This paper provides insights of an advanced architecture for authoring and consumption of second screen content aiming to develop innovative functionalities for enjoying multimedia content by connecting it to other related content, augmenting it with virtual information of interest, and allowing navigation of the 3D reconstruction of the scene. Innovative technology and the underlying architecture for efficient production of second screen applications is described, which includes novel front-end authoring tools as well as back-end enabling technologies such as visual search, media structure analysis and 3D A/V reconstruction to support new editorial workflows. A strong commitment on standardisation by the project's partners ensures the future-proof utility of the results.
Question answering systems use information retrieval (IR) and information extraction (IE) methods to retrieve documents containing a valid answer. Question classification plays an important role in the question answer frame to reduce the gap between question and answer. This paper presents our research work on automatic question classification through machine learning approaches. We have experimented with machine learning algorithms Support Vector Machines (SVM) using kernel methods. An effective way to integrate syntactic structures for question classification in machine learning algorithms is the use of tree kernel (TK) functions. Here we use SubSet Tree kernel with Bag of words. Trade-off between training error and margin, Cost-factor and the decay factor has significant impact when we use SVM for the mentioned kernel type. The experiments determined the individual impact for Trade-off between training error and margin, Cost-factor and the decay factor and later the combined effect for Trade-off between training error and margin, Cost-factor. Depending on these result we also figure out some hyperplanes which can maximize the performance. Based on some standard data set outcomes of our experiment for question classification is promising.
Lasers are currently used for a wide spectrum of medical applications, including the treatment of eye disorders. When combined with digital image processing techniques, the issue of retinal image segmentation becomes of high importance. In this paper, our purpose is twofold: i) to identify and briefly present the existing approaches for the retinal image segmentation and ii) to test our hypothesis that the Viola-Jones algorithm-initially designed for face detection-can be suited as well for optical disc detection.
The media consumption has become more individualized and customized due to the development of digital media and of more efficient portable devices. Among other fields, linguistic learning may benefit greatly from this trend if new types of content are created, specifically for the requirements of this new generation of learners, suitable for individual usage, portable, customized, flexible, interactive and entertaining. In this paper we present a solution that has its roots in the Edutainment (Education and entertainment) field and consists in automatically generating language comprehension quizzes based on foreign-language audiovisual content (TV series, documentaries, news). The proposed approach turns any foreign-language video into a true interactive teaching material, by combining different fields of expertise, such as video analysis and meta-data extraction, information search and automatic language processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.