控制铰接对象时控制其姿势对于电影虚拟现实或动画等应用至关重要。然而,操纵对象的姿势需要了解其基础结构,即其关节以及它们如何互相互动。不幸的是,假设要知道的结构,因为现有方法所做的,排除了在新的对象类别上工作的能力。我们建议通过观察它们从多个视图移动,没有额外的监督,例如联合注释或有关该结构的信息,从而了解先前看不见的对象的外观和结构。我们的洞察力是,相对于彼此移动的相邻部件必须通过接头连接。为了利用这一观察,我们将3D的物体部分塑造为椭圆体,这使我们能够识别关节。我们将这种明确表示与隐式的表示,该显式表示可以补偿引入的近似值。我们表明我们的方法为不同的结构,从四足动物到单臂机器人到人类工作。
translated by 谷歌翻译
使用单视图2D照片仅集合,无监督的高质量多视图 - 一致的图像和3D形状一直是一个长期存在的挑战。现有的3D GAN是计算密集型的,也是没有3D-一致的近似;前者限制了所生成的图像的质量和分辨率,并且后者对多视图一致性和形状质量产生不利影响。在这项工作中,我们提高了3D GAN的计算效率和图像质量,而无需依赖这些近似。为此目的,我们介绍了一种表现力的混合明确隐式网络架构,与其他设计选择一起,不仅可以实时合成高分辨率多视图一致图像,而且还产生高质量的3D几何形状。通过解耦特征生成和神经渲染,我们的框架能够利用最先进的2D CNN生成器,例如Stylega2,并继承它们的效率和表现力。在其他实验中,我们展示了与FFHQ和AFHQ猫的最先进的3D感知合成。
translated by 谷歌翻译
我们解决了预测动态场景视频的显着图的问题。我们注意到,从固定数量的观察者的凝视数据重建的地图的准确性随帧而变化,因为它取决于场景的内容。当有有限数量的观察者可用时,此问题尤其如此紧迫。在这种情况下,随着传统的深度学习方法,直接最大限度地减少预测和测量的显着性图之间的差异,导致对嘈杂数据过度接受。我们提出了一种噪声感知培训(NAT)范式,这些培训量量化和占帧特异性凝视数据不准确的不确定性。我们表明NAT在有限的培训数据可用时特别有利,在不同模型,丢失函数和数据集中有实验。我们还引入了基于视频游戏的显着数据集,具有富有的时间语义,每帧多个凝视吸引子。数据集和源代码可在https://github.com/nvlabs/nattacy上获得。
translated by 谷歌翻译
These notes were compiled as lecture notes for a course developed and taught at the University of the Southern California. They should be accessible to a typical engineering graduate student with a strong background in Applied Mathematics. The main objective of these notes is to introduce a student who is familiar with concepts in linear algebra and partial differential equations to select topics in deep learning. These lecture notes exploit the strong connections between deep learning algorithms and the more conventional techniques of computational physics to achieve two goals. First, they use concepts from computational physics to develop an understanding of deep learning algorithms. Not surprisingly, many concepts in deep learning can be connected to similar concepts in computational physics, and one can utilize this connection to better understand these algorithms. Second, several novel deep learning algorithms can be used to solve challenging problems in computational physics. Thus, they offer someone who is interested in modeling a physical phenomena with a complementary set of tools.
translated by 谷歌翻译
In this work, we propose a framework relying solely on chat-based customer support (CS) interactions for predicting the recommendation decision of individual users. For our case study, we analyzed a total number of 16.4k users and 48.7k customer support conversations within the financial vertical of a large e-commerce company in Latin America. Consequently, our main contributions and objectives are to use Natural Language Processing (NLP) to assess and predict the recommendation behavior where, in addition to using static sentiment analysis, we exploit the predictive power of each user's sentiment dynamics. Our results show that, with respective feature interpretability, it is possible to predict the likelihood of a user to recommend a product or service, based solely on the message-wise sentiment evolution of their CS conversations in a fully automated way.
