Keystroke inference attacks are a form of side-channel attacks in which an attacker leverages various techniques to recover a user's keystrokes as she inputs information into some display (e.g., while sending a text message or entering her pin). Typically, these attacks leverage machine learning approaches, but assessing the realism of the threat space has lagged behind the pace of machine learning advancements, due in-part, to the challenges in curating large real-life datasets. We aim to overcome the challenge of having limited number of real data by introducing a video domain adaptation technique that is able to leverage synthetic data through supervised disentangled learning. Specifically, for a given domain, we decompose the observed data into two factors of variation: Style and Content. Doing so provides four learned representations: real-life style, synthetic style, real-life content and synthetic content. Then, we combine them into feature representations from all combinations of style-content pairings across domains, and train a model on these combined representations to classify the content (i.e., labels) of a given datapoint in the style of another domain. We evaluate our method on real-life data using a variety of metrics to quantify the amount of information an attacker is able to recover. We show that our method prevents our model from overfitting to a small real-life training set, indicating that our method is an effective form of data augmentation, thereby making keystroke inference attacks more practical.

In this work, we propose "tangent images," a spherical image representation that facilitates transferable and scalable 360 degree computer vision. Inspired by techniques in cartography and computer graphics, we render a spherical image to a set of distortion-mitigated, locally-planar image grids tangent to a subdivided icosahedron. By varying the resolution of these grids independently of the subdivision level, we can effectively represent high resolution spherical images while still benefiting from the low-distortion icosahedral spherical approximation. We show that training standard convolutional neural networks on tangent images compares favorably to the many specialized spherical convolutional kernels that have been developed, while also scaling efficiently to handle significantly higher spherical resolutions. Furthermore, because our approach does not require specialized kernels, we show that we can transfer networks trained on perspective images to spherical data without fine-tuning and with limited performance drop-off. Finally, we demonstrate that tangent images can be used to improve the quality of sparse feature detection on spherical images, illustrating its usefulness for traditional computer vision tasks like structure-from-motion and SLAM.

We propose a primary visual cortex inspired oriented edge feature for object pose estimation. The neural feedback like feature is based on a Center-Surround Contrast excitation and a k-Winner-Take-AU inhibition, to extract different orientations of edge response from an image patch. To compute local descriptor, we model each oriented edge response with a PDF distribution, before concatenating their attributes from all orientations. To choose a suitable PDF candidate during training, we ran a similarity test fit between empirical and parametric statistics. We train a bank of binary view pose classifiers using SVM on dense features with Spatial Pyramid Representation [15]. We evaluate and compare the Mean Average Precision of our proposed descriptor with HOG [6] for pose estimation evaluation. Lastly, we showed that using our proposed feature over baseline resulted in a gain of nearly 15% on the EPFL Multi-View Car Dataset [2].

This paper introduces a novel antipodal-epipolar constraint on relative camera motion. By using antipodal points, which are available in large Field-of-View cameras, the translational and rotational motions of a camera are geometrically decoupled, allowing them to be separately estimated as two problems in smaller dimensions. We present a new formulation based on discrete camera motions, which works over a larger range of motions compared to previous differential techniques using antipodal points. The use of our constraints is demonstrated with two robust and practical algorithms, one based on RANSAC and the other based on Hough-like voting. As an application of the motion decoupling property, we also present a new structure-from-motion algorithm that does not require explicitly estimating rotation (it uses only the translation found with our methods). Finally, experiments involving simulations and real image sequences will demonstrate that our algorithms perform accurately and robustly, with some advantages over the state-of-the-art.

We develop a convex relaxation of maximum a posteriori estimation of a mixture of regression models. Although our relaxation involves a semidefinite matrix variable, we reformulate the problem to eliminate the need for general semidefinite programming. In particular, we provide two reformulations that admit fast algorithms. The first is a max-min spectral reformulation exploiting quasi-Newton descent. The second is a min-min reformulation consisting of fast alternating steps of closed-form updates. We evaluate the methods against Expectation-Maximization in a real problem of motion segmentation from video data.

We present a novel geometrical constraint on the egomotion of a single, moving camera. Using a camera with a large field-of-view (FOV), the optical flow measured at a single pair of antipodal points on the image sphere constrains the set of all possible camera motion directions to a subset region. By considering the flow at many such antipodal point pairs, it is shown that the intersection of all subset regions arising from each pair yields an estimate on the directions of motion. These antipodal point constraints rely on the geometrical properties of using a spherical representation of the image as well as the larger information content available from a large FOV. An algorithm using these constraints was implemented and tested on both simulated and real images. Results show comparable performance to the state of the art in the presence of noise and outliers whilst processing in constant time.

