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.
In this paper, we propose a method to classify K-pop dance based on motion data obtained from Kinect V2 for research of motion classification and development of anti-plagiarism system. To do this, 200-point dances of K-pop are acquired. Dance motions from 40 amateur dancers are acquired to construct a total of 400 data. The proposed classification method consists of three steps. First, we obtain 13...
At present, machine learning is widely used for classification, such as automatic speech recognition, image identification, text classification and numbers of researches for fault diagnosis besides. Generally, most of the models used for fault diagnosis are based on the same data distribution, while the applications of the equipment in actual production and operation are mostly under unstable conditions,...
This paper presents the results of systematic and comparative experimentation with major types of methodologies for automatic duplicate question detection when these are applied to datasets of progressively larger sizes, thus allowing to study the learning profiles of this task under these different approaches and evaluate their merits. This study was made possible by resorting to the recent release...
In machine learning applications, there are scenarios of having no labeled training data, due to the data being rare or too expensive to obtain. In these cases, it is desirable to use readily available labeled data, that is similar to, but not the same as, the domain application of interest. Transfer learning algorithms are used to build high-performance classifiers, when the training data has different...
In this paper we propose a cluster based version of the anomaly detection methodology based on signal reconstruction, using Auto Associative Kernel Regression (AAKR), combined with residuals analysis, using Sequential Probability Ratio Test (SPRT). We demonstrate how the proposed cluster based methodology can be successfully applied for anomaly detection on a marine diesel engine in operation. Furthermore,...
To quickly and efficiently analyze a large-scale environment by the camera with limited field-of-view, intelligent systems should sequentially select the optimal field-of-view to observe important and informative parts of area. Especially in the image retrieval tasks, small observations could be sequentially selected to improve the performance of image retrieval with less computational costs than...
Traffic anomaly detection is primarily concerned with identifying malicious traffic patterns in a much larger stream of benign traffic. Traditionally, this is achieved by selecting a very specialized set of traffic-based features that are used for both training a model, as well as for detection at runtime. This paper introduces a novel method of anomaly detection that breaks the assumption that the...
Radio tomographic imaging (RTI) is an emerging technique of device-free localization (DFL). The main challenge of RTI is the multipath interferences in RSS measurements, which could make the links become more unpredictable and finally lead to unsatisfactory DFL performance. For addressing this challenge, this paper presents a novel modeling method based on relevance vector machine (RVM), which can...
To make full use of the data information and improve the classification performance, a new evidential neural network classifier is proposed and a novel implementation of multiple classifier systems based on the new evidential neural network classifier is presented in this paper. The ambiguous data contained in the training data is considered as a new class — compound class and the training data is...
In this paper, we address the problem of estimating the total flow of a crowd of pedestrians from spatially limited observations. Our approach relies on identifying a dynamical system regime that characterizes the observed flow in a limited spatial domain by solving for the modes and eigenvalues of the corresponding Koopman operator. We develop a framework where we first approximate the Koopman operator...
This work is about recognizing human activities occurring in videos at distinct semantic levels, including individual actions, interactions, and group activities. The recognition is realized using a two-level hierarchy of Long Short-Term Memory (LSTM) networks, forming a feed-forward deep architecture, which can be trained end-to-end. In comparison with existing architectures of LSTMs, we make two...
We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data such that an attribute of a synthesized sample is at a desired value or strength. This is particularly interesting in situations where little data with no attribute...
In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process, data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far,...
Zero-shot learning (ZSL) aims to recognize objects of unseen classes with available training data from another set of seen classes. Existing solutions are focused on exploring knowledge transfer via an intermediate semantic embedding (e.g., attributes) shared between seen and unseen classes. In this paper, we propose a novel projection framework based on matrix tri-factorization with manifold regularizations...
Compositionality and contextuality are key building blocks of intelligence. They allow us to compose known concepts to generate new and complex ones. However, traditional learning methods do not model both these properties and require copious amounts of labeled data to learn new concepts. A large fraction of existing techniques, e.g., using late fusion, compose concepts but fail to model contextuality...
Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the number of cameras are fixed in a network. Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may...
A class of recent approaches for generating images, called Generative Adversarial Networks (GAN), have been used to generate impressively realistic images of objects, bedrooms, handwritten digits and a variety of other image modalities. However, typical GAN-based approaches require large amounts of training data to capture the diversity across the image modality. In this paper, we propose DeLiGAN...
This paper presents a new pruning extreme learning machine (N-PELM) algorithm which can generate a compact single-hidden-layer neural network (SLNN) by automatically pruning the number of hidden nodes while keep high accuracy. The proposed N-PELM algorithm initializes a SLNN by using extreme learning machine (ELM) algorithm given superfluous number of hidden nodes. The following part consists of two...
The research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high performance descriptor in Euclidean space via the Convolutional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strategy which enables the network to access billions of training...
We approach the problem of fast detection and recognition of a large number (thousands) of object categories while training on a very limited amount of examples, usually one per category. Examples of this task include: (i) detection of retail products, where we have only one studio image of each product available for training, (ii) detection of brand logos, and (iii) detection of 3D objects and their...
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.