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.
The Internet of Things (IoT) has penetrated various domains, from smart grids to precision agriculture, facilitating remote sensing and control. However, IoT devices are target to a spectrum of reliability and security issues. Therefore, capturing the normal behavior of these devices and detecting abnormalities in program execution is key for reliable deployment. However, existing program anomaly...
The motivation behind the research on overlapping speech has always been dominated by the need to model human-machine interaction for dialog systems and conversation analysis. To have more complex insights of the interlocutors' intentions behind the interaction, we need to understand the type of overlaps. Overlapping speech signals the interlocutor's intention to grab the floor. This act could be...
Group activity recognition from videos is a very challenging problem that has barely been addressed. We propose an activity recognition method using group context. In order to encode both single-person description and two-person interactions, we learn mappings from highdimensional feature spaces to low-dimensional dictionaries. In particular the proposed two-person descriptor takes into account geometric...
This paper proposes CPERS, a contextual and personalized event recommender system that exploits overall user preference and context influences to produce recommendations in event-based social networks (EBSNs). Diversely from items in traditional recommendation scenarios (e.g. movies, songs), events in EBSNs are only valid for a short period of time, having no explicit feedback. Therefore the event...
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,...
This paper presents a data-driven approach towards the modeling of agent behaviors in a full-fledged, commercial off-the-shelf simulation milieu for tactical military training. The modeling approach employs machine learning to identify behavioral rules and patterns in data. Potential advantages of this approach are that it may improve modeling efficiency and, perhaps more importantly, increase the...
The MapReduce framework is being increasingly used in the scientific computing and image/video processing fields. Relevant research has tailored it for the field's specificities but there are still overwhelming limitations when it comes to temporal locality-sensitive computations. The performance of this class of computations is closely tied to an efficient use of the memory hierarchy, concern that...
Fine-scale classification in form of object extraction or segmentation for high resolution SAR images is a challenging task due to the existing local noises, object deformation and part missing. A novel SAR classification method based on CRFs which combines low-level features, label context and object structure priors is presented in this paper. Local label pattern is proposed in this paper to model...
In machine learning, an information-theory optimal way to filter the best input features, without reference to any specific machine learning models, consists of maximizing the mutual information between the selected features and the model output, a choice which will minimize the uncertainty in the output to be predicted, given the feature values.
Existing joint models of deep Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs) face two problems for object segmentation: 1) CNNs can hardly extract high level features; 2) fully connected layers of CNNs are lack of capability of dealing with structured multi-level features. To address these problems, we utilize a Structured Random Forests based border ownership detection...
This research aims to exploring the new research of personalized information access in the context of the online retailing. In this paper, we present PERSO-Retailer Modeler, the first stage in this line of research. We propose to add a new level of personalization in the Content Management System (CMS) application by not only creating an e-commerce website to run the retailer's business but by recommending...
Difficulties can arise from the segmentation of three-dimensional objects formed by multiple non-rigid parts represented in two-dimensional images. Problems involving parts whose spatial arrangement is subject to weak restrictions, and whose appearance and form change across images, can be particularly challenging. Segmentation methods that take into account spatial context information have addressed...
Structured data extracted from the Web is highly heterogeneous due to its disparate origins and nature. There exist some techniques to integrate this information based on the extraction of synonymy relationships among the different entities involved. However, synonymy is a very strict and therefore uncommon relationship. We present a novel approach for the discovery of subsumption relationships among...
Language vector space models (VSMs) have recently proven to be effective across a variety of tasks. In VSMs, each word in a corpus is represented as a real-valued vector. These vectors can be used as features in many applications in machine learning and natural language processing. In this paper, we study the effect of vector space representations in cyber security. In particular, we consider a passive...
Video annotation is a kind of "high-level feature extraction" or "semantic concept detection", which is a promising approach to bridging semantic gap between low-level features and user descriptions. In this paper we propose a two layer video annotation scheme based on video structure and the visual context information through the video clips. To improve the retrieval performance...
Detecting abnormal events in video sequences is a challenging task that has been broadly investigated over the last decade. The main challenges come from the lack of a clear definition of abnormality and from the scarcity, often absence, of abnormal training samples. To address these two shortages, the computer vision community made use of generative models to learn normal behavioral patterns in videos...
This work combines model-based local shape analysis and data-driven local contextual feature learning for improved detection of pulmonary nodules in low dose computed tomography (LDCT) chest scans. We reduce orientation-induced appearance variability by performing intensity-weighted principal component analysis (PCA) to estimate the local orientation at each candidate location. Random comparison primitives...
Top down image semantics play a major role in predicting where people more attend in images. In the state of computational models of human visual attention incorporate high level object detections signifying top down image semantics in a separate channel along with other bottom up saliency channels. The different occurrences of objects in a scene also to attract our attention and this interaction...
In this paper, we present a new shape-based system for person re-identification. The silhouette shape is represented by a Point Distribution Model (PDM) aligned on the body. We improve a fitting model which iteratively adjusts the shape by maximizing a boosted score of local features: the "Boosted Deformable Model". We modify the training procedure with a ranking structure to find how the...
Structured knowledge bases are an increasingly important way for storing and retrieving information. Within such knowledge bases, an important search task is finding similar entities based on one or more example entities. We present QBEES, a novel framework for defining entity similarity based only on structural features, so-called aspects, of the entities, that naturally model potential interest...
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.