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.
Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details. Fine-grained sketch-based image retrieval (FG-SBIR) importantly leverages on such fine-grained characteristics of sketches to conduct instance-level retrieval of photos. Nevertheless, human sketches are often highly abstract and iconic, resulting in severe misalignments...
The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training. For example recognition in sketch images, which are distinctly more abstract and rarer...
To improve the dynamic response characteristics of permanent magnet synchronous motor (PMSM) servo systems, inertia identification based on the theory of model reference adaptive system (MRAS) has been researched. A novel method with variable gain is proposed for requirements of rapid convergence and high accuracy. This method improved by introducing an error integrator, which was employed to adjust...
In this paper, a fast and accurate method for extracting surface and leaky wave poles in planar multilayered structure is reported, which is based on GPU/CPU heterogeneous platform. To realize high-level parallel computing, the way to balance hardware computing and communications between different units are discussed in detail. By accurately extracting all the discrete poles on the complex plane,...
A planar W-band array antenna backed by a substrate integrated waveguide (SIW) cavity with high radiation efficiency is proposed in this paper. In order to avoid large loss caused by the complex feeding network, a SIW cavity operating at high-order resonating mode is adopted for the proposed antenna. Multiple radiation slots are etched on the top surface of a single layer SIW cavity for implementing...
The overlapped domain decomposition method is applied to the combined current and charge integral equation formulation for efficiently analyzing electromagnetic scattering in low frequency. The hybrid method is fast convergent when one of charge unknowns is removed for eliminating linear dependence in charges. In the method, only part of impedance matrix needs to be stored into memory, which reduces...
Sketch-based image retrieval (SBIR) has become a prominent research topic in recent years due to the proliferation of touch screens. The problem is however very challenging for that photos and sketches are inherently modeled in different modalities. Photos are accurate (colored and textured) depictions of the real-world, whereas sketches are highly abstract (black and white) renderings often drawn...
Sketch-based image retrieval (SBIR) is a challenging task due to the ambiguity inherent in sketches when compared with photos. In this paper, we propose a novel convolutional neural network based on Siamese network for SBIR. The main idea is to pull output feature vectors closer for input sketch-image pairs that are labeled as similar, and push them away if irrelevant. This is achieved by jointly...
To improve the dynamic response characteristics of permanent magnet synchronous motor (PMSM) servo system, an inertia identification method based on the theory of model reference adaptive system (MRAS) has been researched. A novel inertia identification method using genetic algorithm (GA) is proposed for requirements of rapid convergence and high precision. This method takes advantage of the global...
We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images. This is an extremely challenging task because (i) visual comparisons not only need to be fine-grained but also executed cross-domain, (ii) free-hand (finger) sketches are highly abstract, making fine-grained matching harder,...
We investigate whether it is possible to improve the performance of automated facial forensic sketch matching by learning from examples of facial forgetting over time. Forensic facial sketch recognition is a key capability for law enforcement, but remains an unsolved problem. It is extremely challenging because there are three distinct contributors to the domain gap between forensic sketches and photos:...
Many segmentation algorithms describe images in terms of a hierarchy of regions. Although such hierarchies can produce state of the art segmentations and have many applications, they often contain more data than is required for an efficient description. This paper shows Laplacian graph energy is a generic measure that can be used to identify semantic structures within hierarchies, independently of...
This paper addresses the problem of grouping image primitives; its principal contribution is an explicit definition of the Gestalt principle of Prägnanz, which organizes primitives into descriptions of images that are both simple and stable. Our definition of Prägnanz assumes just two things: that a vector of free variables controls some general grouping algorithm, and a scalar function measures the...
We study the problem of fine-grained sketch-based image retrieval. By performing instance-level (rather than category-level) retrieval, it embodies a timely and practical application, particularly with the ubiquitous availability of touchscreens. Three factors contribute to the challenging nature of the problem: (i) free-hand sketches are inherently abstract and iconic, making visual comparisons with...
Summary In this chapter, combustion process is improved by computing control settings with clustering algorithms. The framework involves learning from a high-dimensional data stream generated by the combustion process. Thus the system's dynamics is captured. The concepts of virtual age of the boiler and the control settings are introduced. The confidence of applying a control setting to improve boiler...
In this paper, an implementation of the ACA on GPU platform is presented, involving two parts: the matrix compression using the ACA and the batched matrix-vector products utilizing H-matrix form. Some numerical examples are provided to demonstrate the overall performance of the proposed implementation of the ACA algorithm on GPU platform through comparison with the 4-threaded CPU algorithm. In these...
The development of a city gradually fosters different functional regions, and between these regions there exists different social information due to human activities. In this paper, a Region Activation Entropy Model (RAEM) is proposed to discover the social relations hidden between the regions. Specifically we segment a city into coherent regions according the base station (BS) position and detect...
This paper proposes a new application of power amplifiers linearization technology for concurrent Dual-band differing in power. A Broadband power amplifier is used to verify proposed application. The dual 20MHz band spacing 200MHz are test at the carrier frequency of 2.3GHz and 2.5GHz. And the dual-band's power have more than 10dB difference. When the difference is 15dB, the simplified model can achieve...
We present a graph matching refinement framework that improves the performance of a given graph matching algorithm. Our method synergistically uses the inherent structure information embedded globally in the active association graph, and locally on each individual graph. The combination of such information reveals how consistent each candidate match is with its global and local contexts. In doing...
We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks. Our grouper formulates edge grouping as a graph partition problem, where a learning to rank method is developed to encode probabilities of candidate edge pairs. In particular, RankSVM is employed for the first time to combine multiple Gestalt...
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.