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.
To support code migration, we introduce JV2CS, a tool to generate asequence of C# API elements and related control units that are neededto migrate a given Java code fragment. First, we mine the mappingsbetween single APIs in Java and C#. To overcome the lexical mismatchbetween the names of Java and C# APIs, we represent an API by itsusages instead of its name. To characterize an API with its contextconsisting...
Word embeddings are a low-dimensional vector representation of words that incorporates context. TWo popular methods are word2vec and global vectors (GloVe). Word2vec is a single-hidden layer feedforward neural network (SLFN) that has an auto-encoder influence for computing a word context matrix using backpropagation for training. GloVe computes the word context matrix first then performs matrix factorization...
Impulse noise corruption in digital images frequently occurs because of errors generated in noisy sensors or communication channels, such as faulty memory locations in devices, malfunctioning pixels within the camera, and bit errors in transmission. Although the recently developed big data streaming enhances the viability of video communication, visual distortions in images that are caused by impulse...
This paper addresses the estimation of pairwise supervoxel correspondences toward automatic semi-dense medical image registration. Supervoxel matching is performed through random forests (RF) with supervoxel indexes as label entities to predict matching areas in another target image. Ensuring accurate supervoxel boundary adherence requires a fine supervoxel decomposition which highly increases learning...
Detection and segmentation of small renal mass (SRM) in renal CT images are important pre-processing for computer-aided diagnosis of renal cancer. However, the task is known to be challenging due to its variety of size, shape, and location. In this paper, we propose an automated method for detecting and segmenting SRM in contrast-enhanced CT images using texture and context feature classification...
New pedagogical methods delivered through mobile mixed reality (via a user-supplied mobile phone incorporating 3d printing and augmented reality) are becoming possible in distance education, shifting pedagogy from 2D images, words and videos to interactive simulations and immersive mobile skill training environments. This paper presents insights from the implementation and testing of a mobile mixed...
Difficulty on collecting annotated medical images leads to lack of enough supervision and makes discrimination tasks challenging. However, raw data, e.g., spatial context information from 3D CT images, even without annotation, may contain rich useful information. In this paper, we exploit spatial context information as a source of supervision to solve discrimination tasks for fine-grained body part...
Online social media has changed the way of interacting among users, nowadays, is used as a tool for expressing polarized opinions related to a global or specific context. Valuable information can be gathered in real-time basis and can help to determine if such data has a social impact on users represented as comfort or discomfort on a political domain. Analyzing data related to political domains like...
Over the past decade, major advancements in software development have occurred in the global context. Global software development (GSD) is an effective strategy, and many higher educational institutions have been offering GSD courses. These courses are usually organized together with another institution situated in a different location. However, conducting such a course with more than one institution...
The software architecture is usually the first design artifact that addresses quality issues (e.g., performance, security). Also, the architecture is reference point for other development activities, e.g., coding and maintenance. Based on our experience teaching software engineering and architecture at different institutions and levels, we discuss what makes teaching software architecture difficult,...
This paper studies the influence factor on HMM-based Tibetan Lhasa speech synthesis. In order to find the key factor which makes the most contribution to improve the synthesized Tibetan Lhasa speech, we synthesize Tibetan Lhasa speech by different context labeling and different number of training sentences with different speech synthesis unit, respectively. We build two Tibetan Lhasa speech corpora...
Automatic drum transcription methods aim at extracting a symbolic representation of notes played by a drum kit in audio recordings. For automatic music analysis, this task is of particular interest as such a transcript can be used to extract high level information about the piece, e.g., tempo, downbeat positions, meter, and genre cues. In this work, an approach to transcribe drums from polyphonic...
The last decade of John Cozzens's tenure at the NSF witnessed the advent of theory and methods at the heart of modern data science. These advances include (but are not limited to) compressed sensing, sparse coding, inference methods robust to outliers and missing data, and convex optimization tools that facilitate a host of novel inference methods. This paper describes how these methods evolved from...
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not possible. In this paper we propose a residual memory neural network (RMN) architecture...
Adding context information into recurrent neural network language models (RNNLMs) have been investigated recently to improve the effectiveness of learning RNNLM. Conventionally, a fast approximate topic representation for a block of words was proposed by using corpus-based topic distribution of word incorporating latent Dirichlet allocation (LDA) model. It is then updated for each subsequent word...
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog...
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 target improving the accuracy of acoustic modelling for statistical parametric speech synthesis (SPSS) and introduce the convolutional neural network (CNN) due to its powerful capacity in locality modelling. A novel model architecture combining unidirectional long short-term memory (LSTM) and a time-domain convolutional output layer (COL) is proposed and employed to acoustic modelling...
This paper deals with the separation of music into individual instrument tracks which is known to be a challenging problem. We describe two different deep neural network architectures for this task, a feed-forward and a recurrent one, and show that each of them yields themselves state-of-the art results on the SiSEC DSD100 dataset. For the recurrent network, we use data augmentation during training...
The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which shows that a significant improvement can be achieved by combining different existing heterogeneous models in a single architecture. This is done through 1) a feature...
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.