摘要 :
We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and tel...
展开
We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. These include an innovative cue to measure the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined objectness measure to perform better than any cue alone. We also compare to interest point operators, a HOG detector, and three recent works aiming at automatic object segmentation. Finally, we present two applications of objectness. In the first, we sample a small numberof windows according to their objectness probability and give an algorithm to employ them as location priors for modern class-specific object detectors. As we show experimentally, this greatly reduces the number of windows evaluated by the expensive class-specific model. In the second application, we use objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. As shown in several recent papers, objectness can act as a valuable focus of attention mechanism in many other applications operating on image windows, including weakly supervised learning of object categories, unsupervised pixelwise segmentation, and object tracking in video. Computing objectness is very efficient and takes only about 4 sec. per image.
收起
摘要 :
The learning object remains an ill-defined concept, despite numerous and extensive discussion in the literature. This paper attempts to address this problem by providing a classification that potentially brings together various pe...
展开
The learning object remains an ill-defined concept, despite numerous and extensive discussion in the literature. This paper attempts to address this problem by providing a classification that potentially brings together various perspectives of what a learning object may be. Six unique types of learning objects are proposed and discussed: presentation, practice, simulation, conceptual models, information and contextual representation objects. The common characteristics of each are synthesized in a proposal that a learning object is best described as a representation designed to afford uses in different educational contexts. The classification of learning objects proposed could be useful as a framework for designers of digital resources and for those engaged in use of these resources in educational contexts.
收起
摘要 :
The generation of object proposals plays an important role in object detection. Most existing methods produce object proposals by using bottom-up cues, such as closed contour or superpixel. In this paper, we propose a novel method...
展开
The generation of object proposals plays an important role in object detection. Most existing methods produce object proposals by using bottom-up cues, such as closed contour or superpixel. In this paper, we propose a novel method to improve the ranking of object proposals by combining bottom-up cues with top-down information of objectivity. Firstly, we utilize the bottom-up method to generate initial object proposals of the given test image. Then we retrieve its top-k similar images from training images set. Considering both appearance and spatial similarity between initial object proposals and the ground truth bounding boxes of these top-k similar images, we obtain the top-down guided scores of initial object proposals. Finally, the refined score of each initial object proposal is modeled as a fusion of the bottom-up score and the top-down score. Experiments show that our method achieves better performance compared with the state-of-art on the Pascal VOC2007 dataset.
收起
摘要 :
The problem of object recognition has been considered here. Color descriptions from distinct regions covering multiple segments are considered for object representation. Distinct multicolored regions are detected using edge maps a...
展开
The problem of object recognition has been considered here. Color descriptions from distinct regions covering multiple segments are considered for object representation. Distinct multicolored regions are detected using edge maps and clustering. Performance of the proposed methodologies has been evaluated on three data sets and the results are found to be better than existing methods when a small number of training views is considered.
收起
摘要 :
This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the phys...
展开
This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3D proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our object segmentation results are superior compared to the state-of-the-art methods.
收起
摘要 :
The objective of the present paper is to present an overview of LFN characteristics of modem MW turbines based on numerical simulations. Typical sizes of modem turbines are from 1-3 MW nominal generator power and a rotor diameter ...
展开
The objective of the present paper is to present an overview of LFN characteristics of modem MW turbines based on numerical simulations. Typical sizes of modem turbines are from 1-3 MW nominal generator power and a rotor diameter ranging from 80-100 m but larger prototypes up to 5 MW and with a rotor diameter of 126 m have now been installed. The numerical investigations comprise the common upwind rotor concept but also the turbines with a downwind rotor are considered. The reason to include the downwind rotor concept is that this turbine design has some advantages which could lead to future competitive designs compared with the upwind threebladed rotor. The simulation package comprises an aeroelastic time simulation code HAWC2 and an acoustic low frequency noise (LFN) prediction model. Computed time traces of rotor thrust and rotor torque from the aeroelastic model are input to the acoustic model which computes the sound pressure level (SPL) at a specified distance from the turbine. The influences on LFN on a number of turbine design parameters are investigated and the position of the rotor relative to the tower (upwind or downwind rotor) is found to be the most important design parameter. For an upwind rotor the LFN levels are so low that it should not cause annoyance of neighbouring people. Important turbine design parameters with strong influence on LFN are the blade tip speed and the distance between rotor and tower.
