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.
Deep visual attention in computer vision has attracted much attention over the past years, which achieves great contributions especially in image classification, image caption and action recognition. However, due to taking BP training wholly or partially, they can not show the true power of attention in computational efficiency and focusing accuracy. Our intuition is that attention mechanism should...
In this work we apply a fully differentiable Recurrent Model of Visual Attention to unconstrained real-world images. We propose a deep recurrent attention model and show that it can successfully learn to jointly localize and classify objects. We evaluate our model on multiple digit images generated from MNIST data, Google Street View images, and a fine-grained recognition dataset of 200 bird species,...
In this paper, we propose a novel method of label propagation for one-class learning. For binary (positive/negative) classification, the proposed method simultaneously measures the pair-wise similarity between samples and the negativity at every sample based on a cone-based model of local neighborhoods. Relying only on positive labeled samples as in one-class learning, the method estimates the labels...
This paper deals with an estimation of the Remaining Useful Life of bearings based on the utilization of the Wavelet Packet Decomposition (WPD) and the Mixture of Gaussians Hidden Markov Models (MoG-HMM). The raw data provided by the sensors are first processed to extract features by using the wavelet packet decomposition. This latter provides a more flexible way of time-frequency representation and...
Incorporating annotators' knowledge into a machine-learning framework for detecting psychological traits using multimodal data is an open issue in human communication and social computing. We present a model that is designed to exploit the subjective judgements of multiple annotators on a social trait labeling task. Our two-stage model first estimates a ground truth by modeling the annotators using...
Inspired by the primate visual system, computational saliency models decompose the visual input into a set of feature maps across spatial scales. In the standard approach, the feature maps of the pre-specified channels are summed to yield the final saliency map. We study the feature integration problem and propose two improved strategies: first, we learn a weighted linear combination of features using...
In this paper, we propose a new segmentation algorithm that combines a graph-based shape model with image cues based on boosted features. The landmark-based shape model encodes prior constraints through the normalized Euclidean distances between pairs of control points, alleviating the need of a large database for the training. Moreover, the graph topology is deduced from the dataset using manifold...
Detecting anomalous traffic on the Internet has remained an issue of concern for the community of security researchers over the years. Advances in computing performance, in terms of processing power and storage, have allowed the use of resource-intensive intelligent algorithms, to detect intrusive activities, in a timely manner. Naïve Bayes is a statistical inference learning algorithm with promise...
Wu and coworkers introduced an active basis model (ABM) for detecting generic objects in static images. A grey-value local power spectrum was utilized to find a common template and deformable templates from a set of training images and to detect an object in unknown images by template matching. In this paper, we propose a color-based active basis model (color-based ABM for short) which includes color...
A new 3D object retrieval approach is proposed based on a novel Bayesian networks lightfield descriptor (BLD). To overcome the disadvantages of the existing 3D object retrieval methods, firstly, we explore Bayesian network for building a new lightfield descriptor, 3D object is put into lightfield, and multi-views information can be obtained along a sphere, and then features of images can be extracted...
In this paper we present a computational model for incremental word meaning acquisition. It is designed to rapidly build category representations which correspond to the meaning of words. In contrast to existing approaches, our model further extracts word meaning-relevant features using a statistical learning technique. Both category learning and feature extraction are performed simultaneously. To...
We present a novel learning-based image restoration and enhancement technique for improving character recognition performance of OCR products for degraded documents or documents/text captured with mobile devices such as camera-phones. The proposed technique is language independent and can simultaneously increase the effective resolution and restore broken characters with artifacts due to image capturing...
Archetypal analysis (AA) proposed by Cutler and Breiman in estimates the principal convex hull of a data set. As such AA favors features that constitute representative 'corners' of the data, i.e. distinct aspects or archetypes. We will show that AA enjoys the interpretability of clustering - without being limited to hard assignment and the uniqueness of SVD - without being limited to orthogonal representations...
In this paper we propose a methodology for improving the accuracy of models that predict self-reported player pairwise preferences. Our approach extends neuro-evolutionary preference learning by embedding a player modeling module for the prediction of player preferences. Player types are identified using self-organization and feed the preference learner. Our experiments on a dataset derived from a...
A biologically-inspired top-down learning model based on visual attention is proposed in this paper. Low-level visual features are extracted from learning object itself and do not depend on the background information. All the features are expressed as a feature vector, which is looked as a random variable following a normal distribution. So every learning object is represented as the mean and standard...
Recently, bag of words (BoW) model has led to many significant results in visual object classification. However, due to the limited descriptive and discriminative ability of visual words, the resulting performance of visual object classification is still incomparable to its analogy in text domain, i.e. document categorization. Furthermore, for weakly labeled image data, where we only know whether...
The volatility of crude oil market and its chain effects to the world economy augmented the interest and fear of individuals, public and private sectors. Previous statistical and econometric techniques used for prediction, offer good results when dealing with linear data. Nevertheless, crude oil price series deal with high nonlinearity and irregular events. The continuous usage of statistical and...
Bio-inspired computer vision is an emerging field. It aims to reproduce the capabilities of biological vision systems, eventually to simulate the visual functions for various purposes. In this paper, we propose a bio-inspired computer visual system using Graphical Processing Unit (GPU), and its application on breast cancer prognosis. The system extracts visual features from an input image using a...
Hybrid learning can reduce the computational complexity of incremental algorithms for Bayesian network structures significantly. In this paper, a group of hybrid incremental algorithms are proposed. The central idea of these algorithms is to use the polynomial-time constraint-based technique to build a candidate parent set for each domain variable, followed by the hill climbing search procedure to...
Attention and recognition have been addressed separately as two challenging computational vision problems, but an engineering-grade solution to their integration and interaction is still open. Inspired by the brain's dorsal and ventral pathways in cortical visual processing, we present a neuromorphic architecture, called Where-What Network 2 (WWN-2), to integrate object attention and recognition interactively...
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.