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.
Estimating a depth map from multiple views of a scene is a fundamental task in computer vision. As soon as more than two viewpoints are available, one faces the very basic question how to measure similarity across >2 image patches. Surprisingly, no direct solution exists, instead it is common to fall back to more or less robust averaging of two-view similarities. Encouraged by the success of machine...
Distributed computing platforms provide a robust mechanism to perform large-scale computations by splitting the task and data among multiple locations, possibly located thousands of miles apart geographically. Although such distribution of resources can lead to benefits, it also comes with its associated problems such as rampant duplication of file transfers increasing congestion, long job completion...
Mobile phones equipped with a monocular camera and an inertial measurement unit (IMU) are ideal platforms for augmented reality (AR) applications, but the lack of direct metric distance measurement and the existence of aggressive motions pose significant challenges on the localization of the AR device. In this work, we propose a tightly-coupled, optimization-based, monocular visual-inertial state...
In this paper we present an optimization algorithm for simultaneously detecting video freeze and obtaining the minimum number of the frame required in motion intention estimation for real time robust video stabilization on multirotor unmanned aerial vehicles. A combination of a filter and a threshold is used to the video freeze detection, and for optimizing the algorithm, we find the minimum number...
Study on the design of a robust network against malicious attacks has gained increased interest in various areas such as wireless communications networks. One of the main obstacles towards finding the optimum robust network is the large number of possible network configurations. In this paper, we propose a novel method to design robust networks against malicious attacks based on the network degree...
In this paper, the problem of single-channel blind source separation (SCBSS) of a mixture of two co-frequency phase-shift keying (PSK) signals with unknown carrier frequency offsets (CFOs) is investigated. Two SCBSS algorithms which are robust to CFOs are proposed to perform separation of the mixture signals. In the first algorithm, the phase changes of the received signals caused by CFOs are tracked...
It is well accepted that we learn hard lessons when implementing and re-evaluating systems, yet it is also acknowledged that science faces a crisis in reproducibility. Experimental computer science is far from immune, although it should be easier for CS than other sciences, given the emphasis on experimental artifacts, such as source code, data sets, workflows, parameters, etc. The data management...
In this paper we examine the effects of using object poses as guidance to learning robust features for 3D object pose estimation. Previous works have focused on learning feature embeddings based on metric learning with triplet comparisons and rely only on the qualitative distinction of similar and dissimilar pose labels. In contrast, we consider the exact pose differences between the training samples,...
The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images. While deep metric learning has yielded impressive performance gains by extracting high level abstractions from image data, a proper objective loss function becomes the central issue to boost the performance. In this paper,...
We investigate the problem of person search in the wild in this work. Instead of comparing the query against all candidate regions generated in a query-blind manner, we propose to recursively shrink the search area from the whole image till achieving precise localization of the target person, by fully exploiting information from the query and contextual cues in every recursive search step. We develop...
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To overcome these difficulties, in this work we propose a Pose-driven Deep Convolutional (PDC) model to learn...
To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the training convergence of this triplet model can be compromised by the fact that the vast majority of the...
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings. In this work, we show how to improve the robustness of embeddings by exploiting independence in ensembles. We divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each...
Current image captioning methods are usually trained via maximum likelihood estimation. However, the log-likelihood score of a caption does not correlate well with human assessments of quality. Standard syntactic evaluation metrics, such as BLEU, METEOR and ROUGE, are also not well correlated. The newer SPICE and CIDEr metrics are better correlated, but have traditionally been hard to optimize for...
Over a decade of continual expansion in networking and cloud computing has naturally created an increased demand for cybersecurity solutions. Due to the large number of communication devices and content, it is ideal that these cybersecurity solutions are automated. Unfortunately, malicious content and/or activity is often designed to “look” normal and new malicious attacks are repeatedly being developed...
In this paper the calculations of the robustness of a network is addressed. After a brief description of the most relevant metrics, our Network Robustness Simulator(NRS) is presented as well as its structure and working model. The NRS computes the robustness I a dynamic scenario, it copes with multiple failures and different types of attack. In particular, the addition of the epidemic based model...
Content Delivery Networks (CDNs) are a key en-abler for the distribution of large amounts of data with high capacity and low latency. For instance, content streaming companies extensively use geographical distribution and replication to meet the ever-growing demand for media. Optical networks are the only future-proof technology available that meets the reach and capacity requirements of CDNs. However,...
The extreme growth in deployment of cloud based services along with applications requiring high computational complexity has had an adverse effect on energy consumption in data centers. When cloud data centers add more computing capacity and increase in size, they generate more heat, require extra cooling. To counter this effect, energy dissipation must be reduced. Servers consume power even when...
This paper uses results from geometric mechanics and control to determine the degree of coupling between actuated and unactuated degrees of freedom in a two-link biped robot. By comparing the degree of coupling when ankle actuation is used and when hip actuation is used, it is clear that ankle actuation affords stronger dynamic coupling and hence, may provide a superior means for control design for...
Previous models based on Deep Convolutional Neural Networks (DCNN) for face verification focused on learning face representations. The face features extracted from the models are applied to additional metric learning to improve a verification accuracy. The models extract high-dimensional face features to solve a multi-class classification. This results in a dependency of a model on specific training...
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.