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 order to meet the needs of China higher education of training students with strong foundation ability and innovation in the filed computer science, in recent years, the computer basic teaching team of Beijing Jiaotong University has carried out a series of scientific and effective educational reforms research and practice: 1. Carrying out “MOOC + SPOC + Flipped classroom” practice; 2. Construction...
In Acoustic Scene Classification (ASC) two major approaches have been followed. While one utilizes engineered features such as mel-frequency-cepstral-coefficients (MFCCs), the other uses learned features that are the outcome of an optimization algorithm. I-vectors are the result of a modeling technique that usually takes engineered features as input. It has been shown that standard MFCCs extracted...
Video capturing using Unmanned Aerial Vehicles provides cinematographers with impressive shots but requires very adept handling of both the drone and the camera. Deep Learning techniques can be utilized in this process to facilitate the video shooting process by allowing the drone to analyze its input and make intelligent decisions regarding its flight path. Fast and accurate on-board face detection...
In this paper a novel human crowd detection method, that utilizes deep Convolutional Neural Networks (CNN), for drone flight safety purposes is proposed. The aim of our work is to provide light architectures, as imposed by the computational restrictions of the application, that can effectively distinguish between crowded and non-crowded scenes, captured from drones, and provide crowd heatmaps that...
With the increasing use of unmanned aerial vehicles (UAVs) by consumers, automatic UAV detection systems have become increasingly important for security services. In such a system, video imagery is a core modality for the detection task, because it can cover large areas and is very cost-effective to acquire. Many detection systems consist of two parts: flying object detection and subsequent object...
This paper presents a case study based on the experience of implementing a blended learning (BL) approach by SPOC to a Computer General course for all the first year undergraduates in China University of Geosciences (Beijing). It introduces ubiquitous learning environment (ULE), teaching preparation for student-centered learning, and teaching practice of the BL. The study shows that BL approach has...
Vocal Tract Length Normalization (VTLN) is a very important speaker normalization technique for speech recognition tasks. In this paper, we propose the use of Gaussian posteriorgram of VTLN-warped spectral features for a Query-by-Example Spoken Term Detection (QbE-STD). This paper presents the use of a Gaussian Mixture Model (GMM) framework for estimation of VTLN warping factor. This GMM framework...
Customer reviews, a.k.a. word-of-mouth reviews, have been important resources of information for text mining. They naturally include both positive and negative opinions on the products or services, as well as neutral observations helpful for everyone who is about to purchase the products or about to decide what to do with the product or the service. Among many customer reviews, we focus on cosmetic...
Deep convolutional neural network have led to a series of breakthroughs for computer vision task. The success of convolutional neural networks (CNNs) is attributed to their ability to learn rich image representations. However, mid-level representations (features) learned by hidden layers, which contains rich discriminative information, are not directly used for downstream tasks. In this paper, we...
In this paper, we study the model of human trust where an operator controls a robotic swarm remotely for a search mission. Existing trust models in human-in-the-loop systems are based on task performance of robots. However, we find that humans tend to make their decisions based on physical characteristics of the swarm rather than its performance since task performance of swarms is not clearly perceivable...
Recommender systems are becoming the crystal ball of the Internet because they can anticipate what the users may want, even before the users know they want it. However, the machine-learning algorithms typically involved in the training of such systems can be computationally expensive, and often may require several days for retraining. Here, we present a distributed approach for load-balancing the...
The proliferation of big data and big computing boosted the adoption of machine learning across many application domains. Several distributed machine learning platforms emerged recently. We investigate the architectural design of these distributed machine learning platforms, as the design decisions inevitably affect the performance, scalability, and availability of those platforms. We study Spark...
Distributed representations have become the de facto standard by which many modern neural network architectures deal with natural language processing tasks. In particular, the word2vec algorithm introduced by Mikolov, et al. popularized the use of distributed representations by demonstrating that learned embeddings capture semantic relationships geometrically. Though word2vec addresses some of the...
In the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training...
Ozonation is one of the most important processes during drinking water treatment. To improve the efficiency of ozonation and to stabilize the quality of the treated water, the ozone dosage should be a good trade-off between the requirement of disinfection and the restriction of bromate formation. However, because of the changes of raw water quality and the nonlinear behavior of ozonation process,...
Representation Learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low dimensional space. There exits two kinds of representation methods for entities in Knowledge Graphs (KGs), including structure-based representation and description-based representation. Most methods represent entities with fact triples of KGs through translating embedding models, which...
CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset to a (typically smaller) target dataset. This is usually accomplished through fine-tuning a fixed-size network on new target data. Indeed, virtually every contemporary...
Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image Super-Resolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input image to the high-resolution target image, at the cost of requiring enormous parameters. This paper proposes a very deep CNN model (up to 52 convolutional...
This paper proposes a method for generative learning of hierarchical random field models. The resulting model, which we call the hierarchical sparse FRAME (Filters, Random field, And Maximum Entropy) model, is a generalization of the original sparse FRAME model by decomposing it into multiple parts that are allowed to shift their locations, scales and rotations, so that the resulting model becomes...
Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information...
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.