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.
Real-world visual classification tasks typically need to deal with data observed from different domains. Inspired by canonical correlation analysis (CCA), we propose an enhanced CCA with local density for associating and recognizing cross-domain data. In addition to maximizing the correlation of the projected cross-domain data, our CCA model further exploits the local density information observed...
A method is presented which applies Long Short-Term Memory Recurrent Neural Networks on real market-research voice recordings in order to automatically predict emotional arousal from speech. While most previous work has dealt with evaluations of algorithms within the same speech corpus, the novelty of this paper lies in an extensive evaluation across corpora and languages. The approach is evaluated...
Robust appearance model is significantly important to state-of-the-art trackers. However, such trackers highly rely on the reliability of foreground appearance model. When the foreground is seriously occluded or the scene contains multiple objects with similar appearance, such foundation is destroyed. To extend the ability of trackers to handle these difficulties, we propose selective object and context...
In this paper, we develop a novel scheme to reduce the amount of training data required for training deep neural networks (DNNs). We first apply a partial mutual information (PMI) technique to seek for the optimal DNN feature set. Then we use a correlation matching based active learning (CMAL) technique to select and label the most informative training data. We integrate these two techniques with...
Functional magnetic resonance imaging (fMRI) is a powerful tool to analyze brain development and neuronal activity. Identifying discriminative brain regions between various groups within a population has generated great interest in recent years. In this work, we consider the problem of estimating multiple sparse, co-activated brain regions from fMRI observations belonging to different classes. More...
Neural word vector (NWV) such as word2vec is a powerful text representation tool that can encode extensive semantic information into compact vectors. This ability poses an interesting question in relation to image processing research - Can we learn better semantic image features from NWVs? We empirically explore this question in the context of semantic content-based image retrieval (CBIR). In this...
In this paper, the use of mutual information and the Learn++.NSE algorithm is proposed to create an EEG SSVEP BCI system that can select and utilize data sets originating from a group of users. In typical BCI systems, the nonstationarity in the EEG prevents the system from blindly applying training data from other users to the incoming data. Mutual information is introduced to select previous data...
Zero-shot Learning (ZSL) can leverage attributes to recognise unseen instances. However, the training data is limited and cannot adequately discriminate fine-grained classes with similar attributes. In this paper, we propose a complementary procedure that inversely makes use of attributes to infer discriminative visual features for unseen classes. In this way, ZSL is fully converted into conventional...
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent...
The cascade correlation neural network structure is proposed in this paper, which is used to predicting the closing price of the stocks related to state bank of India at the end of the particular day. The underlying fact of any neural network architecture is to minimize the error between the original outcome and expected result of the problem, by adjusting its weights in the architecture to the possible...
In the current engross world, traffic overflow is a common problem for the metropolises. In spite of increasing the size of transportation systems and prompting the public transportation may increase the traffic overflow. This kind of traffic overflow problem cannot be solved manually. Today the traffic data has been entered and erupted the time of huge transportation of the data. Hence it is important...
We propose a model of feature selection for offline handwriting recognition. The targeted area is recognition of Khmer handwritten text. We make use of correlation of features, two dimensional Fourier transformation and Gabor filters. We also pass the reduced data through a distance-based classifier to compare performance of each method. Feature selection is an important step towards improving recognition...
With its high-dimensional state and action space, large-scale multi-agent reinforcement learning (MARL) is a challenging problem. Centralized approximate RL is impractical to deal with this because the search cost grows exponentially with the number of agents. Further, traditional decentralized approaches require delicate model-specific decomposition and communication within multi-agent system (MAS)...
This is a set of research exploring using animation in the Massive Open Online Course (MOOC) / Small Private Online Course (SPOC) for learning information security. We established an Information Security SPOC course, with animations made of GoAnimate for learning. The course content was largely based on the standard of the Certified Information Systems Auditor (CISA) from Information Systems Audit...
Because of the challenge of collecting labelled training data, zero-shot learning (ZSL) which transfers semantic knowledge represented by category attributes from seen classes to recognize unseen classes has received a lot of attention recently. Existing methods assume that the source attributes are completely correct in zero-shot learning. However, the source attributes in practice may contain noise...
In recent years, multi-label classification problem has become a controversial issue. In this kind of classification, each sample is associated with a set of class labels. Ensemble approaches are supervised learning algorithms in which an operator takes a number of learning algorithms, namely base-level algorithms and combines their outcomes to make an estimation. The simplest form of ensemble learning...
A low-density spatial downlink reference signal (LDS-RS) design is proposed for frequency-division duplex (FDD) massive full-dimensional multiple-input multiple-output (FD-MIMO) systems. By exploiting the spatial correlation between the channels of different antennas, this scheme can efficiently reduce the downlink RS overhead and therefore enhances the achievable spectral efficiency significantly...
This paper proposes an object verification method by using sparse representation (SR) which has been applied for object representation and recognition. However, SR dictionary does not show sufficient compactness. Our method comprises three major modules. First, we train the sparse matrix by using boost K-Singular Value Decomposition (boost K-SVD) to obtain a sparse vector set. Second, we combine two...
Inferring scene depth from a single monocular image is an essential component in several computer vision applications such as 3D modeling and robotics. This process is an ill-posed problem. To tackle this challenging problem, previous efforts have been focusing on exploiting only global or local depth aware properties. We propose a model that incorporates both of them to obtain significantly more...
Aesthetic quality estimation of an image is a challenging task. In this paper, we introduce a deep CNN approach to tackle this problem. We adopt the sate-of-the-art object-recognition CNN as our baseline model, and adapt it for handling several high-level attributes. The networks capable of dealing with these high-level concepts are then fused by a learned logical connector for predicting the aesthetic...
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.