空间到潜在更具辨别力的子空间的最佳映射； 3）空间和光谱对齐每个学习潜在子空间中的流形结构，以保持压缩数据和原始数据之间相同或相似的拓扑属性。 [37] 首先，我们的框架通过使用语法规则和潜在狄利克雷分配（LDA）模型识别出具有语法和语义意义的短语，这些短语包含产品属性及其来自原始产品评论的相应意见。 [38] 然后，给定一个新的数据集，可以从具有语义意义规则的知识图谱中推断出有效的可视化。 [39] SANDI 结合了视觉标签、用户提供的标签和背景知识，并使用整数线性程序来计算语义上有意义的对齐。 [40] 接下来，它利用互信息最大化，然后是对抗性训练策略，将这些区域聚类到语义上有意义的类中。 [41] 此外，除了恢复不完整的轨迹外，点轨迹直接分组为不同的对象实例，并自动发现许多语义上有意义的时间原语动作。 [42] 因此，必须设计一个精细的网络来进行准确的皮肤病变分类，该网络可以专注于具有语义意义的病变部位。 [43] 此外，将非负矩阵分解生成的局部权重应用于分解后的潜在空间，使分解后的部分空间在语义上有意义。 [44] 我们为 AE 提出了一种新的训练算法，它有助于学习更多语义上有意义的特征来解决这个问题。 [45] 我们发现，在简化非常粗略和复杂的绘图时，使用简单损失（例如像素损失或鉴别器损失）训练的简化网络可能无法保留语义上有意义的细节。 [46] 它的拓扑特征包括临界点和分隔线，将域分割成连贯流动行为的区域，提供底层数据的稀疏和语义上有意义的表示。 [47] 该度量在概念上很简单，无需训练，并且随着时间的推移提供视觉注意力的语义上有意义的量化。 [48] 我们建议避免看向活生生的其他人延伸到他们周围的附近空间，至少在没有语义上有意义的凝视目标的情况下。 [49] 我们演示了如何训练一个图像翻译网络，该网络可以对一组具有与源图像相似内容的目标图像执行实时语义上有意义的风格转换。 [50]
Generate Semantically Meaningful
To address this issue, test adaptation techniques can be used to automatically generate semantically meaningful GUI tests from test cases of applications with similar functionalities. [1] We show that the method introduced generates semantically meaningful high-level events, suitable for process mining; it is evaluated on real-world patient treatment data of a large U. [2] In this paper, we present an attentive contextual network (ACN) to learn the spatially transformed image features and dense multi-scale contextual information of an image to generate semantically meaningful captions. [3] The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images. [4]为了解决这个问题，可以使用测试适应技术从具有相似功能的应用程序的测试用例中自动生成语义上有意义的 GUI 测试。 [1] 我们展示了所介绍的方法生成了语义上有意义的高级事件，适用于流程挖掘；它是根据大型 U 的真实世界患者治疗数据进行评估的。 [2] 在本文中，我们提出了一个注意力集中的上下文网络（ACN）来学习图像的空间变换图像特征和密集的多尺度上下文信息，以生成具有语义意义的字幕。 [3] nan [4]
Identify Semantically Meaningful
The aim of the work is to identify semantically meaningful structures of musical texts that vividly represent the original compositional style not from the standpoint of their uniqueness, but as a complex multilayered semantic space. [1] Recent research has started to explore node contents to identify semantically meaningful communities. [2]这项工作的目的是识别音乐文本的语义上有意义的结构，这些结构生动地代表了原始的作曲风格，而不是从其独特性的角度，而是作为一个复杂的多层语义空间。 [1] 最近的研究已经开始探索节点内容以识别语义上有意义的社区。 [2]
Learn Semantically Meaningful
We show that TSB is able to learn completely different transcription styles in controlled experiments on artificial data, it improves text recognition accuracy on large-scale real-world data, and it learns semantically meaningful transcription style embeddings. [1] First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. [2]我们表明，TSB 能够在人工数据的受控实验中学习完全不同的转录风格，它提高了大规模真实世界数据的文本识别准确性，并且它学习了语义上有意义的转录风格嵌入。 [1] 首先，我们基于迁移学习任务学习图像的语义上有意义的表示，在此期间，深度神经网络在独立但相似的数据上进行训练。 [2]
semantically meaningful representation
In this study, we focus on the development of contextual, semantically meaningful representations of the driver state, which can then be used to determine the appropriate timing and conditions for transfer of control between driver and vehicle. [1] To reach a new level in the use of information processing technologies, first of all, a transition to a semantically meaningful representation is necessary for scientific knowledge extracted from information in a digital environment. [2] First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. [3] Its topological features include critical points and separatrices, which segment the domain into regions of coherent flow behavior, provide a sparse and semantically meaningful representation of the underlying data. [4] In this talk, I will first discuss deep learning models that can find semantically meaningful representations of words, learn to read documents and answer questions about their content. [5]在这项研究中，我们专注于开发驾驶员状态的上下文、语义上有意义的表示，然后可用于确定驾驶员和车辆之间控制转移的适当时机和条件。 [1] 为了在信息处理技术的使用方面达到一个新的水平，首先，对于从数字环境中的信息中提取的科学知识，必须过渡到语义上有意义的表示。 [2] 首先，我们基于迁移学习任务学习图像的语义上有意义的表示，在此期间，深度神经网络在独立但相似的数据上进行训练。 [3] 它的拓扑特征包括临界点和分隔线，将域分割成连贯流动行为的区域，提供底层数据的稀疏和语义上有意义的表示。 [4] nan [5]
semantically meaningful feature
