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.
Because unprecedented volumes of multimedia data associated with spoken documents have been made available to the public, spoken document retrieval (SDR) has become an important research area in the past decades. Recently, representation learning has emerged as an active research topic in many machine learning applications owing largely to its excellent performance. In the context of natural language...
While recent advances in deep neural networks have lead to significant improvements in speech recognition, they have been applied mainly to acoustic and language modeling. We instead apply the models to bottleneck feature extraction. Several DNN, CNN, and BLSTM-based bottleneck feature networks are compared using both DNN and BLSTM acoustic models. Multiple variations in network architecture and feature...
Supervised speech separation algorithms seldom utilize output patterns. This study proposes a novel recurrent deep stacking approach for time-frequency masking based speech separation, where the output context is explicitly employed to improve the accuracy of mask estimation. The key idea is to incorporate the estimated masks of several previous frames as additional inputs to better estimate the mask...
Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs need to consider longer history of tokens to properly predict the next one. We address this problem by proposing hierarchical RNN architectures, which...
Behavioral annotation using signal processing and machine learning is highly dependent on training data and manual annotations of behavioral labels. Previous studies have shown that speech information encodes significant behavioral information and be used in a variety of automated behavior recognition tasks. However, extracting behavior information from speech is still a difficult task due to the...
Automatic transcriptions of consumer generated multi-media content such as “Youtube” videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap hardware and a focus on the visual modality, and may have been post-processed or edited.
At University level, particularly in Engineering fields, the academe shows significant enthusiasm for the development of various competencies concerning entrepreneurship and innovation, focusing on the promotion of opportunities and the strengthening of the existing connection between the University and the Software Industry. One of the main challenges in Engineering is finding a proper answer to...
Recently it has been noticed an increased number of cyber-incidents, sometimes causing seriously impact to organizations and governments. Cyberattacks exploits a variety of technological and social vulnerabilities to achieve a malicious objective. The emergence of new and sophisticated Cyberthreats demand very skilled operators with a solid knowledge about concepts and technologies related to Cybersecurity...
Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of improving significantly logo detection performance when only a handful of (e.g., 10) labelled training images captured in realistic context are available, avoiding...
This paper investigates the problem of recognizing activities and dynamic ad-hoc collaboration involving multiple users. Thus, we consider people performing various predominantly physical, compound activities in a smart environment (which includes personal/wearable devices). In this case, being “compound” means that the activity can be decomposed into primitive (atomic) actions that are executed by...
We propose a Convolutional Neural Network (CNN) based algorithm – StuffNet – for object detection. In addition to the standard convolutional features trained for region proposal and object detection [33], StuffNet uses convolutional features trained for segmentation of objects and 'stuff' (amorphous categories such as ground and water). Through experiments on Pascal VOC 2010, we show the importance...
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such...
The growing use of informal social text messages on Twitter is one of the known sources of big data. These type of messages are noisy and frequently rife with acronyms, slangs, grammatical errors and non-standard words causing grief for natural language processing (NLP) techniques. In this study, our contribution is to target non-standard words in the short text and propose a method to which the given...
Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements and 2) the localization and classification of actions have to be performed even before they are fully observed. We propose a new random forest (RF)-based online action detection framework that addresses these challenges. Our...
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...
Software project artifacts such as source code, requirements, and change logs represent a gold-mine of actionable information. As a result, software analytic solutions have been developed to mine repositories and answer questions such as "who is the expert?,'' "which classes are fault prone?,'' or even "who are the domain experts for these fault-prone classes?'' Analytics often require...
Human-centered Internet-of-Things (IoT) applications utilize computational algorithms such as machine learning and signal processing techniques to infer knowledge about important events such as physical activities and medical complications. The inference is typically based on data collected with wearable sensors or those embedded in the environment. A major obstacle in large-scale utilization of these...
Detecting actions or verbs in still images is a challenging problem for a variety of reasons such as the absence of temporal information and polysemy of verbs which lead to difficulty in generating large verb datasets. In this paper, we propose to first detect the prominent objects in the image and then infer the relevant actions or verbs using Natural Language Processing (NLP)-based techniques. The...
Instruction detection technology is a new generation of security technology that monitor networks or systems to avoid malicious activity and policy violation. Compared with traditional security protection measures such as firewall, instruction detection can prevent attacks both from external and internal. The SVM is a statistical learning model(SLT), which shows an extraordinary advantage when dealing...
In this paper, we present a heuristic for labeling a given term a taxonomy label. Specifically, for a given term, our goal is to construct a model for determining an "is-a" relationship between the given term and an inferred concept. Such term-labelling problem is not new, but the existing solutions require semi-supervised training processing, e.g., supervised LDA, or rely on lexicographers,...
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.