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.
Least squares support vector machines (LSSVM) has a good performance in small data samples, but can't solve the large-scale sample problems. In this paper, large data set sparse least squares support vector machines model based on stochastic entropy is proposed, and it can be applied to large-scale data samples. Firstly, the large-scale data set is divided into several subsets. Then the entropy method...
In this paper, we address the problem of estimating the total flow of a crowd of pedestrians from spatially limited observations. Our approach relies on identifying a dynamical system regime that characterizes the observed flow in a limited spatial domain by solving for the modes and eigenvalues of the corresponding Koopman operator. We develop a framework where we first approximate the Koopman operator...
Zepeda and Pérez [41] have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time with negligible effect on accuracy. We call this model square-loss exemplar machine,...
Convolutional Neural Networks (CNNs) with Bilinear Pooling, initially in their full form and later using compact representations, have yielded impressive performance gains on a wide range of visual tasks, including fine-grained visual categorization, visual question answering, face recognition, and description of texture and style. The key to their success lies in the spatially invariant modeling...
We propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style, for neural image style transfer. To transfer an image to a specific style, the corresponding filter bank is operated on top of the intermediate feature embedding produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt, where the learning...
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear. Moreover, recent machine...
Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we...
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods...
Nonlinear regression is a common statistical tool to solve many computer vision problems (e.g., age estimation, pose estimation). Existing approaches to nonlinear regression fall into two main categories: (1) The universal approach provides an implicit or explicit homogeneous feature mapping (e.g., kernel ridge regression, Gaussian process regression, neural networks). These approaches may fail when...
To predict a set of diverse and informative proposals with enriched representations, this paper introduces a differentiable Determinantal Point Process (DPP) layer that is able to augment the object detection architectures. Most modern object detection architectures, such as Faster R-CNN, learn to localize objects by minimizing deviations from the ground truth, but ignore correlation between multiple...
In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-based domain adaptation methods generally ignore the changes of class prior distributions, i.e., class weight bias across domains. This remains an open problem but ubiquitous for domain adaptation, which can be caused by...
Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, and general. Rather than imposing a prior based on theory, we propose instead to learn one from the data...
In this paper, we propose a fully convolutional network for iterative non-blind deconvolution. We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noise in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve...
Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a deep transfer learning scheme, called selective joint fine-tuning, for improving the performance of deep learning tasks with insufficient training data. In this scheme, a target learning task...
To overcome the limitations of manual features and obtain the operating characteristics of the equipment in complex operation processes, different deep learning models have been utilized for industrial data, improving classification accuracy yet causing some other limitations meanwhile. In this paper, a deep hybrid model named Stochastic Convolutional and Deep Belief Network (SCDBN), which assembles...
Pattern recognition techniques have been widely used in security-sensitive applications to distinguish malicious samples from legitimate ones. However, there usually exist some intelligent attackers who intend to have malicious samples to be mis-classified as legitimate at test time, i.e. evasion attack. Current researches show that traditional Support Vector Machines (SVMs) are vulnerable to evasion...
In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically. Unlike previous works which have stressed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the networks backbone and operates on feature maps. Feature maps will be inflated/shrinked...
For the mathematical model of tug handling simulator, the locally optimal locally weighted learning (LWL) is proposed. Firstly, samples space rearrangement is taken to diminish the one-to-many mapping and non-separable of ship motion states. Secondly, distance metric is learned by leave-one-out cross validation for every sample, and this approach improves the nonlinearity mapping ability and robustness...
In this work, we develop a new framework to combine ensemble learning and composite kernel learning for hyperspectral image classification. We refer it as the multiple composite kernel learning, which is based on an iterative architecture. More specifically, in each iteration, we use the rotation-based ensemble to create rotation matrix, which is used to generate rotated features for both spectral...
Very large overhead imagery associated with ground truth maps has the potential to generate billions of training image patches for machine learning algorithms. However, random sampling selection criteria often leads to redundant and noisy-image patches for model training. With minimal research efforts behind this challenge, the current status spells missed opportunities to develop supervised learning...
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.