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.
The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, label noise has been treated as statistical outliers, and techniques such as importance re-weighting and bootstrapping have been proposed to alleviate the problem. According to our observation, the real-world noisy labels...
Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing...
This work proposes Recurrent Neural Network (RNN) models to predict structured ‘image situations’ – actions and noun entities fulfilling semantic roles related to the action. In contrast to prior work relying on Conditional Random Fields (CRFs), we use a specialized action prediction network followed by an RNN for noun prediction. Our system obtains state-of-the-art accuracy on the challenging recent...
Super resolution is the problem of artificially enlarging a low resolution photograph to recover a plausible high resolution version. In the regime of high magnification factors, the problem is dramatically underspecified and many plausible, high resolution images may match a given low resolution image. In particular, traditional super resolution techniques fail in this regime due to the multimodality...
The efficient development of all-digital RF-transmitters (DRFTx) requires models that can capture the memory induced, nonlinear behavior of the circuitry. Broadband time-domain models work well for this application, although, gaining dependable model prediction errors from verification measurements is difficult. For the presented DRFTx, the model predicts output signals over the full bandwidth (DC-20...
With the availability of medical data for large number of patients in hospitals, early detection of diseases has been made easier in the recent past. Conditions like Infertility which are hard to detect or diagnose can be now diagnosed with greater precision with the help of predictive modeling. One of the key challenges for early detection and timely treatment is in identifying and recording key...
Many existing scene parsing methods adopt Convolutional Neural Networks with fixed-size receptive fields, which frequently result in inconsistent predictions of large objects and invisibility of small objects. To tackle this issue, we propose a scale-adaptive convolution to acquire flexiblesize receptive fields during scene parsing. Through adding a new scale regression layer, we can dynamically infer...
Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem. Our approach is a joint image pixel and word concept embeddings framework, where word concepts...
In complex industrial environment, there are many interference objects when detect the objects on the production line. The interference objects are very similar with the objects to be sorted in terms of color, shape and size. The existing detection method like edge detection and object segmentation is difficult to recognize the objects when it comes to complex industrial environment. In the complex...
Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands of images per class for training is infeasible in such a scenario, prompting the use of webly supervised data. This paper explores the training of image-recognition systems on large numbers of images and associated user...
Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For example, in object detection, many objects of interest often go unlabeled, and in human pose estimation, occluded joints are often labeled with ambiguous...
Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space. The key idea is to impose the structural constraint that semantic representations...
This paper proposes a development's prediction model based on Artificial Neural Network. The methodology proposed consists in: i) countries selection; ii) selection and obtainment of indicators referring to the selected countries; iii) proposal prediction model; iv) Artificial Neural Network training and validation. The results indicated predicted values close to the real values of the Brazilian indicators...
This paper introduces an ensemble model that solves the binary classification problem by incorporating the basic Logistic Regression with the two recent advanced paradigms: extreme gradient boosted decision trees (xgboost) and deep learning. To obtain the best result when integrating sub-models, we introduce a solution to split and select sets of features for the sub-model training. In addition to...
This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the context of a more general project related to the development of an AI engine for video games, called Grail. We also discuss the outcomes of this challenge and...
The following article is created as a result of the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone. The Challenge goal was to correctly predict which bot would win a bot-vs-bot Hearthstone match based on what was known at the given time. Hearthstone is an online two-players card game with imperfect information (unlike chess and go, and like poker), where the goal of one player is to...
The benefits of well-informed water management systems are related to the forecasting skills of hydrological variables. These benefits can be reflected in reducing economic and social losses to come. Therefore, the optimal design of water management projects frequently involves finding the methods or techniques that generate long sequences of hydrological data. These sequences considered as time series...
Road traffic accident is a serious threat to human life and safety of living environment. In this paper, a new road traffic accident prediction model (TAP-CNN) is established by using traffic accident influencing factors, such as traffic flow, weather, light to build a state matrix to describe the traffic state and CNN model. This paper uses samples to test the accuracy of the new model. The experimental...
Environment monitoring is a challenging task owing to its ever changing dynamics. Furthermore, deploying a team of resource constrained robots to persistently monitor the environment encompasses intelligently selecting the training samples which are spread across a significantly large area to conservatively spend the resources allocated. In order to accomplish this using a team of fully autonomous...
In this paper, we present a model for rainfall rate prediction 30 seconds ahead of time using an artificial neural network. The resultant predicted rainfall rate can then be used in determining an appropriate fade counter-measure, for instance, digital modulation scheme ahead of time, to keep the bit error rate (BER) on the link within acceptable levels to allow constant flow of data on the link during...
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.