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.
Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires realtime inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment.,,,,,, In this work, we propose SqueezeDet, a fully convolutional neural network...
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets...
Sparse-matrix vector multiplication (SpMV) is the core compute routine for several scientific and commercial codebases. Because of its extremely irregular memory accesses (low temporal locality), indirect memory referencing (low spatial locality), low arithmetic intensity, and the non-zero pattern and non-zero density of the matrix, SpMV achieves a mere 10% of peak system performance. Because sparse...
Panoramic images capture cityscapes of dense urban structures by mapping multiple images from different viewpoints into a single composite image. One challenge to their construction is that objects that lie at different depth are often not stitched correctly in the panorama. The problem is especially troublesome for objects occupying large horizontal spans, such as telephone wires, crossing multiple...
Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random fields), while CNNs are “black-box” non-linear classifiers. In this paper, we show that a DPM can be formulated as a CNN, thus providing a synthesis of the two ideas. Our construction involves...
This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to train visual detectors for words that commonly occur in captions, including many different parts of speech such as nouns, verbs, and adjectives. The word detector...
Aircraft Electric Power Systems (EPS) route power from generators to vital avionic loads by configuring a set of electronic control switches denoted as contactors. In this paper, we address the problem of designing a hierarchical optimal control strategy for the EPS contactors in the presence of system faults. We first formalize the system connectivity, safety and performance requirements in terms...
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large pose variation often present in these domains. Pose-normalization seeks to align training exemplars, either piecewise by part or globally for the...
This paper develops a framework to analyze the latency and delay composition of workflows in a real-time networked aggregation system. These workflows are characterized by different sensor inputs that are processed along parallel branches that eventually merge or fuse to compute the aggregation result. The results for each flow must be produced within certain end-to-end deadlines or else the information...
In networked data fusion systems, results must be produced by end-to-end deadlines. As such, latency is an important attribute contributing to quality-of-information (Qol) in these systems. A key question is how much work can be completed on time given some amount of distributed resources and the logical workflow topology of the data fusion graph. To answer this question, this paper presents the concept...
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.