Our results indicate that the application of data mining techniques guided by knowledge gained from qualitative observation was instrumental in the discovery of semantically meaningful features from the raw log data. [1] We propose a novel training algorithm for the AE that facilitates learning more semantically meaningful features to address this problem. [2] It will encourage the network to generate more semantically meaningful features for each category. [3] However, they suffer from the following two limitations: (1) the classifier is trained on source samples and forms a source-domain-specific boundary, which ignores features from the target domain and (2) semantically meaningful features are merely built from the adversary of a generator and a discriminator, which ignore selecting the domain invariant features. [4] The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images. [5]我们的结果表明，以定性观察获得的知识为指导的数据挖掘技术的应用有助于从原始日志数据中发现具有语义意义的特征。 [1] 我们为 AE 提出了一种新的训练算法，它有助于学习更多语义上有意义的特征来解决这个问题。 [2] nan [3] nan [4] nan [5]
semantically meaningful information
To endow such environments with truly autonomous behaviours, algorithms must extract semantically meaningful information from whichever sensor data is available. [1] We also introduce two data augmentation strategies and present evidence that the model learns generalizable and semantically meaningful information. [2]为了赋予这样的环境真正的自主行为，算法必须从任何可用的传感器数据中提取语义上有意义的信息。 [1] 我们还介绍了两种数据增强策略，并提供了模型学习可概括和语义上有意义的信息的证据。 [2]
semantically meaningful entity
The skeleton is then recovered from the flux representation, which captures the position of skeletal pixels relative to semantically meaningful entities (e. [1] Information granules are semantically meaningful entities, which play a central role in knowledge representation and system modeling in the framework of Granular Computing. [2]然后从通量表示中恢复骨架，该表示捕获骨架像素相对于语义上有意义的实体的位置（例如。 [1] 信息粒是语义上有意义的实体，在粒计算框架中的知识表示和系统建模中起着核心作用。 [2]
semantically meaningful lesion
Existing computer-aided diagnosis algorithms show poor segmentation performance because of specular reflections, insufficient training data and the inability to focus on semantically meaningful lesion parts. [1] Therefore, it is essential to design an elaborate network for accurate skin lesion classification, which can focus on semantically meaningful lesion parts. [2]由于镜面反射、训练数据不足以及无法专注于具有语义意义的病变部位，现有的计算机辅助诊断算法表现出较差的分割性能。 [1] 因此，必须设计一个精细的网络来进行准确的皮肤病变分类，该网络可以专注于具有语义意义的病变部位。 [2]
semantically meaningful result
We provide further analysis demonstrating that unsupervised cluster selection results in semantically meaningful results, that finer grained categorization often has higher utility for VPR than high level semantic categorization (e. [1] (ii) The result of a parameter sweep, rather than a single simulation, is the semantically meaningful result. [2]我们提供了进一步的分析，证明无监督的聚类选择会产生语义上有意义的结果，更细粒度的分类对于 VPR 的效用通常高于高级语义分类（例如。 [1] (ii) 参数扫描的结果，而不是单个模拟，是语义上有意义的结果。 [2]
semantically meaningful sentence
Targets in Experiments 1 and 2 were matrix-style sentences, while targets in Experiment 3 were semantically meaningful sentences. [1] Siamese-ERNIE is a modification of the pretrained ERNIE network that uses siamese network structures to derive semantically meaningful sentence embeddings. [2]实验 1 和 2 中的目标是矩阵式句子，而实验 3 中的目标是语义有意义的句子。 [1] Siamese-ERNIE 是对预训练 ERNIE 网络的修改，它使用连体网络结构来推导语义上有意义的句子嵌入。 [2]
semantically meaningful class
However, the Earth is not covered equally by semantically meaningful classes. [1] Next, it utilizes Mutual-Information-Maximization followed by an adversarial training strategy to cluster these regions into semantically meaningful classes. [2]然而，地球并没有被具有语义意义的类平等地覆盖。 [1] 接下来，它利用互信息最大化，然后是对抗性训练策略，将这些区域聚类到语义上有意义的类中。 [2]
semantically meaningful object
However, as we envision robots performing complex tasks specified with semantically meaningful objects, it is necessary to capture semantic categories in the measurements, map representation, and exploration objective. [1] Introducing semantically meaningful objects to visual Simultaneous Localization And Mapping (SLAM) has the potential to improve both the accuracy and reliability of pose estimates, especially in challenging scenarios with significant viewpoint and appearance changes. [2]然而，当我们设想机器人执行由具有语义意义的对象指定的复杂任务时，有必要在测量、地图表示和探索目标中捕获语义类别。 [1] 将语义上有意义的对象引入视觉同步定位和映射 (SLAM) 有可能提高姿势估计的准确性和可靠性，尤其是在具有显着视点和外观变化的挑战性场景中。 [2]
semantically meaningful local
To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background. [1] We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism. [2]为了克服这个问题，我们开发了一种用于语义上有意义的局部人脸属性转移的新框架，该框架可以灵活地将人脸器官的局部属性从参考图像转移到输入图像中的语义等效器官，同时保留背景。 [1] 我们提出了一种新颖的算法，用于将图像的语义上有意义的局部区域的艺术风格转移到目标视频的局部区域，同时保持其照片真实感。 [2]