Having large databases of annotated images is important for many applications in computer vision and computer graphics. Some of the largest databases of annotated images rely on user participation (as in Flickr, Label...
详细信息
Having large databases of annotated images is important for many applications in computer vision and computer graphics. Some of the largest databases of annotated images rely on user participation (as in Flickr, LabelMe or Peekaboom). In this paper we address the problem of performing semiautomatic object labeling as a way of providing new annotated images. Some current efforts in this direction provide bounding boxes as the annotations (i.e. OPTIMOL and Seville Systems). However, in this work we present an approach that relies on a boosting process to automatically create polygonal annotations for objects similar to those entered by users in tools such as LabelMe. In particular, we train single class boosting classifiers using local image features to perform the simultaneous object detection and segmentation. We validate our approach using different object classes from the LabelMe, the TUD and the Weizmann databases. Moreover, our experiments show that we are able to correctly annotate new data returned by internet search engines.
GPGPU has been widely used in recent years in both academia and industry. Many research for benchmarks on GPUs were reported to achieve over 100 times speedup, however, due to the high overhead of data transfer betwee...
详细信息
In the article we describe the approach to parallel implementation of elementary operations for textual data categorization. In the experiments we evaluate parallel computations of similarity matrices and k-means algo...
详细信息
In the article we describe the approach to parallel implementation of elementary operations for textual data categorization. In the experiments we evaluate parallel computations of similarity matrices and k-means algorithm. The test datasets have been prepared as graphs created from Wikipedia articles related with links. W also present the approach to computing pairs of eigenvectors and eigenvalues for visualizations of the datasets. The implemented basic operations: computing similarity matrix, data clustering and spectral analysis have been used in our system for visualization of the Wikipedia categories on SOM as well as in a system for categorization search results in Wikipedia.
In order to minimize the conflict miss rate, cache memories can be organized in set-associative manner. The downside of increasing the associativity is increase in the per access energy consumption. In conventional n-...
详细信息
In order to minimize the conflict miss rate, cache memories can be organized in set-associative manner. The downside of increasing the associativity is increase in the per access energy consumption. In conventional n-way set-associative caches, irrespective of the set-wise demand, each set has n cache ways at its disposal, but cache sets may exhibit non-uniform demand for these cache ways. Exploiting this property, we propose a novel cache architecture, called way sharing cache, wherein by allowing sharing of cache ways among a pair of cache sets, we obtain dynamic energy savings as high as 41% in DL1 cache with negligible performance penalty.
There have been many attacks that exploit side-effects of program execution to expose secret information and many proposed countermeasures to protect against these attacks. However there is currently no systematic, ho...
详细信息
ISBN:
(纸本)9781450316422
There have been many attacks that exploit side-effects of program execution to expose secret information and many proposed countermeasures to protect against these attacks. However there is currently no systematic, holistic methodology for understanding information leakage. As a result, it is not well known how design decisions affect information leakage or the vulnerability of systems to side-channel attacks. In this paper, we propose a metric for measuring information leakage called the Side-channel Vulnerability Factor (SVF). SVF is based on our observation that all side-channel attacks ranging from physical to microarchitectural to software rely on recognizing leaked execution patterns. SVF quantifies patterns in attackers' observations and measures their correlation to the victim's actual execution patterns and in doing so captures systems' vulnerability to side-channel attacks. In a detailed case study of on-chip memory systems, SVF measurements help expose unexpected vulnerabilities in whole-system designs and shows how designers can make performance-security trade-offs. Thus, SVF provides a quantitative approach to secure computerarchitecture.
In this paper, an actual system based on wavelet transform and artificial neural networks was established to diagnose different types of fault in a gearbox. As a key step, biorthogonal wavelet was used to denoise in f...
详细信息
In the future scenario of transport and human mobility, the optimization of electric vehicles and their infrastructures (transport and energy supply) will be a key. This is the reason why it will have to provide adequ...
详细信息
In the future scenario of transport and human mobility, the optimization of electric vehicles and their infrastructures (transport and energy supply) will be a key. This is the reason why it will have to provide adequate intelligent systems, both in electric vehicles and in infrastructures that provide service. Moreover, the development nowadays of Intelligent Electronic Devices (IED) and communications Machine To Machine (M2M) have enabled commercial solutions with relatively inexpensive cost. This paper discusses the design of M2M-based IED to develop a prototype with a flexible architecture, incorporating GPRS as wireless WAN solution and GPS technology to equip the system with geo-location functions, in order to cover future applications between electric vehicles and the different infrastructures to provide service.
The context of energy diversification of the electricity market has triggered that many users have decided to invest in their own micro-grid to meet their needs. Moreover, at present the concept of Smart Grid is drivi...
详细信息
The context of energy diversification of the electricity market has triggered that many users have decided to invest in their own micro-grid to meet their needs. Moreover, at present the concept of Smart Grid is driving that all entities involved in the electricity market tend to form an open network where everyone can interact with each other, including those who use renewable energy. This document explains how must be an Intelligent Electronic Device (IED) that allows the user to control their micro-grid, describing what must be the functionality and architecture of this system. Finally, we present an IED prototype based on combining a processor and a FPGA to control a micro-grid.
Large-scale failures in telecommunication networks make the preservation of the connections inside a community a challenging task, being traditional approaches focused on the preservation of the global connectivity. T...
详细信息
ISBN:
(纸本)9781618399823;1618399829
Large-scale failures in telecommunication networks make the preservation of the connections inside a community a challenging task, being traditional approaches focused on the preservation of the global connectivity. To achieve this goal, a new concept of community is proposed, which combines not only the topological information of the network but also the traffic-level interaction. Moreover, six novel community-based strategies to determine best node candidates to be protected according to a limited budget are assessed. The proposed strategies have been tested over four different types of networks and compared to other well-known immunization or protection methods. The obtained results show that, depending on the network topology, either an improved intra-community or global traffic preservation can be achieved w.r.t. traditional approaches.
Nowadays, most computers that are commercially available off-the-shelf (COTS) include hardware features that increase the performance of parallel general-purpose threads (hyper threading, multicore, ccNUMA architectur...
详细信息
Nowadays, most computers that are commercially available off-the-shelf (COTS) include hardware features that increase the performance of parallel general-purpose threads (hyper threading, multicore, ccNUMA architectures) or SIMD kernels (CPU vector instructions, GPUs). The purpose of this paper is to perform a compared evaluation of several parallel programming models where each one is fitted to exploit some of these features but also each one requires a different level of programming skills. Four parallel programming models (OpenMP, Intel TBB, Intel ArBB, and CUDA) have been selected. The idea is to cover a wide spectrum of programming models and most of the parallel hardware features included in modern computers. On one hand, OpenMP and TBB platforms, that exploits parallel threads running on multicore systems. On the other hand, ArBB, that combines multicore parallel threads and multicore SIMD features with a simpler programming model, and CUDA that exploits SIMD features of the GPU hardware. Our results obtained with the benchmarks used on this paper suggest that OpenMP and TBB have a lower performance compared to ArBB and CUDA. But also that ArBB performance tends to be comparable with CUDA performance in most cases (although it is normally lower). Thus, there are evidences that a careful designed top range multicore and multisocket architecture, can be comparable in terms of performance with top range GPU cards for many applications, with the advantage of a simpler programming model.
暂无评论