The increasing number of international negotiations involving multiple languages has triggered a growing reliance on computer-based multilingual support. Whereas empirical studies on negotiation support systems (NSS) have shown that NSS generally improve negotiation performance, very few NSS exist that cater for multilingual negotiations. With multilingual support, international negotiators of different language backgrounds are expected to address communication barriers and problems. This study involves the development of an NSS prototype with multilingual support as well as a laboratory experiment to examine the efficacy of such support on six important negotiation outcome variables (individual outcome, joint outcome, equality of outcome, time to settlement, satisfaction with process and satisfaction with outcome). Findings suggested significant effects of NSS support on individual outcome and joint outcome. Multilingual support helped to improve equality of outcome (under qualified conditions), but the time taken was significantly longer. The paper underlines the possibility and significance of computer-based multilingual support to address diverse linguistic groups in global negotiation context.

This paper develops an algorithm for estimating the epipole or direction of translation of a moving monocular observer. To this end, we use constraints arising from two points that are antipodal on the image sphere. The antipodal point condition is necessary for decoupling rotation from translation. One such pair of points constrains the epipole to lie on a plane, and using two pairs of points, we have two such planes. The intersection of these two planes gives an estimate of the epipole. This means we require image motion measurements at two pairs of antipodal points to obtain an estimate. Repeating this will yield a set of possible solutions and a variety of methods could be applied to obtain a robust and refined estimate from this set. One robust and simple method is chosen for illustrative purposes and results on real images are shown. With real sequences, results of below 2deg error in the estimate of the epipole can be obtained. Since antipodal points on an image sphere are required, this algorithm must use some kind of omnidirectional or large field-of-view (FOV) sensor.

Business negotiations, as a ubiquitous phenomenon in international marketplaces, are becoming more complex and prevalent as a result of globalization of today’s world economy. This has made the possibility of computer support very appealing. Whereas past studies of negotiation support systems (NSS) have examined the potential benefits of supporting negotiations, computer support for pre-negotiation activities has been largely ignored in so far as empirical work is concerned. The current article addresses this gap by categorizing negotiation activities into the pre-negotiation phase and the negotiation phase, and reports on an experimental study of the impact of NSS on the different phases of negotiation. Results show that both pre-negotiation and negotiation support improved gains in outcome with increased time in reaching agreement. In addition, pre-negotiation support led to more equal outcomes for negotiating dyads. The findings show the usefulness of NSS in enhancing the quality of differing stages of negotiation. Further, it is to note that this article recognizes the important role of culture in the negotiation setting, and discusses its pertinence with respect to the context of the current study. The corresponding implications and conclusions are highlighted.

Online transactions have become increasingly popular and deserve greater attention from a research perspective. Whereas there are various aspects of online transactions, this study specifically examined an online bargaining scenario utilizing software agents. User’s performance and attitudes were studied in a 2x2 factorial-design experiment. The independent variables were power distance (a dimension of culture)-for reasons associated with increasing and irresistible globalization, and explanation facility-for its conjecturable benefits in helping users to better understand and work with their software agents. Results showed these factors to have an interaction effect on task performance; as well, explanation facility exhibited main effects on trust and satisfaction. The findings have implications for system designers and builders; they also help managers in tailoring their expectations on what technology can deliver-under which conditions.

This paper deals with the use of a group support system (GSS) to support virtual team-building. Literature review on Group Support Systems (GSS) indicates that most prior GSS research focuses on supporting face-to-face teamwork, and few studies were conducted in supporting virtual teamwork and team-building. When virtual teamwork becomes more common in modern organizations, how GSS can be used to enhance virtual team-building is becoming an important research issue. This paper proposes a conceptual team-building framework. By embedding this conceptual framework into a GSS, the GSS may have the potential to support virtual team-building. Based on the framework, a set of testable research propositions is formulated, and some suggestions for future GSS research are discussed.

Negotiations are often not as rational as desired due to the cognitive difficulty of finding optimal agreements. With higher information-processing capacity and capability, negotiation support systems (NSS) are viewed as a viable solution to overcome this difficulty and help negotiators achieve integrative agreements. In addition, advances in network communication technology have enabled distributed meetings to be carried out easily. This in turn leads to the notion of conducting distributed negotiations by combining NSS and distributed communication technology. This study examined the impact of NSS in face-to-face and distributed settings. The results suggested that NSS led to higher and fairer outcomes for both face-to-face and distributed dyads. Another interesting finding from this study is that there were gains with respect to initial expectations of outcomes when NSS support was provided. As corporations expand globally, NSS will play a significant role in coordinating distributed negotiations, saving time and cost.