The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation...
Most of the prior works summarize videos by either exploring different heuristically designed criteria in an unsupervised way or developing fully supervised algorithms by leveraging human-crafted training data in form of video-summary pairs or importance annotations. However, unsupervised methods are blind to the video category and often fail to produce semantically meaningful video summaries. On...
We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation and classification. Current state-of-the-art approaches work offline, and are too slow to be useful in real-world settings. To overcome their limitations we introduce two major developments. Firstly, we adopt real-time SSD (Single Shot Multi-Box Detector) CNNs to regress and classify detection boxes...
Smart city has been advanced much from the conceptual model to the actual construction stage. This paper takes Nanhai as an example to demonstrate how to manage the resources of IoT as a whole and plan the top-level design of IoT development and smart city. After analysis of Nanhai IoT status, a general framework of Nanhai IoT development is proposed as the top-level design using five architectures...
Understanding where people look in images is an important problem in computer vision. Despite significant research, it remains unclear to what extent human fixations can be predicted by low-level (contrast) compared to highlevel (presence of objects) image features. Here we address this problem by introducing two novel models that use different feature spaces but the same readout architecture. The...
Estimating a depth map from multiple views of a scene is a fundamental task in computer vision. As soon as more than two viewpoints are available, one faces the very basic question how to measure similarity across >2 image patches. Surprisingly, no direct solution exists, instead it is common to fall back to more or less robust averaging of two-view similarities. Encouraged by the success of machine...
Person re-identification is an important task in video surveillance systems. It can be formally defined as establishing the correspondence between images of a person taken from different cameras at different times. In this paper, we present a two stream convolutional neural network where each stream is a Siamese network. This architecture can learn spatial and temporal information separately. We also...
Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view adaptation scheme to automatically regulate observation viewpoints during the occurrence of an action. Rather than re-positioning the skeletons based on a human defined...
We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem’s geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin...
A novel wideband digital predistortion (DPD) technique that enables a simpler feedback circuit is proposed. The proposed scalar feedback method in baseband can reduce the number of analog to digital converter (ADC) while keeping its bandwidth same as the conventional method. DPD parameter determination algorithm is modified to enable the scalar feedback. To compare the performance of the proposed...
ISO/IEC 17825 defines a methodology to evaluate the vulnerability of a cryptographic module against side-channel attacks. It calculates the correlation between internal data and power consumption or the electro-magnetic (EM) radiation of the module to assess the possibility of hidden information leakage thorough the physical power or EM signals. In order to improve the precision of the assessment,...
The objective of this work is the optimization of a controlled electric vehicle (EV) strategy under a centralized architecture, considering a medium voltage electrical network. The method developed consists of a Particle Swarm Optimization, which determines the time available to charger each EV, segmentation of nodes of the network and their respective charging times, considering as constraints the...
The current IoT ecosystem is Cloud centric which can not handle a diverse set of IoT applications and services, especially those demanding real time response. This paper proposes an Edge Computing (EC) architecture that provides an intermediate computing layer for IoT data. The proposed architecture utilizes Virtual IoT Devices (VID) for local data processing, management of physical IoT devices and...
In this paper, we propose a 2-D grouping FIFO based FFT hardware architecture, supporting 36 different FFT sizes defined in 3GPP-LTE systems. Also, the important design foundation is to develop a hybrid-radix computing kernel engine, including 4 configuration types. In a design implementation via TSMC 90-nm CMOS technology, the reconfigurable FFT chip only has a core area occupation of 1.51 mm2, dissipating...
Data centers availability is mandatory and is conditioned by a quick response to failures and attacks thanks to efficient live forensics. However, this task is lately impossible to complete with classic systems because of encountered data rates and service diversity. Moreover, Software-Defined Networking (SDN) devices agility requirements prevent the use of Application Specific Integrated Circuits...
Smart grid software integrates various software components in Generation, Transmission, Distribution, Smart Metering and Cloud systems. The smart grid architecture is evolving with new features and to accommodate legacy software elements. Smart grid integrated software is an evolving approach in line with modern Information and Communication technology. In this paper, the authors propose a software...
This paper proposes a design pattern based on the service-oriented architecture for the design of flexible distributed automation control system for substation automation systems. The design pattern is intended to be applied to control systems based on the leading standards for software development of smart grid: IEC 61850 and IEC 61499. The proposed design pattern models system requirements as orchestrators...
Artificial neural networks and deep learning methodologies have had growing interest across industry domains, including IoT and mobile systems. However, in low-power applications, resource limitations and operating environment restrictions make implementations difficult. This survey examines efforts that target the data and compute challenges of implementing energy efficient, low cost, and accurate...
Today's industry increasingly requires flexibility and adaptability in the development of automation control software, especially for automated production systems (aPS) including an automated material flow system (aMFS). To meet these demands, the development of the automation control software and the modification during the operation of the aMFS has to become as easy as possible without taking a...
Telecommunications networks have been transitioning from a centralized to distributed architecture. With Fiber extending deeper into the wireline network and Small Cells becoming a more prevalent means for targeting hard-to-reach subscribers, there has been significant growth in the number of network elements located far from the central switching office. The sheer quantity of network devices increases...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.