收起
摘要 :
This study proposes a hybrid approach to predict customer churn by combining statistic approaches and machine learning models. Unlike traditional methods, where churn is defined by a fixed period of time, the proposed algorithm us...
展开
This study proposes a hybrid approach to predict customer churn by combining statistic approaches and machine learning models. Unlike traditional methods, where churn is defined by a fixed period of time, the proposed algorithm uses the probability of customer alive derived from the statistical model to dynamically determine the churn line. After observing customer churn through clustering over time, the proposed method segmented customers into four behaviors: new, short-term, high-value, and churn, and selected machine learning models to predict the churned customers. This combination reduces the risk to be misjudged as churn for customers with longer consumption cycles. Two public datasets were used to evaluate the hybrid approach, an online retail of U.K. gift sellers and the largest E-Commerce of Pakistan. Based on the top three learning models, the recall ranged from 0.56 to 0.72 in the former while that ranged from 0.91 to 0.95 in the latter. Results show that the proposed approach enables companies to retain important customers earlier by predicting customer churn. The proposed hybrid method requires less data than existing methods.
收起
摘要 :
Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), ...
展开
Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), where correlation is efficiently implemented. However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain. Because this was previously unaccounted for, prior CF designs are not truly optimal, as their optimization criteria do not accurately quantify their optimization intention. In this paper, we introduce new zero-aliasing constraints that completely eliminate this aliasing problem by ensuring that the optimization criterion for a given CF corresponds to a linear correlation rather than a circular correlation. This means that previous CF designs can be significantly improved by this reformulation. We demonstrate the benefits of this new CF design approach with several important CFs. We present experimental results on diverse data sets and present solutions to the computational challenges associated with computing these CFs. Code for the CFs described in this paper and their respective zero-aliasing versions is available at
收起
摘要 :
Messier 35 (NGC 2168) in Gemini is a showpiece object of the winter sky, the open cluster fairing very well against the stiff completion from the likes of Auriga's Messier trio. It lies slap bang in the middle of the section of Mi...
展开
Messier 35 (NGC 2168) in Gemini is a showpiece object of the winter sky, the open cluster fairing very well against the stiff completion from the likes of Auriga's Messier trio. It lies slap bang in the middle of the section of Milky Way that runs through western Gemini.
收起
摘要 :
Solving real-world multi-objective optimization problems using Multi-Objective Optimization Algorithms becomes difficult when the number of objectives is high since the types of algorithms generally used to solve these problems ar...
展开
Solving real-world multi-objective optimization problems using Multi-Objective Optimization Algorithms becomes difficult when the number of objectives is high since the types of algorithms generally used to solve these problems are based on the concept of non-dominance, which ceases to work as the number of objectives grows. This problem is known as the curse of dimensionality. Simultaneously, the existence of many objectives, a characteristic of practical optimization problems, makes choosing a solution to the problem very difficult. Different approaches are being used in the literature to reduce the number of objectives required for optimization. This work aims to propose a machine learning methodology, designated by FS-OPA, to tackle this problem. The proposed methodology was assessed using DTLZ benchmarks problems suggested in the literature and compared with similar algorithms, showing a good performance. In the end, the methodology was applied to a difficult real problem in polymer processing, showing its effectiveness. The algorithm proposed has some advantages when compared with a similar algorithm in the literature based on machine learning (NL-MVU-PCA), namely, the possibility for establishing variable–variable and objective–variable relations (not only objective–objective), and the elimination of the need to define/chose a kernel neither to optimize algorithm parameters. The collaboration with the DM(s) allows for the obtainment of explainable solutions.
收起