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.
In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces a binary hash code. In previous work, the aggregating and the hashing processes are designed independently. In this paper, we propose a novel framework where feature aggregating and...
Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher Vector encoding with Variational Auto-Encoder (FV-VAE), a novel deep architecture that quantizes the local activations of convolutional layer in a deep generative...
Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained...
Fine-grained activity understanding in videos has attracted considerable recent attention with a shift from action classification to detailed actor and action understanding that provides compelling results for perceptual needs of cutting-edge autonomous systems. However, current methods for detailed understanding of actor and action have significant limitations: they require large amounts of finely...
Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task. Detectors learned from a public dataset can only work with a fixed list of categories, while training from scratch usually requires a large amount of training data with detailed annotations. This work aims to explore a novel approach – learning object detectors from documentary...
Structured output support vector machine (SVM) based tracking algorithms have shown favorable performance recently. Nonetheless, the time-consuming candidate sampling and complex optimization limit their real-time applications. In this paper, we propose a novel large margin object tracking method which absorbs the strong discriminative ability from structured output SVM and speeds up by the correlation...
Aiming at some characteristics of servo valves that the complex influence between the failure modes and the high order nonlinearity of the fault datum, this paper presents a fault diagnosis model-Deep Intelligent Generalized Regression Neural Network (DGN). The DGN is a supervised deep learning model. In order to fully learning the fault datum, this paper proposed a logistic mapping and dynamic step...
In this paper, we propose a novel domain adaptation method for the classification of hyperspectral images. The proposed method projects the samples from both the source and target domain into a common latent space, where the ratio of within-class distance to between-class distance is minimized. We present a probabilistic framework to learn such transformations and solve the problem with an alternating...
The Belief Rule Base (BRB) has been used in modeling the complex nonlinear systems. Traditionally, the construction of BRB is under the conjunctive assumption which requires covering each and every possible combination of all the referenced values of all the attributes. Later, the disjunctive assumption of BRB is proposed which does not require simultaneously taking the status of all the attributes...
We introduce a novel technique for knowledge transfer, where knowledge from a pretrained deep neural network (DNN) is distilled and transferred to another DNN. As the DNN performs a mapping from the input space to the output space through many layers sequentially, we define the distilled knowledge to be transferred in terms of flow between layers, which is calculated by computing the inner product...
This paper presents a new spatial-spectral classification method for hyperspectral images, which consists of three main techniques. Firstly, fully constrained least squares (FCLS) that is common in hyperspectral unmixing is investigated for hyperspectral image classification in kernel Hilbert space. Secondly, the spatial-spectral information of hyperspectral images is exploited to improve the classification...
Echo state network (ESN) is a powerful tool for nonlinear system modeling. However, the random setting of structure (mainly the reservoir) may degrade its estimation accuracy. To create the optimal reservoir for a given task, a novel ESN design method based on differential evolution algorithm is proposed. Firstly, the weight matrix of reservoir is constructed via the singular value decomposition (SVD)...
The accurate identification of the helicopter flight action is the basis for guiding the training of the pilot. According to the accuracy of the helicopter flight action recognition, the paper proposed a new decision-tree-based support vector machine method to realize the helicopter multi-flight action identification. Use the tree structure of the decision tree to solve the multi-class problem of...
Recently, hashing based approximate nearest neighbor search has attracted much attention in large scale data search task. Moreover, some cross-modal hashing methods have also been proposed to perform efficient search of different modalities. However, there are still some problems to be further considered. For example, some of them cannot make use of label information, which contains helpful information...
Hashing has been recognized as one of the most promising ways in indexing and retrieving high-dimensional data due to the excellent merits in efficiency and effectiveness. Nevertheless, most existing approaches inevitably suffer from the problem of “semantic gap”, especially when facing the rapid evolution of newly-emerging “unseen” categories on the Web. In this work, we propose an innovative approach,...
Support vector machine (SVM) is a popular machine learning method and has been widely applied in many real-world applications. Since SVM is sensitive to noises, fuzzy SVM (FSVM) has been proposed to relieve the over-fitting problem caused by noises through assigning a fuzzy membership to each sample. Then, different samples make different contributions to the learning of classification hyperplane...
Domain adaptation methods have been proposed to reduce the training efforts needed to control an upper-limb prosthesis by adapting well performing models from previous subjects to the new subject. These studies generally reported impressive reductions in the required number of training samples to achieve a certain level of accuracy for intact subjects. We further investigate two popular methods in...
Image classification mainly uses the classifier to classify the extracted image features. In the traditional image feature extraction, it is difficult to set the appropriate feature patterns for the complex images. Simultaneously, the training algorithm of the classifier also affects the accuracy of image classification. In order to solve these problems, the combination of deep belief networks and...
The average time a resource needs to process incoming requests in a monitored workload mix is a key parameter of stochastic performance models. Direct measurement of these resource demands is usually infeasible due to instrumentation overheads causing measurement interferences and perturbation in production environments.Thus, a number of statistical estimation approaches (e.g., based on optimization,...
In this paper, Multi-Task Linear Dependency Modeling is proposed to distinguish drug-related webpages that contain lots of images and text. Linear Dependency Modeling exploits semantic relations between images features and text features, and Multi-Task Learning takes advantage of metadata of webpages. Meaningful information of webpages can be made use of fully to improve classification accuracy. Experimental...
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.