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.
Machine learning is widely used in various applications such as data mining, computer vision, and bioinformatics owing to the explosion of available data. However, in practice, many data have some missing attributes. The graphic theory serves as a powerful tool for modeling and analyzing many such practical problems, such as networks of communication and data organization. This paper focuses on semi-supervised...
Generating photo-realistic images from multiple style sketches is one of challenging tasks in image synthesis with important applications such as facial composite for suspects. While machine learning techniques have been applied for solving this problem, the requirement of collecting sketch and face photo image pairs would limit the use of the learned model for rendering sketches of different styles...
Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance...
Cross-resolution face recognition tackles the problem of matching face images with different resolutions. Although state-of-the-art convolutional neural network (CNN) based methods have reported promising performances on standard face recognition problems, such models cannot sufficiently describe images with resolution different from those seen during training, and thus cannot solve the above task...
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene. Particularly in indoor videos such as captured by robotic platforms or handheld and bodyworn RGBD cameras, nearby video frames provide diverse viewpoints...
Spectrum database plays an increasingly important role in spectrum measurements and monitoring, which lays foundations for accurate and real-time spectrum sensing in future cognitive radio networks. A successful identification of the channel propagation model is of great importance to construct spectrum database so as to give an accurate picture of spectrum use in real-world environments. In this...
The Taiwan Mandarin Radio Speech Corpus consists of roughly 300 (and growing) hours of audio recordings, selected from Taiwan's National Education Radio (NER) archive. The corpus includes speech from hundreds of speakers and various speech styles (spontaneous conversational and read news). This corpus provides a rich resource for research in speech and automatic speech recognition (ASR). In this paper,...
Predicting the gap between taxi demand and supply in taxi booking apps is completely new and important but challenging. However, manually mining gap rule for different conditions may become impractical because of massive and sparse taxi data. Existing works unilaterally consider demand or supply, used only few simple features and verified by little data, but not predict the gap value. Meanwhile, none...
In recent years, the use of license plate recognition technology in traffic monitor has attracted a lot of attention because it can be used in a smart city to do criminal investigation and traffic detection. License plate recognition technology has been widely used in parking lot management systems which has fixed shooting angle and lighting environments. The license plate recognition used in traffic...
Neural machine translation (NMT) has shown promising results and rapidly gained adoption in many large-scale settings. With the NMT model being widely used in empirical productions, its long-standing weakness in handling the rare and out of vocabulary words has been amplified a lot. In order to release the model from the stress of “understanding” the rare words, copy mechanism has been proposed to...
Multi-temporal PolSAR data is suitable for crops classification and growth monitoring. It is still difficult to establish a classifier with good robustness and high generation over a long temporal acquisition duration. This work aims to provide a solution to this task by exploring benefits from both the target scattering mechanism interpretation and the advanced deep learning. A polarimetric-feature-driven...
We propose a new pretreatment for pedestrian detection with convolutional networks. It is widely known that the phenomenon of overlapping feature distribution is common, which leads to overfitting problem. We present a method that divide one category that have overlapping distributed features into multi-subcategories. By this means smooth boundaries can be easily found to separate different subcategories,...
Domain adaptation (DA) aims to eliminate the difference between the distribution of labeled source domain on which a classifier is trained and that of unlabeled or partly labeled target domain to which the classifier is to be applied. Compared with the semi-supervised domain adaptation where some labeled data from target domain is utilized to help train the classifier, the unsupervised domain adaptation...
This research proposes a novel Bayesian sparse representation (BSR) method along with extracting facial parameters of SIFT to create sparse dictionaries, which are invariant to rotation, scale, and shift. By using K-means and information theory, a new dictionary called extended dictionary is developed. Compared with conventional orthogonal matching pursuit (OMP) algorithm, the proposed system that...
Recently, the synthesis of 3D dynamic expressions has become an important concern in computer graphics, facial recognition, etc. In this study, we propose a regression based joint subspace learning method for the automatic synthesis of 3D dynamic expression images. This method synthesizes 3D dynamic expression images from a single 2D facial image. We use two subspaces (the view subspace and the frame...
Feature point detection is an important pre-processing step for quantitative evaluation of facial paralysis. Since the conventional methods such as active shape model (ASM) or active appearance model (AAM) are trained by using normal face and they are not possible to detect the feature points accurately for the face with paralysis. In this paper, we propose an automatic and accurate feature point...
There are two important factors to improve the accuracy of the support vector machine(SVM) classifier. First, selected training samples should uniquely represent each class. Second, SVM training parameters which are pre-defined by the user should be suitable for training samples to obtain satisfied results of the SVM classifier. The proposed method of this paper presents a technique to adjust the...
Single-image super-resolution is an important technique for high resolution display related applications. Example learning-based approaches can provide plenty of image details by using trained dataset. The regression based methods reduce the memory storage size by training mapping functions rather than using a huge dictionary. However, the speed of searching the nearest cluster for the desired mapping...
Active Shape Model (ASM) is considered as a high level image processing algorithm. Typical applications include image segmentation and interpretation. A major challenge in ASMs is to repeatedly move model points towards true boundaries. It is a crucial step in the algorithm which fails in cases of low contrast images. In this paper, we present a new search algorithm for ASM to tackle segmentation...
In this paper, a new method based on deep learning for robotics autonomous navigation is presented. Different from the most traditional methods based on fixed models, a convolutional neural network (CNN) modelling technique in Deep learning is selected to extract the feature inspired by the working pattern of the biological brain. This neural network model has muti-layer features where the ambient...
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.