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 Convolutional Neural Networks (CNNs) achieve substantial improvements in face detection in the wild. Classical CNN-based face detection methods simply stack successive layers of filters where an input sample should pass through all layers before reaching a face/non-face decision. Inspired by the fact that for face detection, filters in deeper layers can discriminate between difficult face/non-face...
Online reviews play a crucial role in helping consumers to make purchase decisions. However, a severe problem Internet Water Army (a large amount of paid posters who write inauthentic reviews) emerge in many E-commerce websites recently which dramatically undermines the value of user reviews. Although the word Internet Water Army originated from China, some other countries also suffered from this...
Patch-based face hallucination algorithms utilize either local patches (e.g., position-patch approaches) or nonlocal patches (e.g., dictionary-learning approaches) to exploit self-similarity prior from training samples. Although they yield decent results, solo source patches limit their performance due to not fully taking self-similarity prior from both local and nonlocal ones. In order to overcome...
This paper presents a system for performance-driven avatar animation by estimating facial pose and expression parameters from single image. In this system, a 3D shape prediction model is trained based on local binary feature (LBF) algorithm, which use random forest to extract image features and learns a linear regression model mapping these features to 3D shape. With the help of this model, the 3D...
Tooth segmentation on dental model is an essential step of computer-aided-design systems for orthodontic virtual treatment planning. However, efficiently identifying cutting boundary to separate tooth from dental model still remains a challenge, due to various geometrical shapes of teeth, complex tooth arrangements and varying degrees of crowding problem. Most segmentation approaches presented before...
Providing accurate information about human's state, activity is one of the most important elements in Ubiquitous Computing. Various applications can be enabled if one's state, activity can be recognized. Due to the low deployment cost, non-intrusive sensing nature, Wi-Fi based activity recognition has become a promising, emerging research area. In this paper, we survey the state-of-the-art of the...
This paper proposes a novel approach to voice conversion with non-parallel training data. The idea is to bridge between speakers by means of Phonetic PosteriorGrams (PPGs) obtained from a speaker-independent automatic speech recognition (SI-ASR) system. It is assumed that these PPGs can represent articulation of speech sounds in a speaker-normalized space and correspond to spoken content speaker-independently...
Extracting opinion words and opinion targets from online reviews is an important task for fine-grained opinion mining. Usually, traditional extraction methods under the pipeline-based framework have higher precision but lower recall, while methods in the propagation-based framework possess greater recall but poorer precision. To achieve better performance both in precision and recall, this paper proposes...
While e-commerce has grown substantially over last several years, more and more people are utilizing this popular channel to purchase products and services. Thus the ability to predict user demographics, including gender, age and location has important applications in advertising, personalization, and recommendation. In this paper, we aim to automatically predict the users' genders based on their...
Extracting opinion words and targets is a main task in opinion mining. This paper proposes a novel approach with a dynamic process of joint propagation and refinement. In the propagation process, two initial datasets of opinion words and targets are separately obtained by given seed words and seed dependency patterns under the pre-defined extraction rules, and meanwhile new dependency patterns are...
In recent years, with the prevailing usage of web data repository over emergency field, extracting the web data plays an important role in tracking the evolution of event. With huge and still growing web data, an important task is to track emergency event evolution and analyze its latent events or topics over time. Unfortunately, emergency events are inherently with uncertainty because the complexity...
In recent years, with the improvement of sensor technologies, the volumes of remote sensing data are increased dramatically. The feature extraction of hyper spectral remotely sensed images can reduce such high-dimensional datasets, solve the big data problem, avoid the Hughes phenomena and improve the classification performance. Accordingly, this paper presents a framework for feature extraction of...
Among all the feature matching algorithms, SURF is famous for its computation efficiency in lots of practical applications. For recently popular stereoscopic videos, sparse feature matching, in which SURF is usually adopted, is the pre-processing of adjusting the 3D effect. However, significant improvement still can be made for SURF in stereo images. In this paper, a new two-layer feature descriptor...
For the wavelet transform has limitations in extract features of the edge of images, a method of the facial expression recognition is proposed that using curvelet transform to extract features of the edge of images. The curvelet transform can get more representation of sparse images than the wavelet transform on the representation of the singular of the edges of image curve. The curvelet coefficient...
Surveying a large amount of small sub-kilometer craters in planetary images is a challenging task due to their non-distinguishable features. In this paper, we integrate the LASSO (Least Absolute Shrinkage and Selection Operator) method with the Bayesian network classifier and propose an L1 Regularized Bayesian Network Classifier (L1-BNC) algorithm for this task. The L1-BNC algorithm uses the LASSO...
In this paper, we study a new research problem of causal discovery from streaming features. A unique characteristic of streaming features is that not all features can be available before learning begins. Feature generation and selection often have to be interleaved. Managing streaming features has been extensively studied in classification, but little attention has been paid to the problem of causal...
A novel feature extraction algorithm of Inverse Synthetic Aperture Radar (ISAR) image based on wavelet transform (WT) and multi-scale block local binary pattern (MB-LBP) is proposed in this paper. Firstly, the mathematical morphology method is adopted to enhance ISAR image. Secondly, 2D wavelet transform is used to get the low frequency sub-band image from the enhancement ISAR image. Then, ISAR image...
In this paper, focused on three targets with simple structure, such as cone, sphere and cone, cylinder and cone, dynamic RCS echo signals is predicted with the improved Greco software. The Dynamic RCS echo signals of targets with micro-movement are preprocessed by using short time Fourier transform, and high-resolution time-frequency distribution images are obtained. A new radar target recognition...
In this paper, we propose an intelligent system to help people create customized icons on touch sensitive mobile devices. Users can create their own icons from one or multiple drawings in an intelligent and interactive way. The system could automatically combine several hand-drawn sketches or drawings to create new complex icons. We also provide one recommendation function to assist the creation process...
Video surveillance usually requires multiple cameras to monitor objects of interest, such as people. However, different appearances acquired from different cameras of the same people often make the construction of a robust individualized appearance model very challenging. In this paper, we present a kernel-based method that maps the bag-of-feature based image features to a hierarchical representation...
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.