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 propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively...
We propose “Areas of Attention”, a novel attentionbased model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attentionbased approaches that associate image regions only to the RNN state, our method allows a direct association between caption...
Even though the various features of satirical language have been studied in computational linguistics, most of the research works have relied on the performance of the single machine learning algorithm. However, the implicit traits embedded in the language demand more certain, precise and accurate combination powers of an individual algorithm. In this study, we analyzed the performance of emotion-based...
The questions of training simulators development technique for oil and gas industry automation control systems are considered. The possibility of using this technique for control systems based on mathematical and algorithmic control models is introduced. A mathematical model is used. The training simulator operating result is the process studying, learning management skills, adjusting parameters to...
Human behavior understanding is a well-known area of interest for computer vision researchers. This discipline aims at evaluating several aspects of interactions among humans and system components to ensure long term human well-being. The robust human posture analysis is a crucial step towards achieving this target. In this paper, the deep representation learning paradigm is used to analyze the articulated...
We propose herein a data-driven dead-zone (DZ) compensation strategy using a model-free Virtual Reference Feedback Tuning (VRFT) approach. The VRFT tuning scheme is accommodated for two controller structures: the first one which explicitly includes a model of the DZ inverse to be identified and the second one which uses a Neural Network (NN) to model the controller to be identified. The main question...
For applications in robot manipulate with object, get the pose of objects is very important for controller's subsequent operations, especially in PCB feeding and blanking field, the grasp success rate will be enhanced if robot can get a exact pose of objects that relative to end manipulator. So in this paper we utilize the CNN model to build on a neural network for 3 tasks: object recognition, location...
The current focus of our research is to detect and classify the plant disease in agricultural domain, by implementing image processing techniques. We aim to propose an innovative set of statistical texture features for classification of plant diseases images of leaves. The input images are taken by various mobile cameras. The Scale-invariant feature transform (SIFT) features used as texture feature...
Technical solution skills — though important — are not enough for effective, multicultural teamwork. Despite broad consensus on the vital function of communication- and social skills, they tend to be underrepresented in the training of software-engineers and project managers. This is partly because such skills are less explicit than technical methods, tools, and artefacts. To address this deficiency,...
In this study, we investigated the effects of mastering multiple scripts in handwritten character recognition by means of computational simulations. In particular, we trained a set of deep neural networks on two different datasets of handwritten characters: the HODA dataset, which is a collection of images of handwritten Persian digits, and the MNIST dataset, which contains Latin handwritten digits...
Most present methods of saliency detection emphasize too much on the local contrast while ignore the global feature of image. The detailed characteristics of the image can be reflected based on the local comparison of image. However, the overall saliency of the image cannot be reflected. In this paper, a saliency detection model combined local and global features was proposed. Firstly, a local feature...
This paper presents a support vector machine (SVM) based model predictive control (MPC) strategy to manage the engine speed to the set-point of idle speed. The predictive model is trained by SVM due to its accuracy of learning nonlinear process, simple training program and no over-fitting nature. To reduce the computational burden of controller and retain the dynamic information of system, the instantaneous...
We consider the problem of link prediction in dynamic networks under the condition of a set of snapshots of the networks. To address the nonlinear transitional patterns in network structures, we propose an approach that incorporates the historical linkage and neighboring information into the restricted Boltzmann machine (RBM) model by adding temporal and neighboring connections between the hidden...
Region of Interest (ROI) crowd counting can be formulated as a regression problem of learning a mapping from an image or a video frame to a crowd density map. Recently, convolutional neural network (CNN) models have achieved promising results for crowd counting. However, even when dealing with video data, CNN-based methods still consider each video frame independently, ignoring the strong temporal...
Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that...
In this paper, we propose a CNN-based framework for online MOT. This framework utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame. Simply applying single object tracker for MOT will encounter the problem in computational efficiency and drifted results caused by occlusion. Our framework achieves computational efficiency by sharing...
Recent studies have shown that the performance of single-image super-resolution methods can be significantly boosted by using deep convolutional neural networks. In this study, we present a novel single-image super-resolution method by introducing dense skip connections in a very deep network. In the proposed network, the feature maps of each layer are propagated into all subsequent layers, providing...
Riding on the waves of deep neural networks, deep metric learning has achieved promising results in various tasks by using triplet network or Siamese network. Though the basic goal of making images from the same category closer than the ones from different categories is intuitive, it is hard to optimize the objective directly due to the quadratic or cubic sample size. Hard example mining is widely...
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen...
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present...
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.