translated by 谷歌翻译
多语言神经文本到语音(NTTS)系统的基本设计决策是如何表示模型中的输入语言特征。查看文献中各种各样的方法,出现了两个主要范式,统一和单独的表示。前者在跨语言中使用一组共享的语音令牌,而后者为每种语言使用独特的语音令牌。在本文中,我们进行了一项全面的研究,比较了两种表示训练的多语言NTTS系统模型。我们的结果表明,统一方法始终在自然和口音方面始终获得更好的跨语性综合。单独的表示形式往往比统一的代币更大的令牌,这可能会影响模型容量。因此,我们进行了一项消融研究,以了解表示类型与令牌嵌入尺寸的相互作用。我们发现,两个范式之间的差异仅在一定阈值嵌入尺寸之上出现。这项研究提供了有力的证据,表明在构建多语言NTTS系统时,统一表示应该是首选的范式。
translated by 谷歌翻译
培训仅使用单语言语料库的多语言神经文本到语音(NTTS)模型已成为构建基于语音克隆的Polyglot NTTS系统的流行方式。为了训练这些模型,必须了解培训语料库的组成如何影响多语言语音综合的质量。在这种情况下,通常会听到诸如“包含更多西班牙数据有助于我的意大利综合,考虑到两种语言的亲密关系?”之类的问题。不幸的是,我们发现有关该主题缺乏完整性的现有文献。在目前的工作中,我们进行了一项广泛的消融研究,旨在了解培训语料库的各种因素(例如语言家族隶属关系,性别组成和演讲者的数量)如何有助于多面化综合的质量。我们的发现包括在大多数情况下首选女性扬声器数据的观察结果,并且在培训语料库中拥有更多来自目标语言的说话者并不总是有益的。此处的发现对于数据采购和语料库构建过程提供了信息。
translated by 谷歌翻译
近年来,对图表的研究受到了极大的关注。但是,到目前为止,大多数研究都集中在单层图的嵌入上。涉及多层结构的表示问题问题的少数研究取决于以下强烈的假设:层间链接是已知的,这限制了可能的应用范围。在这里,我们提出了多层,这是允许嵌入多重网络的图形算法的概括。我们表明,多层能够重建层内和层间连接性,超过了图形,该图是为简单图形而设计的。接下来,通过全面的实验分析,我们还以简单和多重网络中的嵌入性能阐明,表明图的密度或链接的随机性都会强烈影响嵌入的质量。
translated by 谷歌翻译
This article proposes a method to diminish the pose (position plus attitude) drift experienced by an SVO (Semi-Direct Visual Odometry) based visual navigation system installed onboard a UAV (Unmanned Air Vehicle) by supplementing its pose estimation non linear optimizations with priors based on the outputs of a GNSS (Global Navigation Satellite System) Denied inertial navigation system. The method is inspired in a PI (Proportional Integral) control system, in which the attitude, altitude, and rate of climb inertial outputs act as targets to ensure that the visual estimations do not deviate far from their inertial counterparts. The resulting IA-VNS (Inertially Assisted Visual Navigation System) achieves major reductions in the horizontal position drift inherent to the GNSS-Denied navigation of autonomous fixed wing low SWaP (Size, Weight, and Power) UAVs. Additionally, the IA-VNS can be considered as a virtual incremental position (ground velocity) sensor capable of providing observations to the inertial filter. Stochastic high fidelity Monte Carlo simulations of two representative scenarios involving the loss of GNSS signals are employed to evaluate the results and to analyze their sensitivity to the terrain type overflown by the aircraft as well as to the quality of the onboard sensors on which the priors are based. The author releases the C ++ implementation of both the navigation algorithms and the high fidelity simulation as open-source software.
translated by 谷歌翻译
虽然深入学习(DL)技术是解决映射到分类任务的网络问题的有前途的工具,但它们的计算复杂性仍然太高,而是相对于实时业务测量要求。为了降低DL推理成本,我们提出了一种新的缓存范例,我们命名为近似密钥缓存,这返回基于缓存的DL推断结果的所选输入的查找的近似结果。虽然近似缓存点击缓解DL推理工作负载并提高系统吞吐量,但是它们介绍了近似误差。因此,我们将近似密钥高速缓存以纠错原理算法,我们命名为Auto-Refresh。我们分析模拟了我们对经典LRU和理想高速缓存的缓存系统性能,我们对预期的绩效进行了跟踪驱动的评估,并比较了我们所提出的方法与最先进的相似性缓存的好处 - 作证我们提案的实际利益。
translated by 谷歌翻译