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.
We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator’s action. After training, the original operator need not be run at all. The trained network operates at full resolution and runs in constant time. We investigate the effect of network architecture on...
Data diversity in terms of types, styles, as well as radiometric, exposure and texture conditions widely exists in training and test data of vision applications. However, learning in traditional neural networks (NNs) only tries to find a model with fixed parameters that optimize the average behavior over all inputs, without using data-specific properties. In this paper, we develop a meta-level NN...
The strong abilities of deep learning models have been shown in the area of text detection in natural scene images. In this paper, we introduce a new method called deep metric learning for scene text detection. We use the triplet loss [1] to replace the traditional loss function (Softmax) and learn a mapping from image regions to a compact Euclidean space where distances correspond to a measure of...
The paper deals with the use of modelling and simulation tools for preparation and implementation of exercises of Integrated Rescue System components and crisis management bodies with the main emphasis on the use of means of constructive simulation using SIMEX simulator. A scenario of multiple traffic accident was prepared for the crisis management authorities. Activities performed by crisis management...
A large portion of data mining and analytic services use modern machine learning techniques, such as deep learning. The state-of-the-art results by deep learning come at the price of an intensive use of computing resources. The leading frameworks (e.g., TensorFlow) are executed on GPUs or on high-end servers in datacenters. On the other end, there is a proliferation of personal devices with possibly...
SVM (Support Vector Machine), a state of the art classifier model is implemented on a computational mobile platform and its performances are evaluated against a low complexity classifier such as SFSVC (Super Fast Vector Support Classifier) on the same platform. For a better comparison, similar implementation for the two architectures are considered, such as using the same basic linear algebra library...
In this paper, we explore the use of recent conditional generative adversarial network framework for image to image translation applied to the domain of heterogeneous face sketch synthesis. Since the inception of the adversarial framework in 2014, great success has been noted with several variants till date. Further, we introduce a new dataset for composite sketch images. In particular we explore...
Anomaly detection is the process of identifying unusual signals in a set of observations. This is a vital task in a variety of fields including cybersecurity and the battlefield. In many scenarios, observations are gathered from a set of distributed mobile or small form factor devices. Traditionally, the observations are sent to centralized servers where large-scale systems perform analytics on the...
Deep learning techniques are able to process and learn from data (e.g., images, video, audio) without explicit feature extraction. As a result, not only is the manual workload to build such models reduced, but the performance and accuracy of these models can often outperform those in which the preprocessing phase embeds human intuition. In the light of these advancements this study aims to examine...
Human action recognition in video is highly challenging due to the substantial variations in motion performance, recording settings and inter-personal differences. Most current research focuses on the extraction of effective features and the design of suitable classifiers. Conversely, in this paper we tackle this problem by a dissimilarity-based approach where classification is performed in terms...
Virtual accident scenes in specific environments are simulated via the virtual reality technology. In the light of emergency rescue principles, trainees are allowed to mobilize and deploy emergency rescue forces, and work out combat schemes to control the development and expansion of accidents. In addition, based on the tactical knowledge repository, the system carries out logical reasoning for combat...
Automated Planning focuses on plan search. Traditionally, it aimed at domain-independent methods with handcrafted domain models. However, automated domain model acquisition, especially the action model acquisition is difficult. On the other hand, many problem specific search space pruning techniques were proposed. Therefore, we combine the automated domain model acquisition and problem specific search...
E-learning is the application of IT and Internet in education to make it easier, spacious, and more efficient. Advantages of e-learning are recognized, but its impact on learning achievement and knowledge transferring are not confirmed clearly. Learning is considered the skills of students and knowledge gained through experience in the training process. Learning achievement has been defined as students'...
It is a challenge to precisely predict hand grasps based on EMG signals given practical scenarios, due to its inherent nature. This paper proposes a solution to tackle the challenge with a force-driven granular model (FDGM). The problem of n-class hand grasp classification has been represented as force-based granular modelling, in which a number of granules are constructed for each class relying on...
The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) has been widely used to build image classification model which allow researchers transfer the pre-trained learning model for other classifications. We propose a transfer learning method to detect breast cancer using histopathology...
This paper contributes to the development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed SC networks (SCNs). In contrast to the existing randomized learning algorithms for single layer feed-forward networks, we randomly assign the input weights and biases of the hidden nodes in the light of a supervisory...
Word2Vec (Word to Vector) processes natural language by calculating the cosine similarity. However, the serial algorithm of original Word2Vec fails to satisfy the demands of training of corpus text because of the explosive growth of information. It has become the bottleneck owing to its comparatively low processing efficiency. The High Performance Computing (HPC) specializes in improving the calculation...
In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g. intelligent image manipulation. We attempt to accomplish such synthesis: given a source image and a target text description, our model synthesizes images to meet two requirements: 1) being realistic while matching the target text description; 2) maintaining...
We propose an efficient and unified framework, namely ThiNet, to simultaneously accelerate and compress CNN models in both training and inference stages. We focus on the filter level pruning, i.e., the whole filter would be discarded if it is less important. Our method does not change the original network structure, thus it can be perfectly supported by any off-the-shelf deep learning libraries. We...
This paper introduces a probabilistic latent variable model to address unsupervised domain adaptation problems. Specifically, we tackle the task of categorization of visual input from different domains by learning projections from each domain to a latent (shared) space jointly with the classifier in the latent space, which simultaneously minimizes the domain disparity while maximizing the classifier's...
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.