We propose an architecture based on Convolutional Neural Networks (CNNs) for the detection of motion boundaries from two consecutive images of a video sequence. Existing learning-based approaches start with dense optical flow estimates, which are expensive to compute and often fail near motion boundaries, exactly where they are needed most. In contrast, we explore ways to detect motion boundaries without first computing optical flow. For efficiency, we hypothesize that motion boundaries occur at or near the edges of superpixels in an over-segmentation of the first image.
Providing a satisfactory quality of experience (QoE) to Internet users is crucial for content and service providers. When users get bad QoE from an application, such as the videos they are watching on a streaming provider keep freezing or the shopping Web site they are visiting takes a long time to load, they often spend less time on the application, return to it less frequently, or even worse they might switch to an alternative application, in all cases hurting the business financially.
Tenure-Track Faculty Positions in Computer Science
Duke University invites applications and nominations for four tenure-track or tenured faculty positions in all areas of computer science, and for two additional joint positions between Computer Science and other departments. Areas include artificial intelligence, machine learning, computer systems, security and privacy, database systems, computer vision, algorithms, optimization, as well as interdisciplinary work that relates to the social sciences or biological sciences. Positions are at all ranks and to begin July 2019. More information
Grad Student Awards 2017-18
Graduate student awards for 2017-18 were presented at the 2018 annual departmental meeting. More